{
 "license": "SI-IQ values, ranks and intervals: CC BY 4.0 (IQ of SI); input scores and prices keep their sources' licences (see /data/LICENSES.md)",
 "attribution": "Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.",
 "method_version": "1.0.0",
 "calibration": {
  "calibrated_at": "2026-10-18T16:18:22Z",
  "calibration_id": "a75ecba7e64a",
  "inputs": {
   "ai-co-mathematician|frontiermath_t4": 0.756,
   "claude-2-1|gpqa_diamond": 0.32954545454545453,
   "claude-2-1|otis_mock_aime": 0.019444444444444445,
   "claude-2|gpqa_diamond": 0.3465909090909091,
   "claude-2|math_level_5": 0.1172583081570997,
   "claude-2|otis_mock_aime": 0.025,
   "claude-3-5-haiku|aider_polyglot": 0.28,
   "claude-3-5-haiku|gpqa_diamond": 0.3813131313131313,
   "claude-3-5-haiku|math_level_5": 0.46355740181268884,
   "claude-3-5-haiku|otis_mock_aime": 0.043055555555555555,
   "claude-3-5-sonnet-october-2024|aider_polyglot": 0.516,
   "claude-3-5-sonnet-october-2024|gpqa_diamond": 0.553030303030303,
   "claude-3-5-sonnet-october-2024|math_level_5": 0.5694864048338368,
   "claude-3-5-sonnet-october-2024|otis_mock_aime": 0.08472222222222223,
   "claude-3-5-sonnet|gpqa_diamond": 0.5404040404040404,
   "claude-3-5-sonnet|math_level_5": 0.5168051359516617,
   "claude-3-5-sonnet|otis_mock_aime": 0.06527777777777778,
   "claude-3-7-sonnet|aider_polyglot": 0.649,
   "claude-3-7-sonnet|gpqa_diamond": 0.7973484848484849,
   "claude-3-7-sonnet|math_level_5": 0.9116314199395771,
   "claude-3-7-sonnet|otis_mock_aime": 0.5777777777777777,
   "claude-3-7-sonnet|swe_bench_verified": 0.609504132231405,
   "claude-3-haiku|gpqa_diamond": 0.3630050505050505,
   "claude-3-haiku|math_level_5": 0.1487915407854985,
   "claude-3-haiku|otis_mock_aime": 0.018055555555555554,
   "claude-3-opus|chess_puzzles": 0.03,
   "claude-3-opus|gpqa_diamond": 0.4715909090909091,
   "claude-3-opus|math_level_5": 0.37481117824773413,
   "claude-3-opus|otis_mock_aime": 0.04722222222222222,
   "claude-3-opus|simpleqa_verified": 0.126,
   "claude-3-sonnet|gpqa_diamond": 0.4059343434343434,
   "claude-3-sonnet|math_level_5": 0.18174093655589124,
   "claude-3-sonnet|otis_mock_aime": 0.025,
   "claude-fable-5-1|chess_puzzles": 0.48,
   "claude-fable-5-1|frontiermath_t13": 0.9017543859649123,
   "claude-fable-5-1|frontiermath_t4": 0.8780487804878049,
   "claude-fable-5-1|furniture_assembly": 0.7,
   "claude-fable-5-1|mystery_game_puzzles": 0.58,
   "claude-fable-5-1|or_gpqa_diamond": 0.8894498333333334,
   "claude-fable-5-1|or_tau2_airline": 0.7906666,
   "claude-fable-5-1|otis_mock_aime": 1.0,
   "claude-fable-5-1|simpleqa_verified": 0.708,
   "claude-fable-5|chess_puzzles": 0.47,
   "claude-fable-5|frontiermath_t13": 0.8701754385964913,
   "claude-fable-5|frontiermath_t4": 0.902,
   "claude-fable-5|furniture_assembly": 0.35833333333333334,
   "claude-fable-5|gpqa_diamond": 0.8585858585858586,
   "claude-fable-5|mystery_game_puzzles": 0.52,
   "claude-fable-5|or_gpqa_diamond": 0.8615317499999998,
   "claude-fable-5|or_tau2_airline": 0.7957576363636364,
   "claude-fable-5|otis_mock_aime": 1.0,
   "claude-fable-5|simpleqa_verified": 0.707,
   "claude-haiku-4-5|bfcl_overall": 0.687,
   "claude-haiku-4-5|chess_puzzles": 0.08,
   "claude-haiku-4-5|gpqa_diamond": 0.7121212121212122,
   "claude-haiku-4-5|math_level_5": 0.9636087945413192,
   "claude-haiku-4-5|or_gpqa_diamond": 0.7310605833333333,
   "claude-haiku-4-5|or_tau2_airline": 0.6657576363636364,
   "claude-haiku-4-5|otis_mock_aime": 0.6666666666666666,
   "claude-haiku-4-5|simpleqa_verified": 0.132,
   "claude-haiku-5-5|chess_puzzles": 0.55,
   "claude-haiku-5-5|frontiermath_t13": 0.7508771929824561,
   "claude-haiku-5-5|frontiermath_t4": 0.4634146341463415,
   "claude-haiku-5-5|furniture_assembly": 0.475,
   "claude-haiku-5-5|gpqa_diamond": 0.8964646464646465,
   "claude-haiku-5-5|mystery_game_puzzles": 0.3,
   "claude-haiku-5-5|or_gpqa_diamond": 0.8692479999999999,
   "claude-haiku-5-5|or_tau2_airline": 0.7577776666666667,
   "claude-haiku-5-5|otis_mock_aime": 0.9888888888888889,
   "claude-haiku-5-5|simpleqa_verified": 0.238,
   "claude-opus-4-1|frontiermath_t13": 0.12631578947368421,
   "claude-opus-4-1|frontiermath_t4": 0.024390243902439025,
   "claude-opus-4-1|gpqa_diamond": 0.7727272727272727,
   "claude-opus-4-1|mystery_game_puzzles": 0.21,
   "claude-opus-4-1|otis_mock_aime": 0.6888888888888889,
   "claude-opus-4-1|swe_bench_verified": 0.7334710743801653,
   "claude-opus-4-5|bfcl_overall": 0.7746999999999999,
   "claude-opus-4-5|chess_puzzles": 0.14,
   "claude-opus-4-5|frontiermath_t13": 0.34385964912280703,
   "claude-opus-4-5|frontiermath_t4": 0.04878048780487805,
   "claude-opus-4-5|furniture_assembly": 0.2833333333333333,
   "claude-opus-4-5|gpqa_diamond": 0.860479797979798,
   "claude-opus-4-5|mystery_game_puzzles": 0.22,
   "claude-opus-4-5|or_gpqa_diamond": 0.8610461538461541,
   "claude-opus-4-5|or_tau2_airline": 0.7700000714285714,
   "claude-opus-4-5|otis_mock_aime": 0.8611111111111112,
   "claude-opus-4-5|simpleqa_verified": 0.457,
   "claude-opus-4-5|swe_bench_verified": 0.7665289256198347,
   "claude-opus-4-6|chess_puzzles": 0.21,
   "claude-opus-4-6|frontiermath_t13": 0.6596491228070176,
   "claude-opus-4-6|frontiermath_t4": 0.2682926829268293,
   "claude-opus-4-6|furniture_assembly": 0.2833333333333333,
   "claude-opus-4-6|gpqa_diamond": 0.9053030303030303,
   "claude-opus-4-6|mystery_game_puzzles": 0.25,
   "claude-opus-4-6|or_gpqa_diamond": 0.856643153846154,
   "claude-opus-4-6|or_tau2_airline": 0.7638095,
   "claude-opus-4-6|otis_mock_aime": 0.9444444444444444,
   "claude-opus-4-6|simpleqa_verified": 0.47,
   "claude-opus-4-6|swe_bench_verified": 0.7871900826446281,
   "claude-opus-4-7|chess_puzzles": 0.41,
   "claude-opus-4-7|frontiermath_t13": 0.7017543859649122,
   "claude-opus-4-7|frontiermath_t4": 0.3170731707317073,
   "claude-opus-4-7|furniture_assembly": 0.3333333333333333,
   "claude-opus-4-7|gpqa_diamond": 0.9015151515151515,
   "claude-opus-4-7|mystery_game_puzzles": 0.28,
   "claude-opus-4-7|or_gpqa_diamond": 0.892375117408907,
   "claude-opus-4-7|or_tau2_airline": 0.7757142142857143,
   "claude-opus-4-7|otis_mock_aime": 0.978,
   "claude-opus-4-7|simpleqa_verified": 0.517,
   "claude-opus-4-7|swe_bench_verified": 0.8347107438016529,
   "claude-opus-4-8|chess_puzzles": 0.52,
   "claude-opus-4-8|frontiermath_t13": 0.8,
   "claude-opus-4-8|frontiermath_t4": 0.5609756097560976,
   "claude-opus-4-8|furniture_assembly": 0.425,
   "claude-opus-4-8|gpqa_diamond": 0.9103535353535354,
   "claude-opus-4-8|mystery_game_puzzles": 0.36,
   "claude-opus-4-8|or_gpqa_diamond": 0.8959834999999999,
   "claude-opus-4-8|or_tau2_airline": 0.7776190714285715,
   "claude-opus-4-8|otis_mock_aime": 0.9833333333333333,
   "claude-opus-4-8|simpleqa_verified": 0.53,
   "claude-opus-4|aider_polyglot": 0.72,
   "claude-opus-4|gpqa_diamond": 0.7626262626262627,
   "claude-opus-4|math_level_5": 0.850453172205438,
   "claude-opus-4|otis_mock_aime": 0.6444444444444445,
   "claude-opus-4|swe_bench_verified": 0.7066115702479339,
   "claude-opus-5-5|chess_puzzles": 0.67,
   "claude-opus-5-5|frontiermath_t13": 0.9122807017543859,
   "claude-opus-5-5|frontiermath_t4": 0.95,
   "claude-opus-5-5|furniture_assembly": 0.8333333333333334,
   "claude-opus-5-5|gpqa_diamond": 0.9059343434343434,
   "claude-opus-5-5|mystery_game_puzzles": 0.71,
   "claude-opus-5-5|or_gpqa_diamond": 0.9020199999999999,
   "claude-opus-5-5|or_tau2_airline": 0.756,
   "claude-opus-5-5|otis_mock_aime": 1.0,
   "claude-opus-5-5|simpleqa_verified": 0.722,
   "claude-opus-5|chess_puzzles": 0.43,
   "claude-opus-5|frontiermath_t13": 0.856140350877193,
   "claude-opus-5|frontiermath_t4": 0.7317073170731707,
   "claude-opus-5|furniture_assembly": 0.6083333333333333,
   "claude-opus-5|gpqa_diamond": 0.9387626262626263,
   "claude-opus-5|mystery_game_puzzles": 0.59,
   "claude-opus-5|or_gpqa_diamond": 0.8957629166666667,
   "claude-opus-5|or_tau2_airline": 0.7727272727272727,
   "claude-opus-5|otis_mock_aime": 0.9888888888888889,
   "claude-opus-5|simpleqa_verified": 0.599,
   "claude-sonnet-4-5|bfcl_overall": 0.7323999999999999,
   "claude-sonnet-4-5|chess_puzzles": 0.1,
   "claude-sonnet-4-5|frontiermath_t13": 0.23859649122807017,
   "claude-sonnet-4-5|frontiermath_t4": 0.024390243902439025,
   "claude-sonnet-4-5|gpqa_diamond": 0.8232323232323232,
   "claude-sonnet-4-5|math_level_5": 0.9773413897280967,
   "claude-sonnet-4-5|mystery_game_puzzles": 0.17,
   "claude-sonnet-4-5|or_gpqa_diamond": 0.8111110666666667,
   "claude-sonnet-4-5|or_tau2_airline": 0.7528572857142857,
   "claude-sonnet-4-5|otis_mock_aime": 0.7777777777777778,
   "claude-sonnet-4-5|simpleqa_verified": 0.307,
   "claude-sonnet-4-5|swe_bench_verified": 0.7128099173553719,
   "claude-sonnet-4-6|chess_puzzles": 0.23,
   "claude-sonnet-4-6|gpqa_diamond": 0.8737373737373737,
   "claude-sonnet-4-6|mystery_game_puzzles": 0.16,
   "claude-sonnet-4-6|or_gpqa_diamond": 0.6459467692307692,
   "claude-sonnet-4-6|or_tau2_airline": 0.7490475714285715,
   "claude-sonnet-4-6|otis_mock_aime": 0.857936507936508,
   "claude-sonnet-4-6|simpleqa_verified": 0.355,
   "claude-sonnet-4-6|swe_bench_verified": 0.7520661157024794,
   "claude-sonnet-4|aider_polyglot": 0.613,
   "claude-sonnet-4|gpqa_diamond": 0.7918781725888325,
   "claude-sonnet-4|math_level_5": 0.8436555891238671,
   "claude-sonnet-4|or_gpqa_diamond": 0.7672559999999999,
   "claude-sonnet-4|or_tau2_airline": 0.64,
   "claude-sonnet-4|otis_mock_aime": 0.7111111111111111,
   "claude-sonnet-5-5|chess_puzzles": 0.59,
   "claude-sonnet-5-5|frontiermath_t13": 0.887719298245614,
   "claude-sonnet-5-5|frontiermath_t4": 0.8048780487804879,
   "claude-sonnet-5-5|furniture_assembly": 0.75,
   "claude-sonnet-5-5|gpqa_diamond": 0.9558080808080808,
   "claude-sonnet-5-5|mystery_game_puzzles": 0.65,
   "claude-sonnet-5-5|or_gpqa_diamond": 0.92929275,
   "claude-sonnet-5-5|or_tau2_airline": 0.775,
   "claude-sonnet-5-5|otis_mock_aime": 1.0,
   "claude-sonnet-5-5|simpleqa_verified": 0.465,
   "claude-sonnet-5|chess_puzzles": 0.45,
   "claude-sonnet-5|frontiermath_t13": 0.656140350877193,
   "claude-sonnet-5|frontiermath_t4": 0.2926829268292683,
   "claude-sonnet-5|gpqa_diamond": 0.9053030303030303,
   "claude-sonnet-5|mystery_game_puzzles": 0.35,
   "claude-sonnet-5|or_gpqa_diamond": 0.8576035833333334,
   "claude-sonnet-5|or_tau2_airline": 0.76,
   "claude-sonnet-5|otis_mock_aime": 0.9472222222222222,
   "claude-sonnet-5|simpleqa_verified": 0.337,
   "cohere-command-a|bfcl_overall": 0.46490000000000004,
   "dbrx|gpqa_diamond": 0.32891414141414144,
   "dbrx|math_level_5": 0.11650302114803625,
   "deepseek-r1-0528-qwen3-8b|gpqa_diamond": 0.0928030303030303,
   "deepseek-r1-0528-qwen3-8b|otis_mock_aime": 0.4388888888888889,
   "deepseek-r1-distill-llama-70b|gpqa_diamond": 0.5574494949494949,
   "deepseek-r1-distill-llama-70b|math_level_5": 0.8989803625377644,
   "deepseek-r1-distill-llama-70b|otis_mock_aime": 0.5138888888888888,
   "deepseek-r1-distill-qwen-1-5b|gpqa_diamond": 0.33585858585858586,
   "deepseek-r1-distill-qwen-1-5b|otis_mock_aime": 0.21388888888888888,
   "deepseek-r1-distill-qwen-14b|gpqa_diamond": 0.44696969696969696,
   "deepseek-r1-distill-qwen-14b|math_level_5": 0.8712235649546828,
   "deepseek-r1-distill-qwen-14b|otis_mock_aime": 0.5055555555555555,
   "deepseek-r1-distill-qwen-32b|gpqa_diamond": 0.6414141414141414,
   "deepseek-r1-distill-qwen-32b|otis_mock_aime": 0.5555555555555556,
   "deepseek-r1-may-2025|gpqa_diamond": 0.7632575757575758,
   "deepseek-r1-may-2025|math_level_5": 0.9663897280966768,
   "deepseek-r1-may-2025|or_gpqa_diamond": 0.7851099187817259,
   "deepseek-r1-may-2025|or_tau2_airline": 0.47874697986577186,
   "deepseek-r1-may-2025|otis_mock_aime": 0.6638888888888889,
   "deepseek-r1|aider_polyglot": 0.569,
   "deepseek-r1|gpqa_diamond": 0.7171717171717171,
   "deepseek-r1|math_level_5": 0.9305135951661632,
   "deepseek-r1|otis_mock_aime": 0.5333333333333333,
   "deepseek-v3-1-terminus|or_gpqa_diamond": 0.7942762,
   "deepseek-v3-1-terminus|or_tau2_airline": 0.48266679999999995,
   "deepseek-v3-1|or_gpqa_diamond": 0.7707982259154932,
   "deepseek-v3-1|or_tau2_airline": 0.47222181249999995,
   "deepseek-v3-2-exp|aider_polyglot": 0.742,
   "deepseek-v3-2-exp|bfcl_overall": 0.5672999999999999,
   "deepseek-v3-2-exp|or_gpqa_diamond": 0.8265989999999999,
   "deepseek-v3-2-exp|or_tau2_airline": 0.693333,
   "deepseek-v3-2|or_gpqa_diamond": 0.802714625,
   "deepseek-v3-2|or_tau2_airline": 0.7193332,
   "deepseek-v3-mar-2025|gpqa_diamond": 0.6761363636363636,
   "deepseek-v3-mar-2025|math_level_5": 0.75547583081571,
   "deepseek-v3-mar-2025|or_gpqa_diamond": 0.646465,
   "deepseek-v3-mar-2025|or_tau2_airline": 0.4337431393442623,
   "deepseek-v3-mar-2025|otis_mock_aime": 0.37777777777777777,
   "deepseek-v3|gpqa_diamond": 0.5653409090909091,
   "deepseek-v3|math_level_5": 0.6485083081570997,
   "deepseek-v3|or_gpqa_diamond": 0.661616,
   "deepseek-v3|or_tau2_airline": 0.4053599698492462,
   "deepseek-v3|otis_mock_aime": 0.15833333333333333,
   "deepseek-v4-1-flash|chess_puzzles": 0.48,
   "deepseek-v4-1-flash|frontiermath_t13": 0.6736842105263158,
   "deepseek-v4-1-flash|frontiermath_t4": 0.2682926829268293,
   "deepseek-v4-1-flash|furniture_assembly": 0.3416666666666667,
   "deepseek-v4-1-flash|gpqa_diamond": 0.8983585858585859,
   "deepseek-v4-1-flash|mystery_game_puzzles": 0.43,
   "deepseek-v4-1-flash|or_gpqa_diamond": 0.8838381666666666,
   "deepseek-v4-1-flash|or_tau2_airline": 0.745,
   "deepseek-v4-1-flash|otis_mock_aime": 0.9833333333333333,
   "deepseek-v4-1-flash|simpleqa_verified": 0.429,
   "deepseek-v4-flash-0731|chess_puzzles": 0.32,
   "deepseek-v4-flash-0731|frontiermath_t13": 0.5754385964912281,
   "deepseek-v4-flash-0731|frontiermath_t4": 0.24390243902439024,
   "deepseek-v4-flash-0731|gpqa_diamond": 0.9103535353535354,
   "deepseek-v4-flash-0731|mystery_game_puzzles": 0.34,
   "deepseek-v4-flash-0731|or_gpqa_diamond": 0.8996633999999999,
   "deepseek-v4-flash-0731|or_tau2_airline": 0.7766665,
   "deepseek-v4-flash-0731|otis_mock_aime": 0.9444444444444444,
   "deepseek-v4-flash-0731|simpleqa_verified": 0.33633633633633636,
   "deepseek-v4-flash|or_gpqa_diamond": 0.8989900000000001,
   "deepseek-v4-flash|or_tau2_airline": 0.7755553333333334,
   "deepseek-v4-pro-0813|chess_puzzles": 0.46,
   "deepseek-v4-pro-0813|frontiermath_t13": 0.6456140350877193,
   "deepseek-v4-pro-0813|frontiermath_t4": 0.2682926829268293,
   "deepseek-v4-pro-0813|gpqa_diamond": 0.9166666666666666,
   "deepseek-v4-pro-0813|mystery_game_puzzles": 0.43,
   "deepseek-v4-pro-0813|or_gpqa_diamond": 0.892567903763697,
   "deepseek-v4-pro-0813|or_tau2_airline": 0.767500125,
   "deepseek-v4-pro-0813|otis_mock_aime": 0.9861111111111112,
   "deepseek-v4-pro-0813|simpleqa_verified": 0.5290581162324649,
   "deepseek-v4-pro|chess_puzzles": 0.19,
   "deepseek-v4-pro|frontiermath_t13": 0.45263157894736844,
   "deepseek-v4-pro|frontiermath_t4": 0.024390243902439025,
   "deepseek-v4-pro|gpqa_diamond": 0.9090909090909091,
   "deepseek-v4-pro|mystery_game_puzzles": 0.17,
   "deepseek-v4-pro|or_gpqa_diamond": 0.853535,
   "deepseek-v4-pro|or_tau2_airline": 0.788889,
   "deepseek-v4-pro|otis_mock_aime": 0.9666666666666667,
   "deepseek-v4-pro|simpleqa_verified": 0.46993987975951906,
   "deepseek-v4-pro|swe_bench_verified": 0.7763975155279503,
   "eurus-2-7b-prime|gpqa_diamond": 0.3390151515151515,
   "gemini-1-0-pro|gpqa_diamond": 0.33964646464646464,
   "gemini-1-0-pro|math_level_5": 0.11244335347432025,
   "gemini-1-0-pro|otis_mock_aime": 0.011111111111111112,
   "gemini-1-5-flash-8b|gpqa_diamond": 0.32954545454545453,
   "gemini-1-5-flash-8b|otis_mock_aime": 0.04583333333333333,
   "gemini-1-5-flash-may-2024|gpqa_diamond": 0.40372474747474746,
   "gemini-1-5-flash-may-2024|math_level_5": 0.2512273413897281,
   "gemini-1-5-flash-may-2024|otis_mock_aime": 0.03888888888888889,
   "gemini-1-5-flash-sep-2024|gpqa_diamond": 0.47316919191919193,
   "gemini-1-5-flash-sep-2024|math_level_5": 0.6186744712990937,
   "gemini-1-5-flash-sep-2024|otis_mock_aime": 0.1625,
   "gemini-1-5-pro-may-2024|gpqa_diamond": 0.4586489898989899,
   "gemini-1-5-pro-may-2024|math_level_5": 0.4074773413897281,
   "gemini-1-5-pro-may-2024|otis_mock_aime": 0.06805555555555555,
   "gemini-1-5-pro-sept-2024|gpqa_diamond": 0.5722853535353535,
   "gemini-1-5-pro-sept-2024|math_level_5": 0.7039274924471299,
   "gemini-1-5-pro-sept-2024|otis_mock_aime": 0.23055555555555557,
   "gemini-2-0-flash-dec-2024|aider_polyglot": 0.222,
   "gemini-2-0-flash-feb-2025|gpqa_diamond": 0.6414141414141414,
   "gemini-2-0-flash-feb-2025|math_level_5": 0.8216578549848943,
   "gemini-2-0-flash-feb-2025|otis_mock_aime": 0.3111111111111111,
   "gemini-2-0-flash-thinking-jan-2025|aider_polyglot": 0.182,
   "gemini-2-0-flash-thinking-jan-2025|gpqa_diamond": 0.5707070707070707,
   "gemini-2-0-flash-thinking-jan-2025|otis_mock_aime": 0.5777777777777777,
   "gemini-2-0-pro|aider_polyglot": 0.35600000000000004,
   "gemini-2-0-pro|gpqa_diamond": 0.6565656565656566,
   "gemini-2-0-pro|math_level_5": 0.8345921450151057,
   "gemini-2-5-flash-apr-2025|aider_polyglot": 0.47100000000000003,
   "gemini-2-5-flash-apr-2025|otis_mock_aime": 0.7305555555555555,
   "gemini-2-5-flash-jun-2025|bfcl_overall": 0.5624,
   "gemini-2-5-flash-jun-2025|or_gpqa_diamond": 0.738309,
   "gemini-2-5-flash-jun-2025|or_tau2_airline": 0.5511113333333334,
   "gemini-2-5-flash-may-2025|aider_polyglot": 0.551,
   "gemini-2-5-flash-may-2025|otis_mock_aime": 0.7083333333333334,
   "gemini-2-5-pro-jun-2025|aider_polyglot": 0.831,
   "gemini-2-5-pro-jun-2025|frontiermath_t13": 0.24561403508771928,
   "gemini-2-5-pro-jun-2025|frontiermath_t4": 0.0,
   "gemini-2-5-pro-jun-2025|gpqa_diamond": 0.8529040404040404,
   "gemini-2-5-pro-jun-2025|or_gpqa_diamond": 0.806210222222222,
   "gemini-2-5-pro-jun-2025|or_tau2_airline": 0.5622223333333333,
   "gemini-2-5-pro-jun-2025|otis_mock_aime": 0.8472222222222222,
   "gemini-2-5-pro-jun-2025|swe_bench_verified": 0.5755693581780539,
   "gemini-2-5-pro-mar-2025|aider_polyglot": 0.7290000000000001,
   "gemini-2-5-pro-mar-2025|gpqa_diamond": 0.8383838383838383,
   "gemini-2-5-pro-mar-2025|math_level_5": 0.9556268882175226,
   "gemini-2-5-pro-may-2025|aider_polyglot": 0.769,
   "gemini-2-5-pro-may-2025|gpqa_diamond": 0.6666666666666666,
   "gemini-2-5-pro-may-2025|math_level_5": 0.9590256797583081,
   "gemini-3-1-flash-lite|frontiermath_t13": 0.2771929824561403,
   "gemini-3-1-flash-lite|gpqa_diamond": 0.8181818181818182,
   "gemini-3-1-flash-lite|otis_mock_aime": 0.8,
   "gemini-3-1-pro|chess_puzzles": 0.51,
   "gemini-3-1-pro|frontiermath_t13": 0.5964912280701754,
   "gemini-3-1-pro|frontiermath_t4": 0.2682926829268293,
   "gemini-3-1-pro|furniture_assembly": 0.26666666666666666,
   "gemini-3-1-pro|gpqa_diamond": 0.9444444444444444,
   "gemini-3-1-pro|mystery_game_puzzles": 0.34,
   "gemini-3-1-pro|or_gpqa_diamond": 0.9483723333333332,
   "gemini-3-1-pro|or_tau2_airline": 0.7422223333333333,
   "gemini-3-1-pro|otis_mock_aime": 0.956,
   "gemini-3-1-pro|simpleqa_verified": 0.735,
   "gemini-3-1-pro|swe_bench_verified": 0.756198347107438,
   "gemini-3-5-flash-lite|chess_puzzles": 0.21,
   "gemini-3-5-flash-lite|frontiermath_t13": 0.2596491228070175,
   "gemini-3-5-flash-lite|frontiermath_t4": 0.0,
   "gemini-3-5-flash-lite|gpqa_diamond": 0.8333333333333334,
   "gemini-3-5-flash-lite|mystery_game_puzzles": 0.19,
   "gemini-3-5-flash-lite|or_gpqa_diamond": 0.8402775531250001,
   "gemini-3-5-flash-lite|or_tau2_airline": 0.7349997500000001,
   "gemini-3-5-flash-lite|otis_mock_aime": 0.7111111111111111,
   "gemini-3-5-flash|chess_puzzles": 0.45,
   "gemini-3-5-flash|frontiermath_t13": 0.6280701754385964,
   "gemini-3-5-flash|frontiermath_t4": 0.2682926829268293,
   "gemini-3-5-flash|gpqa_diamond": 0.928030303030303,
   "gemini-3-5-flash|mystery_game_puzzles": 0.32,
   "gemini-3-5-flash|or_gpqa_diamond": 0.9242421666666667,
   "gemini-3-5-flash|or_tau2_airline": 0.7333336666666668,
   "gemini-3-5-flash|otis_mock_aime": 0.9555555555555556,
   "gemini-3-5-flash|simpleqa_verified": 0.662,
   "gemini-3-5-flash|swe_bench_verified": 0.7933884297520661,
   "gemini-3-6-flash|chess_puzzles": 0.42,
   "gemini-3-6-flash|frontiermath_t13": 0.5894736842105263,
   "gemini-3-6-flash|frontiermath_t4": 0.21951219512195122,
   "gemini-3-6-flash|furniture_assembly": 0.23333333333333334,
   "gemini-3-6-flash|gpqa_diamond": 0.9412878787878788,
   "gemini-3-6-flash|mystery_game_puzzles": 0.3,
   "gemini-3-6-flash|or_gpqa_diamond": 0.930415,
   "gemini-3-6-flash|or_tau2_airline": 0.72,
   "gemini-3-6-flash|otis_mock_aime": 0.9416666666666667,
   "gemini-3-6-flash|simpleqa_verified": 0.662,
   "gemini-3-7-flash|chess_puzzles": 0.66,
   "gemini-3-7-flash|frontiermath_t13": 0.7157894736842105,
   "gemini-3-7-flash|frontiermath_t4": 0.36585365853658536,
   "gemini-3-7-flash|furniture_assembly": 0.26666666666666666,
   "gemini-3-7-flash|gpqa_diamond": 0.9482323232323232,
   "gemini-3-7-flash|mystery_game_puzzles": 0.37,
   "gemini-3-7-flash|or_gpqa_diamond": 0.9391951653543308,
   "gemini-3-7-flash|or_tau2_airline": 0.7831052054794521,
   "gemini-3-7-flash|otis_mock_aime": 0.9722222222222222,
   "gemini-3-7-flash|simpleqa_verified": 0.692,
   "gemini-3-8-flash|chess_puzzles": 0.58,
   "gemini-3-8-flash|frontiermath_t13": 0.6842105263157895,
   "gemini-3-8-flash|frontiermath_t4": 0.21951219512195122,
   "gemini-3-8-flash|furniture_assembly": 0.31666666666666665,
   "gemini-3-8-flash|gpqa_diamond": 0.9539141414141414,
   "gemini-3-8-flash|mystery_game_puzzles": 0.47,
   "gemini-3-8-flash|or_gpqa_diamond": 0.9482614885496183,
   "gemini-3-8-flash|or_tau2_airline": 0.734694,
   "gemini-3-8-flash|otis_mock_aime": 0.9888888888888889,
   "gemini-3-8-flash|simpleqa_verified": 0.697,
   "gemini-3-flash|chess_puzzles": 0.39,
   "gemini-3-flash|frontiermath_t13": 0.512280701754386,
   "gemini-3-flash|frontiermath_t4": 0.17073170731707318,
   "gemini-3-flash|gpqa_diamond": 0.8939393939393939,
   "gemini-3-flash|mystery_game_puzzles": 0.26,
   "gemini-3-flash|or_gpqa_diamond": 0.8855220000000001,
   "gemini-3-flash|or_tau2_airline": 0.7533333333333333,
   "gemini-3-flash|otis_mock_aime": 0.9555555555555556,
   "gemini-3-flash|simpleqa_verified": 0.668,
   "gemini-3-flash|swe_bench_verified": 0.7541322314049587,
   "gemini-3-pro|bfcl_overall": 0.7251000000000001,
   "gemini-3-pro|gpqa_diamond": 0.9261363636363636,
   "gemini-3-pro|otis_mock_aime": 0.9138888888888889,
   "gemini-3-pro|swe_bench_verified": 0.7293388429752066,
   "gemini-4-argon|chess_puzzles": 0.59,
   "gemini-4-argon|frontiermath_t13": 0.8596491228070176,
   "gemini-4-argon|frontiermath_t4": 0.7804878048780488,
   "gemini-4-argon|furniture_assembly": 0.725,
   "gemini-4-argon|gpqa_diamond": 0.9640151515151515,
   "gemini-4-argon|mystery_game_puzzles": 0.64,
   "gemini-4-argon|or_gpqa_diamond": 0.964646,
   "gemini-4-argon|or_tau2_airline": 0.786667,
   "gemini-4-argon|otis_mock_aime": 1.0,
   "gemini-4-argon|simpleqa_verified": 0.76,
   "gemma-2-27b|gpqa_diamond": 0.3648989898989899,
   "gemma-2-27b|math_level_5": 0.2788897280966767,
   "gemma-2-27b|otis_mock_aime": 0.013888888888888888,
   "gemma-2-9b|gpqa_diamond": 0.2746212121212121,
   "gemma-2-9b|math_level_5": 0.2100641993957704,
   "gemma-2-9b|otis_mock_aime": 0.005555555555555556,
   "gemma-3-12b|bfcl_overall": 0.3043,
   "gemma-3-12b|gpqa_diamond": 0.39457070707070707,
   "gemma-3-12b|or_gpqa_diamond": 0.37878799999999996,
   "gemma-3-12b|or_tau2_airline": 0.48,
   "gemma-3-12b|otis_mock_aime": 0.16666666666666666,
   "gemma-3-1b|bfcl_overall": 0.0717,
   "gemma-3-1b|gpqa_diamond": 0.1994949494949495,
   "gemma-3-1b|otis_mock_aime": 0.011111111111111112,
   "gemma-3-27b|aider_polyglot": 0.049,
   "gemma-3-27b|bfcl_overall": 0.29469999999999996,
   "gemma-3-27b|gpqa_diamond": 0.4772727272727273,
   "gemma-3-27b|math_level_5": 0.740370090634441,
   "gemma-3-27b|otis_mock_aime": 0.225,
   "gemma-3-4b|bfcl_overall": 0.1962,
   "gemma-3-4b|gpqa_diamond": 0.23232323232323232,
   "gemma-3-4b|or_gpqa_diamond": 0.271044,
   "gemma-3-4b|otis_mock_aime": 0.075,
   "gemma-4-26b-a4b|gpqa_diamond": 0.7323232323232324,
   "gemma-4-26b-a4b|or_gpqa_diamond": 0.7762077565217391,
   "gemma-4-26b-a4b|or_tau2_airline": 0.5733334999999999,
   "gemma-4-26b-a4b|otis_mock_aime": 0.8222222222222222,
   "gemma-4-31b-it|gpqa_diamond": 0.7575757575757576,
   "gemma-4-31b-it|or_gpqa_diamond": 0.81649825,
   "gemma-4-31b-it|or_tau2_airline": 0.756666625,
   "gemma-4-31b-it|otis_mock_aime": 0.7333333333333333,
   "gemma-4-31b-it|simpleqa_verified": 0.104,
   "glm-4-5-air|or_tau2_airline": 0.68,
   "glm-4-6|bfcl_overall": 0.7238,
   "glm-4-6|or_gpqa_diamond": 0.7646065075987841,
   "glm-4-6|or_tau2_airline": 0.7344445,
   "glm-4-7-flash-none|gpqa_diamond": 0.4513888888888889,
   "glm-4-7-flash-none|otis_mock_aime": 0.25,
   "glm-4-7-flash|gpqa_diamond": 0.6054292929292929,
   "glm-4-7-flash|or_gpqa_diamond": 0.49197393750000007,
   "glm-4-7-flash|or_tau2_airline": 0.6833333333333333,
   "glm-4-7-flash|otis_mock_aime": 0.5833333333333334,
   "glm-4-7|chess_puzzles": 0.21,
   "glm-4-7|gpqa_diamond": 0.8333333333333334,
   "glm-4-7|or_gpqa_diamond": 0.8364136921606119,
   "glm-4-7|or_tau2_airline": 0.7037037777777777,
   "glm-4-7|otis_mock_aime": 0.8333333333333334,
   "glm-4-7|simpleqa_verified": 0.322,
   "glm-5-1|chess_puzzles": 0.2,
   "glm-5-1|frontiermath_t13": 0.3684210526315789,
   "glm-5-1|gpqa_diamond": 0.898989898989899,
   "glm-5-1|or_gpqa_diamond": 0.8115756996197718,
   "glm-5-1|or_tau2_airline": 0.7433332500000001,
   "glm-5-1|otis_mock_aime": 0.9333333333333333,
   "glm-5-1|simpleqa_verified": 0.34,
   "glm-5-1|swe_bench_verified": 0.7417,
   "glm-5-2|chess_puzzles": 0.22,
   "glm-5-2|frontiermath_t13": 0.592057761732852,
   "glm-5-2|frontiermath_t4": 0.2926829268292683,
   "glm-5-2|gpqa_diamond": 0.9185606060606061,
   "glm-5-2|mystery_game_puzzles": 0.19,
   "glm-5-2|or_gpqa_diamond": 0.8334862727272728,
   "glm-5-2|or_tau2_airline": 0.7169697272727272,
   "glm-5-2|otis_mock_aime": 0.8638888888888889,
   "glm-5-2|simpleqa_verified": 0.342,
   "glm-5-2|swe_bench_verified": 0.787,
   "glm-5-3-flash|chess_puzzles": 0.21,
   "glm-5-3-flash|frontiermath_t13": 0.5578947368421052,
   "glm-5-3-flash|frontiermath_t4": 0.17073170731707318,
   "glm-5-3-flash|gpqa_diamond": 0.9015151515151515,
   "glm-5-3-flash|mystery_game_puzzles": 0.08,
   "glm-5-3-flash|or_gpqa_diamond": 0.9090909999999999,
   "glm-5-3-flash|or_tau2_airline": 0.762499875,
   "glm-5-3-flash|otis_mock_aime": 0.9388888888888889,
   "glm-5-3|chess_puzzles": 0.37,
   "glm-5-3|frontiermath_t13": 0.6877192982456141,
   "glm-5-3|frontiermath_t4": 0.2926829268292683,
   "glm-5-3|gpqa_diamond": 0.9090909090909091,
   "glm-5-3|mystery_game_puzzles": 0.33,
   "glm-5-3|or_gpqa_diamond": 0.8639263412162163,
   "glm-5-3|or_tau2_airline": 0.78083325,
   "glm-5-3|otis_mock_aime": 0.9111111111111111,
   "glm-5-3|simpleqa_verified": 0.41,
   "glm-5|gpqa_diamond": 0.8781725888324873,
   "glm-5|or_gpqa_diamond": 0.7285024173913045,
   "glm-5|or_tau2_airline": 0.7422222222222222,
   "glm-5|otis_mock_aime": 0.8,
   "glm-5|swe_bench_verified": 0.7207792207792207,
   "gpt-3-5-turbo-jan-2024|frontiermath_t13": 0.0,
   "gpt-3-5-turbo-jan-2024|gpqa_diamond": 0.27178030303030304,
   "gpt-3-5-turbo-jan-2024|math_level_5": 0.1163141993957704,
   "gpt-3-5-turbo-jan-2024|mystery_game_puzzles": 0.03,
   "gpt-3-5-turbo-jan-2024|otis_mock_aime": 0.022222222222222223,
   "gpt-3-5-turbo-nov-2023|gpqa_diamond": 0.2803030303030303,
   "gpt-3-5-turbo-nov-2023|math_level_5": 0.15889350453172205,
   "gpt-4-1-mini|aider_polyglot": 0.324,
   "gpt-4-1-mini|bfcl_overall": 0.5045000000000001,
   "gpt-4-1-mini|chess_puzzles": 0.01,
   "gpt-4-1-mini|frontiermath_t13": 0.06666666666666667,
   "gpt-4-1-mini|gpqa_diamond": 0.6584595959595959,
   "gpt-4-1-mini|math_level_5": 0.8729229607250756,
   "gpt-4-1-mini|mystery_game_puzzles": 0.07,
   "gpt-4-1-mini|or_gpqa_diamond": 0.6473065000000001,
   "gpt-4-1-mini|or_tau2_airline": 0.44333325,
   "gpt-4-1-mini|otis_mock_aime": 0.44722222222222224,
   "gpt-4-1-mini|simpleqa_verified": 0.127,
   "gpt-4-1-nano|aider_polyglot": 0.08900000000000001,
   "gpt-4-1-nano|bfcl_overall": 0.33049999999999996,
   "gpt-4-1-nano|chess_puzzles": 0.0,
   "gpt-4-1-nano|gpqa_diamond": 0.48926767676767674,
   "gpt-4-1-nano|math_level_5": 0.6999622356495468,
   "gpt-4-1-nano|or_gpqa_diamond": 0.4966332500000001,
   "gpt-4-1-nano|or_tau2_airline": 0.11833325,
   "gpt-4-1-nano|otis_mock_aime": 0.28888888888888886,
   "gpt-4-1-nano|simpleqa_verified": 0.06,
   "gpt-4-1|aider_polyglot": 0.524,
   "gpt-4-1|bfcl_overall": 0.5396,
   "gpt-4-1|chess_puzzles": 0.03,
   "gpt-4-1|frontiermath_t13": 0.05964912280701754,
   "gpt-4-1|gpqa_diamond": 0.6691919191919192,
   "gpt-4-1|math_level_5": 0.8300604229607251,
   "gpt-4-1|or_gpqa_diamond": 0.6607744999999999,
   "gpt-4-1|or_tau2_airline": 0.5083332500000001,
   "gpt-4-1|otis_mock_aime": 0.38333333333333336,
   "gpt-4-1|simpleqa_verified": 0.311,
   "gpt-4-1|swe_bench_verified": 0.48541666666666666,
   "gpt-4-5|gpqa_diamond": 0.6868686868686869,
   "gpt-4-5|math_level_5": 0.7862537764350453,
   "gpt-4-5|otis_mock_aime": 0.37777777777777777,
   "gpt-4-jun-2023|gpqa_diamond": 0.30650252525252525,
   "gpt-4-jun-2023|math_level_5": 0.22970166163141995,
   "gpt-4-jun-2023|mystery_game_puzzles": 0.12,
   "gpt-4-jun-2023|otis_mock_aime": 0.011111111111111112,
   "gpt-4-mar-2023|gpqa_diamond": 0.3573232323232323,
   "gpt-4-mar-2023|otis_mock_aime": 0.005555555555555556,
   "gpt-4-turbo-apr-2024|frontiermath_t13": 0.007017543859649123,
   "gpt-4-turbo-apr-2024|gpqa_diamond": 0.4659090909090909,
   "gpt-4-turbo-apr-2024|math_level_5": 0.46733383685800606,
   "gpt-4-turbo-apr-2024|otis_mock_aime": 0.06666666666666667,
   "gpt-4o-aug-2024|aider_polyglot": 0.231,
   "gpt-4o-aug-2024|chess_puzzles": 0.06,
   "gpt-4o-aug-2024|frontiermath_t13": 0.0035087719298245615,
   "gpt-4o-aug-2024|gpqa_diamond": 0.49210858585858586,
   "gpt-4o-aug-2024|math_level_5": 0.5327605740181269,
   "gpt-4o-aug-2024|or_gpqa_diamond": 0.5280586666666666,
   "gpt-4o-aug-2024|or_tau2_airline": 0.43,
   "gpt-4o-aug-2024|otis_mock_aime": 0.06388888888888888,
   "gpt-4o-aug-2024|simpleqa_verified": 0.26,
   "gpt-4o-may-2024|gpqa_diamond": 0.4889520202020202,
   "gpt-4o-may-2024|math_level_5": 0.5104796072507553,
   "gpt-4o-may-2024|or_gpqa_diamond": 0.542088,
   "gpt-4o-may-2024|or_tau2_airline": 0.44,
   "gpt-4o-may-2024|otis_mock_aime": 0.0625,
   "gpt-4o-mini|aider_polyglot": 0.036000000000000004,
   "gpt-4o-mini|chess_puzzles": 0.03,
   "gpt-4o-mini|frontiermath_t13": 0.007017543859649123,
   "gpt-4o-mini|gpqa_diamond": 0.37720959595959597,
   "gpt-4o-mini|math_level_5": 0.5263406344410876,
   "gpt-4o-mini|mystery_game_puzzles": 0.12,
   "gpt-4o-mini|or_gpqa_diamond": 0.4305555,
   "gpt-4o-mini|or_tau2_airline": 0.28000025,
   "gpt-4o-mini|otis_mock_aime": 0.06944444444444445,
   "gpt-4o-mini|simpleqa_verified": 0.083,
   "gpt-4o-nov-2024|aider_polyglot": 0.182,
   "gpt-4o-nov-2024|gpqa_diamond": 0.4788510101010101,
   "gpt-4o-nov-2024|math_level_5": 0.49773413897280966,
   "gpt-4o-nov-2024|otis_mock_aime": 0.0625,
   "gpt-4o-nov-2024|swe_bench_verified": 0.30991735537190085,
   "gpt-5-1|chess_puzzles": 0.42,
   "gpt-5-1|gpqa_diamond": 0.8762626262626263,
   "gpt-5-1|mystery_game_puzzles": 0.19,
   "gpt-5-1|or_gpqa_diamond": 0.8692479999999999,
   "gpt-5-1|or_tau2_airline": 0.7583332500000001,
   "gpt-5-1|otis_mock_aime": 0.8861111111111111,
   "gpt-5-1|simpleqa_verified": 0.48,
   "gpt-5-1|swe_bench_verified": 0.6797520661157025,
   "gpt-5-2-pro|chess_puzzles": 0.6,
   "gpt-5-2-pro|frontiermath_t13": 0.74,
   "gpt-5-2-pro|frontiermath_t4": 0.46,
   "gpt-5-2|bfcl_overall": 0.5587,
   "gpt-5-2|chess_puzzles": 0.48,
   "gpt-5-2|frontiermath_t13": 0.674,
   "gpt-5-2|frontiermath_t4": 0.317,
   "gpt-5-2|furniture_assembly": 0.38333333333333336,
   "gpt-5-2|gpqa_diamond": 0.914,
   "gpt-5-2|mystery_game_puzzles": 0.23,
   "gpt-5-2|or_gpqa_diamond": 0.878788,
   "gpt-5-2|or_tau2_airline": 0.726667,
   "gpt-5-2|otis_mock_aime": 0.9611111111111111,
   "gpt-5-2|simpleqa_verified": 0.371,
   "gpt-5-2|swe_bench_verified": 0.737603305785124,
   "gpt-5-3-codex|or_tau2_airline": 0.753333,
   "gpt-5-3-codex|swe_bench_verified": 0.7479338842975206,
   "gpt-5-4-mini|chess_puzzles": 0.23,
   "gpt-5-4-mini|frontiermath_t13": 0.512280701754386,
   "gpt-5-4-mini|frontiermath_t4": 0.0975609756097561,
   "gpt-5-4-mini|gpqa_diamond": 0.8686868686868687,
   "gpt-5-4-mini|mystery_game_puzzles": 0.11,
   "gpt-5-4-mini|or_gpqa_diamond": 0.84048825,
   "gpt-5-4-mini|or_tau2_airline": 0.6216667499999999,
   "gpt-5-4-mini|otis_mock_aime": 0.8888888888888888,
   "gpt-5-4-mini|simpleqa_verified": 0.294,
   "gpt-5-4-nano|chess_puzzles": 0.45,
   "gpt-5-4-nano|frontiermath_t13": 0.44912280701754387,
   "gpt-5-4-nano|frontiermath_t4": 0.12195121951219512,
   "gpt-5-4-nano|gpqa_diamond": 0.7847,
   "gpt-5-4-nano|mystery_game_puzzles": 0.09,
   "gpt-5-4-nano|or_gpqa_diamond": 0.77567325,
   "gpt-5-4-nano|or_tau2_airline": 0.65166675,
   "gpt-5-4-nano|otis_mock_aime": 0.8778,
   "gpt-5-4-nano|simpleqa_verified": 0.117,
   "gpt-5-4-pro|chess_puzzles": 0.59,
   "gpt-5-4-pro|frontiermath_t13": 0.8245614035087719,
   "gpt-5-4-pro|frontiermath_t4": 0.5853658536585366,
   "gpt-5-4-pro|gpqa_diamond": 0.946,
   "gpt-5-4-pro|simpleqa_verified": 0.463,
   "gpt-5-4|chess_puzzles": 0.48,
   "gpt-5-4|frontiermath_t13": 0.7859649122807018,
   "gpt-5-4|frontiermath_t4": 0.49,
   "gpt-5-4|furniture_assembly": 0.375,
   "gpt-5-4|gpqa_diamond": 0.933,
   "gpt-5-4|mystery_game_puzzles": 0.37,
   "gpt-5-4|or_gpqa_diamond": 0.899551,
   "gpt-5-4|or_tau2_airline": 0.73166675,
   "gpt-5-4|otis_mock_aime": 0.9777777777777777,
   "gpt-5-4|simpleqa_verified": 0.451,
   "gpt-5-4|swe_bench_verified": 0.768595041322314,
   "gpt-5-5-instant|frontiermath_t13": 0.2631578947368421,
   "gpt-5-5-instant|frontiermath_t4": 0.024390243902439025,
   "gpt-5-5-instant|gpqa_diamond": 0.8251262626262627,
   "gpt-5-5-instant|otis_mock_aime": 0.6805555555555556,
   "gpt-5-5-pro|chess_puzzles": 0.62,
   "gpt-5-5-pro|frontiermath_t13": 0.8771929824561403,
   "gpt-5-5-pro|frontiermath_t4": 0.7804878048780488,
   "gpt-5-5-pro|gpqa_diamond": 0.9392135642135643,
   "gpt-5-5-pro|otis_mock_aime": 1.0,
   "gpt-5-5|chess_puzzles": 0.63,
   "gpt-5-5|frontiermath_t13": 0.8526315789473684,
   "gpt-5-5|frontiermath_t4": 0.725,
   "gpt-5-5|furniture_assembly": 0.44166666666666665,
   "gpt-5-5|gpqa_diamond": 0.9400252525252525,
   "gpt-5-5|mystery_game_puzzles": 0.56,
   "gpt-5-5|or_gpqa_diamond": 0.9360266666666668,
   "gpt-5-5|or_tau2_airline": 0.75,
   "gpt-5-5|otis_mock_aime": 1.0,
   "gpt-5-5|simpleqa_verified": 0.63,
   "gpt-5-5|swe_bench_verified": 0.8057851239669421,
   "gpt-5-6-luna|chess_puzzles": 0.43,
   "gpt-5-6-luna|frontiermath_t13": 0.8210526315789474,
   "gpt-5-6-luna|frontiermath_t4": 0.6097560975609756,
   "gpt-5-6-luna|furniture_assembly": 0.425,
   "gpt-5-6-luna|gpqa_diamond": 0.9160353535353535,
   "gpt-5-6-luna|mystery_game_puzzles": 0.21,
   "gpt-5-6-luna|or_gpqa_diamond": 0.8724745,
   "gpt-5-6-luna|or_tau2_airline": 0.72333325,
   "gpt-5-6-luna|otis_mock_aime": 0.9833333333333333,
   "gpt-5-6-luna|simpleqa_verified": 0.41,
   "gpt-5-6-sol|chess_puzzles": 0.59,
   "gpt-5-6-sol|frontiermath_t13": 0.8912280701754386,
   "gpt-5-6-sol|frontiermath_t4": 0.8292682926829268,
   "gpt-5-6-sol|furniture_assembly": 0.5666666666666667,
   "gpt-5-6-sol|gpqa_diamond": 0.9349747474747475,
   "gpt-5-6-sol|mystery_game_puzzles": 0.58,
   "gpt-5-6-sol|or_gpqa_diamond": 0.9234005000000001,
   "gpt-5-6-sol|or_tau2_airline": 0.73333325,
   "gpt-5-6-sol|otis_mock_aime": 1.0,
   "gpt-5-6-sol|simpleqa_verified": 0.697,
   "gpt-5-6-terra|chess_puzzles": 0.47,
   "gpt-5-6-terra|frontiermath_t13": 0.8596491228070176,
   "gpt-5-6-terra|frontiermath_t4": 0.7073170731707317,
   "gpt-5-6-terra|furniture_assembly": 0.5416666666666666,
   "gpt-5-6-terra|gpqa_diamond": 0.9330808080808081,
   "gpt-5-6-terra|mystery_game_puzzles": 0.35,
   "gpt-5-6-terra|or_gpqa_diamond": 0.89267675,
   "gpt-5-6-terra|or_tau2_airline": 0.715,
   "gpt-5-6-terra|otis_mock_aime": 0.9972222222222222,
   "gpt-5-6-terra|simpleqa_verified": 0.432,
   "gpt-5-mini|bfcl_overall": 0.5546,
   "gpt-5-mini|chess_puzzles": 0.24,
   "gpt-5-mini|frontiermath_t13": 0.4666666666666667,
   "gpt-5-mini|frontiermath_t4": 0.12195121951219512,
   "gpt-5-mini|gpqa_diamond": 0.75,
   "gpt-5-mini|math_level_5": 0.9784743202416919,
   "gpt-5-mini|mystery_game_puzzles": 0.1,
   "gpt-5-mini|or_gpqa_diamond": 0.8007853333333332,
   "gpt-5-mini|or_tau2_airline": 0.712121101010101,
   "gpt-5-mini|otis_mock_aime": 0.8666666666666667,
   "gpt-5-mini|simpleqa_verified": 0.216,
   "gpt-5-mini|swe_bench_verified": 0.6466942148760331,
   "gpt-5-nano|bfcl_overall": 0.5145000000000001,
   "gpt-5-nano|chess_puzzles": 0.22,
   "gpt-5-nano|frontiermath_t13": 0.2,
   "gpt-5-nano|frontiermath_t4": 0.024390243902439025,
   "gpt-5-nano|gpqa_diamond": 0.6944444444444444,
   "gpt-5-nano|math_level_5": 0.952416918429003,
   "gpt-5-nano|mystery_game_puzzles": 0.09,
   "gpt-5-nano|or_gpqa_diamond": 0.6843435000000001,
   "gpt-5-nano|or_tau2_airline": 0.4511785656565656,
   "gpt-5-nano|otis_mock_aime": 0.8111111111111111,
   "gpt-5-nano|simpleqa_verified": 0.117,
   "gpt-5-pro|chess_puzzles": 0.48,
   "gpt-5-pro|frontiermath_t13": 0.5578947368421052,
   "gpt-5-pro|frontiermath_t4": 0.1951219512195122,
   "gpt-5|aider_polyglot": 0.88,
   "gpt-5|chess_puzzles": 0.36,
   "gpt-5|frontiermath_t13": 0.5543859649122806,
   "gpt-5|frontiermath_t4": 0.21951219512195122,
   "gpt-5|gpqa_diamond": 0.8617424242424242,
   "gpt-5|math_level_5": 0.9813066465256798,
   "gpt-5|mystery_game_puzzles": 0.23,
   "gpt-5|or_gpqa_diamond": 0.8501685000000001,
   "gpt-5|or_tau2_airline": 0.7066666666666667,
   "gpt-5|otis_mock_aime": 0.9138888888888889,
   "gpt-5|simpleqa_verified": 0.501,
   "gpt-5|swe_bench_verified": 0.7355371900826446,
   "gpt-6-1-sol|chess_puzzles": 0.68,
   "gpt-6-1-sol|frontiermath_t13": 0.9368421052631579,
   "gpt-6-1-sol|frontiermath_t4": 1.0,
   "gpt-6-1-sol|furniture_assembly": 0.8,
   "gpt-6-1-sol|gpqa_diamond": 0.9539141414141414,
   "gpt-6-1-sol|mystery_game_puzzles": 0.8,
   "gpt-6-1-sol|or_gpqa_diamond": 0.944444,
   "gpt-6-1-sol|or_tau2_airline": 0.6822223333333333,
   "gpt-6-1-sol|otis_mock_aime": 1.0,
   "gpt-6-1-sol|simpleqa_verified": 0.739,
   "gpt-6-astra|chess_puzzles": 0.74,
   "gpt-6-astra|frontiermath_t13": 0.9368421052631579,
   "gpt-6-astra|frontiermath_t4": 0.976,
   "gpt-6-astra|furniture_assembly": 0.8,
   "gpt-6-astra|gpqa_diamond": 0.9577020202020202,
   "gpt-6-astra|mystery_game_puzzles": 0.84,
   "gpt-6-astra|or_gpqa_diamond": 0.9472503333333333,
   "gpt-6-astra|or_tau2_airline": 0.6766665000000001,
   "gpt-6-astra|otis_mock_aime": 1.0,
   "gpt-6-astra|simpleqa_verified": 0.756,
   "gpt-6-luna|chess_puzzles": 0.36,
   "gpt-6-luna|frontiermath_t13": 0.7894736842105263,
   "gpt-6-luna|frontiermath_t4": 0.5609756097560976,
   "gpt-6-luna|furniture_assembly": 0.44166666666666665,
   "gpt-6-luna|gpqa_diamond": 0.9046717171717171,
   "gpt-6-luna|mystery_game_puzzles": 0.07,
   "gpt-6-luna|or_gpqa_diamond": 0.8815936666666665,
   "gpt-6-luna|or_tau2_airline": 0.68,
   "gpt-6-luna|otis_mock_aime": 0.9888888888888889,
   "gpt-6-luna|simpleqa_verified": 0.414,
   "gpt-6-sol|chess_puzzles": 0.56,
   "gpt-6-sol|frontiermath_t13": 0.8982456140350877,
   "gpt-6-sol|frontiermath_t4": 0.9,
   "gpt-6-sol|furniture_assembly": 0.5833333333333334,
   "gpt-6-sol|gpqa_diamond": 0.9431818181818182,
   "gpt-6-sol|mystery_game_puzzles": 0.56,
   "gpt-6-sol|or_gpqa_diamond": 0.9208749999999999,
   "gpt-6-sol|or_tau2_airline": 0.7022223333333333,
   "gpt-6-sol|otis_mock_aime": 1.0,
   "gpt-6-sol|simpleqa_verified": 0.607,
   "gpt-oss-120b|aider_polyglot": 0.418,
   "gpt-oss-120b|gpqa_diamond": 0.7575757575757576,
   "gpt-oss-120b|mystery_game_puzzles": 0.02,
   "gpt-oss-120b|or_gpqa_diamond": 0.7578456145038168,
   "gpt-oss-120b|or_tau2_airline": 0.633333,
   "gpt-oss-120b|otis_mock_aime": 0.8888888888888888,
   "gpt-oss-20b|gpqa_diamond": 0.6079545454545454,
   "gpt-oss-20b|or_gpqa_diamond": 0.6311448,
   "gpt-oss-20b|or_tau2_airline": 0.4672696511627907,
   "gpt-oss-20b|otis_mock_aime": 0.6527777777777778,
   "granite-4-0-1b|gpqa_diamond": 0.2398989898989899,
   "granite-4-0-1b|otis_mock_aime": 0.008333333333333333,
   "granite-4-0-350m|bfcl_overall": 0.1898,
   "granite-4-0-350m|gpqa_diamond": 0.11237373737373738,
   "granite-4-0-350m|otis_mock_aime": 0.002777777777777778,
   "granite-4-0-micro|gpqa_diamond": 0.2828282828282828,
   "granite-4-0-micro|otis_mock_aime": 0.027777777777777776,
   "grok-2-dec-2024|gpqa_diamond": 0.5378787878787878,
   "grok-2-dec-2024|math_level_5": 0.6351963746223565,
   "grok-2-dec-2024|otis_mock_aime": 0.11527777777777778,
   "grok-3-mini|aider_polyglot": 0.493,
   "grok-3-mini|gpqa_diamond": 0.7626262626262627,
   "grok-3-mini|math_level_5": 0.9093655589123867,
   "grok-3-mini|otis_mock_aime": 0.7777777777777778,
   "grok-3|aider_polyglot": 0.5329999999999999,
   "grok-3|gpqa_diamond": 0.7575757575757576,
   "grok-3|math_level_5": 0.8874622356495468,
   "grok-3|otis_mock_aime": 0.5555555555555556,
   "grok-4-3-beta|chess_puzzles": 0.18,
   "grok-4-3-beta|frontiermath_t13": 0.4280701754385965,
   "grok-4-3-beta|frontiermath_t4": 0.14634146341463414,
   "grok-4-3-beta|gpqa_diamond": 0.8882575757575758,
   "grok-4-3-beta|otis_mock_aime": 0.9333333333333333,
   "grok-4-3-beta|simpleqa_verified": 0.332,
   "grok-4-5|chess_puzzles": 0.35,
   "grok-4-5|frontiermath_t13": 0.5719298245614035,
   "grok-4-5|frontiermath_t4": 0.24390243902439024,
   "grok-4-5|furniture_assembly": 0.225,
   "grok-4-5|gpqa_diamond": 0.9343434343434344,
   "grok-4-5|otis_mock_aime": 0.9777777777777777,
   "grok-4-5|simpleqa_verified": 0.483,
   "grok-4-6|chess_puzzles": 0.33,
   "grok-4-6|frontiermath_t13": 0.6596491228070176,
   "grok-4-6|frontiermath_t4": 0.3170731707317073,
   "grok-4-6|furniture_assembly": 0.4,
   "grok-4-6|gpqa_diamond": 0.9400252525252525,
   "grok-4-6|mystery_game_puzzles": 0.34,
   "grok-4-6|or_gpqa_diamond": 0.9246375695652174,
   "grok-4-6|or_tau2_airline": 0.747619,
   "grok-4-6|otis_mock_aime": 0.9916666666666667,
   "grok-4-6|simpleqa_verified": 0.493,
   "grok-4-7|chess_puzzles": 0.41,
   "grok-4-7|frontiermath_t13": 0.5298245614035088,
   "grok-4-7|frontiermath_t4": 0.17073170731707318,
   "grok-4-7|furniture_assembly": 0.20833333333333334,
   "grok-4-7|gpqa_diamond": 0.92739898989899,
   "grok-4-7|mystery_game_puzzles": 0.29,
   "grok-4-7|otis_mock_aime": 0.9805555555555555,
   "grok-4-7|simpleqa_verified": 0.56,
   "grok-4|aider_polyglot": 0.7959999999999999,
   "grok-4|bfcl_overall": 0.6297,
   "grok-4|gpqa_diamond": 0.87,
   "grok-4|otis_mock_aime": 0.84,
   "hermes-2-theta-llama-3-70b|gpqa_diamond": 0.3746843434343434,
   "hermes-2-theta-llama-3-70b|math_level_5": 0.22686933534743203,
   "hermes-2-theta-llama-3-70b|otis_mock_aime": 0.025,
   "inkling-small|frontiermath_t13": 0.4631578947368421,
   "inkling-small|frontiermath_t4": 0.17073170731707318,
   "inkling-small|gpqa_diamond": 0.88510101010101,
   "inkling-small|mystery_game_puzzles": 0.06,
   "inkling-small|or_gpqa_diamond": 0.8703701666666666,
   "inkling-small|or_tau2_airline": 0.6076188571428572,
   "inkling-small|otis_mock_aime": 0.9,
   "inkling-small|simpleqa_verified": 0.191,
   "inkling|chess_puzzles": 0.21,
   "inkling|frontiermath_t13": 0.3333333333333333,
   "inkling|frontiermath_t4": 0.04878048780487805,
   "inkling|gpqa_diamond": 0.8825757575757576,
   "inkling|or_gpqa_diamond": 0.818035862576065,
   "inkling|or_tau2_airline": 0.6755556666666667,
   "inkling|otis_mock_aime": 0.8888888888888888,
   "inkling|simpleqa_verified": 0.403,
   "kimi-k2-5|gpqa_diamond": 0.876,
   "kimi-k2-5|or_gpqa_diamond": 0.8592592,
   "kimi-k2-5|or_tau2_airline": 0.7277775,
   "kimi-k2-5|otis_mock_aime": 0.922,
   "kimi-k2-5|simpleqa_verified": 0.343,
   "kimi-k2-5|swe_bench_verified": 0.737603305785124,
   "kimi-k2-6|chess_puzzles": 0.2,
   "kimi-k2-6|frontiermath_t13": 0.5719298245614035,
   "kimi-k2-6|frontiermath_t4": 0.2564102564102564,
   "kimi-k2-6|furniture_assembly": 0.21666666666666667,
   "kimi-k2-6|gpqa_diamond": 0.9078282828282829,
   "kimi-k2-6|mystery_game_puzzles": 0.18,
   "kimi-k2-6|or_gpqa_diamond": 0.8799901428571427,
   "kimi-k2-6|or_tau2_airline": 0.7671130223214285,
   "kimi-k2-6|otis_mock_aime": 0.9611111111111111,
   "kimi-k2-6|simpleqa_verified": 0.349,
   "kimi-k2-6|swe_bench_verified": 0.7665289256198347,
   "kimi-k2-7-code|chess_puzzles": 0.14,
   "kimi-k2-7-code|frontiermath_t13": 0.5403508771929825,
   "kimi-k2-7-code|frontiermath_t4": 0.12195121951219512,
   "kimi-k2-7-code|gpqa_diamond": 0.8787878787878788,
   "kimi-k2-7-code|or_gpqa_diamond": 0.8847767229341582,
   "kimi-k2-7-code|or_tau2_airline": 0.7383231627502177,
   "kimi-k2-7-code|otis_mock_aime": 0.9555555555555556,
   "kimi-k2-7-code|simpleqa_verified": 0.365,
   "kimi-k2-sep-2025|or_gpqa_diamond": 0.7474749999999999,
   "kimi-k2-sep-2025|or_tau2_airline": 0.6366665,
   "kimi-k2-thinking|or_gpqa_diamond": 0.796581,
   "kimi-k2-thinking|or_tau2_airline": 0.695,
   "kimi-k3|chess_puzzles": 0.37,
   "kimi-k3|frontiermath_t13": 0.721830985915493,
   "kimi-k3|frontiermath_t4": 0.3902439024390244,
   "kimi-k3|furniture_assembly": 0.3416666666666667,
   "kimi-k3|gpqa_diamond": 0.9311868686868687,
   "kimi-k3|mystery_game_puzzles": 0.26,
   "kimi-k3|or_gpqa_diamond": 0.9157357830756013,
   "kimi-k3|or_tau2_airline": 0.7347416579476861,
   "kimi-k3|otis_mock_aime": 0.9722222222222222,
   "kimi-k3|simpleqa_verified": 0.506,
   "llama-3-1-405b|gpqa_diamond": 0.5091540404040404,
   "llama-3-1-405b|math_level_5": 0.49773413897280966,
   "llama-3-1-405b|otis_mock_aime": 0.09722222222222222,
   "llama-3-1-70b|gpqa_diamond": 0.44191919191919193,
   "llama-3-1-70b|math_level_5": 0.36678625377643503,
   "llama-3-1-70b|otis_mock_aime": 0.03611111111111111,
   "llama-3-1-8b|gpqa_diamond": 0.26957070707070707,
   "llama-3-1-8b|math_level_5": 0.22875755287009064,
   "llama-3-1-8b|or_gpqa_diamond": 0.26941151269035535,
   "llama-3-1-8b|otis_mock_aime": 0.016666666666666666,
   "llama-3-2-1b|bfcl_overall": 0.1082,
   "llama-3-2-1b|gpqa_diamond": 0.23926767676767677,
   "llama-3-2-1b|otis_mock_aime": 0.005555555555555556,
   "llama-3-2-3b|bfcl_overall": 0.2195,
   "llama-3-2-3b|or_gpqa_diamond": 0.17340049999999999,
   "llama-3-3-70b|bfcl_overall": 0.319,
   "llama-3-3-70b|gpqa_diamond": 0.4744318181818182,
   "llama-3-3-70b|math_level_5": 0.41597432024169184,
   "llama-3-3-70b|or_gpqa_diamond": 0.4753785,
   "llama-3-3-70b|or_tau2_airline": 0.313333,
   "llama-3-3-70b|otis_mock_aime": 0.05138888888888889,
   "llama-3-70b|gpqa_diamond": 0.40561868686868685,
   "llama-3-70b|math_level_5": 0.225547583081571,
   "llama-3-70b|otis_mock_aime": 0.043055555555555555,
   "llama-3-8b|gpqa_diamond": 0.26073232323232326,
   "llama-3-8b|math_level_5": 0.0612726586102719,
   "llama-3-8b|otis_mock_aime": 0.019444444444444445,
   "llama-4-maverick|aider_polyglot": 0.156,
   "llama-4-maverick|bfcl_overall": 0.3729,
   "llama-4-maverick|gpqa_diamond": 0.6698232323232324,
   "llama-4-maverick|math_level_5": 0.7301737160120846,
   "llama-4-maverick|or_gpqa_diamond": 0.6478116,
   "llama-4-maverick|or_tau2_airline": 0.43089426016260163,
   "llama-4-maverick|otis_mock_aime": 0.20555555555555555,
   "llama-4-scout|bfcl_overall": 0.2813,
   "llama-4-scout|gpqa_diamond": 0.5183080808080808,
   "llama-4-scout|math_level_5": 0.6227341389728097,
   "llama-4-scout|otis_mock_aime": 0.07777777777777778,
   "magistral-small-1-0|gpqa_diamond": 0.5606060606060606,
   "magistral-small-1-0|otis_mock_aime": 0.3,
   "magistral-small-1-2|gpqa_diamond": 0.476010101010101,
   "magistral-small-1-2|otis_mock_aime": 0.28055555555555556,
   "mimo-v2-5-pro|or_gpqa_diamond": 0.8550657272727274,
   "mimo-v2-5-pro|or_tau2_airline": 0.743889,
   "mimo-v2-5|or_gpqa_diamond": 0.8239975454545455,
   "mimo-v2-5|or_tau2_airline": 0.7372220833333334,
   "mimo-v2-6-flash|or_gpqa_diamond": 0.758698,
   "mimo-v2-6-flash|or_tau2_airline": 0.76,
   "mimo-v2-6-pro|or_gpqa_diamond": 0.8989897499999999,
   "mimo-v2-6-pro|or_tau2_airline": 0.7983335000000001,
   "minimax-m2-1|or_gpqa_diamond": 0.868687,
   "minimax-m2-1|or_tau2_airline": 0.6783334999999999,
   "minimax-m2-5|or_gpqa_diamond": 0.8539973475609757,
   "minimax-m2-5|or_tau2_airline": 0.6905556666666667,
   "minimax-m2-7|or_gpqa_diamond": 0.8570973081339713,
   "minimax-m2-7|or_tau2_airline": 0.7203921764705883,
   "minimax-m3|chess_puzzles": 0.13,
   "minimax-m3|gpqa_diamond": 0.9090909090909091,
   "minimax-m3|mystery_game_puzzles": 0.08,
   "minimax-m3|or_gpqa_diamond": 0.9151233333333333,
   "minimax-m3|or_tau2_airline": 0.7388889166666667,
   "minimax-m3|otis_mock_aime": 0.7111111111111111,
   "ministral-3b|gpqa_diamond": 0.25252525252525254,
   "ministral-3b|math_level_5": 0.14444864048338368,
   "ministral-8b|bfcl_overall": 0.111,
   "ministral-8b|gpqa_diamond": 0.27146464646464646,
   "ministral-8b|math_level_5": 0.14935800604229607,
   "mistral-7b-v0-3|gpqa_diamond": 0.1518308080808081,
   "mistral-7b-v0-3|otis_mock_aime": 0.002777777777777778,
   "mistral-large-2-jul-2024|gpqa_diamond": 0.49021464646464646,
   "mistral-large-2-jul-2024|math_level_5": 0.4481684290030212,
   "mistral-large-2-jul-2024|otis_mock_aime": 0.08472222222222223,
   "mistral-large-2-nov-2024|bfcl_overall": 0.3837,
   "mistral-large-2-nov-2024|gpqa_diamond": 0.5132575757575758,
   "mistral-large-2-nov-2024|math_level_5": 0.5028323262839879,
   "mistral-large-2-nov-2024|otis_mock_aime": 0.07777777777777778,
   "mistral-large-4|chess_puzzles": 0.33,
   "mistral-large-4|frontiermath_t13": 0.5859649122807018,
   "mistral-large-4|frontiermath_t4": 0.2682926829268293,
   "mistral-large-4|furniture_assembly": 0.20833333333333334,
   "mistral-large-4|gpqa_diamond": 0.8806818181818182,
   "mistral-large-4|mystery_game_puzzles": 0.17,
   "mistral-large-4|otis_mock_aime": 0.9833333333333333,
   "mistral-large-4|simpleqa_verified": 0.2,
   "mistral-large|gpqa_diamond": 0.38762626262626265,
   "mistral-large|math_level_5": 0.24461858006042297,
   "mistral-large|otis_mock_aime": 0.019444444444444445,
   "mistral-medium-3|bfcl_overall": 0.37689999999999996,
   "mistral-medium-3|gpqa_diamond": 0.5953282828282829,
   "mistral-medium-3|math_level_5": 0.8162764350453172,
   "mistral-medium-3|otis_mock_aime": 0.32222222222222224,
   "mistral-nemo|bfcl_overall": 0.2763,
   "mistral-nemo|gpqa_diamond": 0.2989267676767677,
   "mistral-nemo|math_level_5": 0.1082892749244713,
   "mistral-small-3-1|gpqa_diamond": 0.47474747474747475,
   "mistral-small-3-1|math_level_5": 0.4677114803625378,
   "mistral-small-3-1|otis_mock_aime": 0.058333333333333334,
   "mistral-small-3-2|bfcl_overall": 0.3715,
   "mistral-small-3-2|gpqa_diamond": 0.49053030303030304,
   "mistral-small-3-2|otis_mock_aime": 0.30277777777777776,
   "mistral-small-3|gpqa_diamond": 0.47285353535353536,
   "mistral-small-3|math_level_5": 0.4481684290030212,
   "mistral-small-3|otis_mock_aime": 0.06666666666666667,
   "mistral-small-4|or_gpqa_diamond": 0.7528056666666667,
   "mistral-small-4|or_tau2_airline": 0.41142871428571426,
   "mixtral-8x22b|gpqa_diamond": 0.34059343434343436,
   "mixtral-8x22b|math_level_5": 0.24244712990936557,
   "mixtral-8x7b|gpqa_diamond": 0.3058712121212121,
   "mixtral-8x7b|math_level_5": 0.09950906344410876,
   "muse-spark-1-1|chess_puzzles": 0.34,
   "muse-spark-1-1|simpleqa_verified": 0.5778894472361809,
   "muse-spark-1-2|chess_puzzles": 0.27,
   "muse-spark-1-2|simpleqa_verified": 0.6030150753768844,
   "muse-spark-1-3|chess_puzzles": 0.37,
   "muse-spark-1-3|frontiermath_t13": 0.743859649122807,
   "muse-spark-1-3|frontiermath_t4": 0.4634146341463415,
   "muse-spark-1-3|mystery_game_puzzles": 0.25,
   "muse-spark-1-3|otis_mock_aime": 0.9916666666666667,
   "muse-spark-open|frontiermath_t13": 0.6982456140350877,
   "muse-spark-open|frontiermath_t4": 0.3170731707317073,
   "muse-spark-open|gpqa_diamond": 0.8857323232323232,
   "muse-spark-open|or_gpqa_diamond": 0.905724,
   "muse-spark-open|or_tau2_airline": 0.78,
   "muse-spark-open|otis_mock_aime": 0.9805555555555555,
   "muse-spark-open|simpleqa_verified": 0.566,
   "muse-spark|gpqa_diamond": 0.898,
   "muse-spark|otis_mock_aime": 0.889,
   "muse-wonder|frontiermath_t13": 0.8210526315789474,
   "muse-wonder|frontiermath_t4": 0.7073170731707317,
   "muse-wonder|furniture_assembly": 0.5416666666666666,
   "muse-wonder|mystery_game_puzzles": 0.51,
   "muse-wonder|otis_mock_aime": 0.9944444444444445,
   "nemotron-3-ultra|gpqa_diamond": 0.8535353535353535,
   "nemotron-3-ultra|mystery_game_puzzles": 0.2,
   "nemotron-3-ultra|or_tau2_airline": 0.72,
   "nemotron-3-ultra|otis_mock_aime": 0.8666666666666667,
   "o1-mini|aider_polyglot": 0.32899999999999996,
   "o1-mini|gpqa_diamond": 0.6237373737373737,
   "o1-mini|math_level_5": 0.8918051359516617,
   "o1-mini|otis_mock_aime": 0.46944444444444444,
   "o1-preview|gpqa_diamond": 0.5031565656565656,
   "o1-preview|math_level_5": 0.8164652567975831,
   "o1-preview|otis_mock_aime": 0.3111111111111111,
   "o1|chess_puzzles": 0.1,
   "o1|frontiermath_t13": 0.14736842105263157,
   "o1|gpqa_diamond": 0.7676767676767676,
   "o1|math_level_5": 0.947129909365559,
   "o1|otis_mock_aime": 0.7333333333333333,
   "o1|simpleqa_verified": 0.411,
   "o3-mini|aider_polyglot": 0.5379999999999999,
   "o3-mini|chess_puzzles": 0.15,
   "o3-mini|frontiermath_t13": 0.18596491228070175,
   "o3-mini|frontiermath_t4": 0.0,
   "o3-mini|gpqa_diamond": 0.7702020202020202,
   "o3-mini|math_level_5": 0.9648791540785498,
   "o3-mini|mystery_game_puzzles": 0.07,
   "o3-mini|otis_mock_aime": 0.7694444444444445,
   "o3-mini|simpleqa_verified": 0.153,
   "o3-pro|aider_polyglot": 0.8490000000000001,
   "o3|aider_polyglot": 0.813,
   "o3|bfcl_overall": 0.6305,
   "o3|chess_puzzles": 0.37,
   "o3|frontiermath_t13": 0.3333333333333333,
   "o3|gpqa_diamond": 0.8181818181818182,
   "o3|math_level_5": 0.9777190332326284,
   "o3|mystery_game_puzzles": 0.29,
   "o3|otis_mock_aime": 0.8444444444444444,
   "o3|simpleqa_verified": 0.494,
   "o3|swe_bench_verified": 0.6231884057971014,
   "o4-mini|aider_polyglot": 0.72,
   "o4-mini|bfcl_overall": 0.5324,
   "o4-mini|chess_puzzles": 0.22,
   "o4-mini|frontiermath_t13": 0.36140350877192984,
   "o4-mini|frontiermath_t4": 0.04878048780487805,
   "o4-mini|gpqa_diamond": 0.7960858585858586,
   "o4-mini|math_level_5": 0.978285498489426,
   "o4-mini|mystery_game_puzzles": 0.05,
   "o4-mini|otis_mock_aime": 0.8166666666666667,
   "o4-mini|simpleqa_verified": 0.196,
   "openhands-lm-32b-v0-1|aider_polyglot": 0.102,
   "phi-3-medium-14b|gpqa_diamond": 0.2758838383838384,
   "phi-3-medium-14b|math_level_5": 0.17560422960725075,
   "phi-4|bfcl_overall": 0.2879,
   "phi-4|gpqa_diamond": 0.5606060606060606,
   "phi-4|math_level_5": 0.6493580060422961,
   "phi-4|otis_mock_aime": 0.1375,
   "qwen-3-5-flash-hosted-35b-a3b|chess_puzzles": 0.14,
   "qwen-3-5-flash-hosted-35b-a3b|frontiermath_t13": 0.1824561403508772,
   "qwen-3-5-flash-hosted-35b-a3b|gpqa_diamond": 0.8232323232323232,
   "qwen-3-5-flash-hosted-35b-a3b|mystery_game_puzzles": 0.2,
   "qwen-3-5-flash-hosted-35b-a3b|otis_mock_aime": 0.8444444444444444,
   "qwen-3-5-flash-hosted-35b-a3b|simpleqa_verified": 0.2032032032032032,
   "qwen-3-5-plus-hosted-397b-a17b|chess_puzzles": 0.08,
   "qwen-3-5-plus-hosted-397b-a17b|gpqa_diamond": 0.8484848484848485,
   "qwen-3-5-plus-hosted-397b-a17b|mystery_game_puzzles": 0.17,
   "qwen-3-5-plus-hosted-397b-a17b|otis_mock_aime": 0.8666666666666667,
   "qwen-3-5-plus-hosted-397b-a17b|simpleqa_verified": 0.2535070140280561,
   "qwen-3-6-35b-a3b|frontiermath_t13": 0.20350877192982456,
   "qwen-3-6-35b-a3b|gpqa_diamond": 0.8484848484848485,
   "qwen-3-6-35b-a3b|mystery_game_puzzles": 0.22,
   "qwen-3-6-35b-a3b|or_gpqa_diamond": 0.8272847449686571,
   "qwen-3-6-35b-a3b|or_tau2_airline": 0.744993393858478,
   "qwen-3-6-35b-a3b|otis_mock_aime": 0.8666666666666667,
   "qwen-3-6-flash|chess_puzzles": 0.12,
   "qwen-3-6-flash|frontiermath_t13": 0.22456140350877193,
   "qwen-3-6-flash|gpqa_diamond": 0.8333333333333334,
   "qwen-3-6-flash|mystery_game_puzzles": 0.18,
   "qwen-3-6-flash|otis_mock_aime": 0.8444444444444444,
   "qwen-3-6-flash|simpleqa_verified": 0.15915915915915915,
   "qwen-3-6-max-preview|gpqa_diamond": 0.8737373737373737,
   "qwen-3-6-max-preview|mystery_game_puzzles": 0.19,
   "qwen-3-6-max-preview|otis_mock_aime": 0.9111111111111111,
   "qwen-3-6-max-preview|simpleqa_verified": 0.5200400801603207,
   "qwen-3-6-max-preview|swe_bench_verified": 0.7665289256198347,
   "qwen-3-6-plus|chess_puzzles": 0.14,
   "qwen-3-6-plus|frontiermath_t13": 0.3824561403508772,
   "qwen-3-6-plus|gpqa_diamond": 0.8838383838383839,
   "qwen-3-6-plus|mystery_game_puzzles": 0.12,
   "qwen-3-6-plus|otis_mock_aime": 0.9333333333333333,
   "qwen-3-6-plus|simpleqa_verified": 0.44144144144144143,
   "qwen-3-6-plus|swe_bench_verified": 0.5785123966942148,
   "qwen-3-8-27b|or_gpqa_diamond": 0.83367,
   "qwen-3-8-27b|or_tau2_airline": 0.7592592222222222,
   "qwen-3-8-max|chess_puzzles": 0.46,
   "qwen-3-8-max|frontiermath_t13": 0.7473684210526316,
   "qwen-3-8-max|frontiermath_t4": 0.4634146341463415,
   "qwen-3-8-max|gpqa_diamond": 0.9267676767676768,
   "qwen-3-8-max|mystery_game_puzzles": 0.38,
   "qwen-3-8-max|otis_mock_aime": 0.9944444444444445,
   "qwen-3-8-max|simpleqa_verified": 0.458,
   "qwen-plus-jan-2025|gpqa_diamond": 0.4810606060606061,
   "qwen-plus-jan-2025|math_level_5": 0.6527567975830816,
   "qwen-plus-jan-2025|otis_mock_aime": 0.17777777777777778,
   "qwen-turbo|gpqa_diamond": 0.41792929292929293,
   "qwen-turbo|math_level_5": 0.5623111782477341,
   "qwen-turbo|otis_mock_aime": 0.06111111111111111,
   "qwen2-5-32b|gpqa_diamond": 0.46085858585858586,
   "qwen2-5-32b|math_level_5": 0.5607061933534743,
   "qwen2-5-32b|otis_mock_aime": 0.07361111111111111,
   "qwen2-5-72b|gpqa_diamond": 0.4914772727272727,
   "qwen2-5-72b|math_level_5": 0.631703172205438,
   "qwen2-5-72b|or_gpqa_diamond": 0.461279,
   "qwen2-5-72b|or_tau2_airline": 0.25,
   "qwen2-5-72b|otis_mock_aime": 0.08055555555555556,
   "qwen2-5-7b|gpqa_diamond": 0.3547979797979798,
   "qwen2-5-7b|or_gpqa_diamond": 0.3417510000000001,
   "qwen2-5-7b|or_tau2_airline": 0.166667,
   "qwen2-5-7b|otis_mock_aime": 0.025,
   "qwen2-5-coder-32b-instruct|aider_polyglot": 0.16399999999999998,
   "qwen2-5-max|aider_polyglot": 0.218,
   "qwen2-5-max|gpqa_diamond": 0.5612373737373737,
   "qwen2-5-max|math_level_5": 0.6718277945619335,
   "qwen2-5-max|otis_mock_aime": 0.16111111111111112,
   "qwen2-72b|gpqa_diamond": 0.4078282828282828,
   "qwen2-72b|math_level_5": 0.39067220543806647,
   "qwen3-0-6b|bfcl_overall": 0.23929999999999998,
   "qwen3-1-7b|bfcl_overall": 0.2841,
   "qwen3-1-7b|gpqa_diamond": 0.380050505050505,
   "qwen3-1-7b|otis_mock_aime": 0.08055555555555556,
   "qwen3-14b|bfcl_overall": 0.4103,
   "qwen3-14b|gpqa_diamond": 0.6376262626262627,
   "qwen3-14b|or_gpqa_diamond": 0.5331086666666667,
   "qwen3-14b|or_tau2_airline": 0.413333,
   "qwen3-14b|otis_mock_aime": 0.6638888888888889,
   "qwen3-235b-a22b-instruct-jul-2025|bfcl_overall": 0.5215,
   "qwen3-235b-a22b-instruct-jul-2025|or_gpqa_diamond": 0.7388167142857143,
   "qwen3-235b-a22b-instruct-jul-2025|or_tau2_airline": 0.3961905714285714,
   "qwen3-235b-a22b-thinking-jul-2025|gpqa_diamond": 0.8005050505050505,
   "qwen3-235b-a22b-thinking-jul-2025|mystery_game_puzzles": 0.09,
   "qwen3-235b-a22b-thinking-jul-2025|or_gpqa_diamond": 0.7950335,
   "qwen3-235b-a22b-thinking-jul-2025|or_tau2_airline": 0.6266666666666667,
   "qwen3-235b-a22b-thinking-jul-2025|otis_mock_aime": 0.8666666666666667,
   "qwen3-235b-a22b-thinking-jul-2025|simpleqa_verified": 0.4044044044044044,
   "qwen3-235b-a22b|aider_polyglot": 0.596,
   "qwen3-235b-a22b|gpqa_diamond": 0.7070707070707071,
   "qwen3-235b-a22b|math_level_5": 0.6885699899295065,
   "qwen3-30b-a3b-instruct-jul-2025|bfcl_overall": 0.4139,
   "qwen3-30b-a3b-instruct-jul-2025|gpqa_diamond": 0.5561868686868687,
   "qwen3-30b-a3b-instruct-jul-2025|or_gpqa_diamond": 0.6419754999999999,
   "qwen3-30b-a3b-instruct-jul-2025|or_tau2_airline": 0.3695237142857143,
   "qwen3-30b-a3b-instruct-jul-2025|otis_mock_aime": 0.6222222222222222,
   "qwen3-30b-a3b-thinking-jul-2025|gpqa_diamond": 0.7007575757575758,
   "qwen3-30b-a3b-thinking-jul-2025|otis_mock_aime": 0.7027777777777777,
   "qwen3-30b-a3b|gpqa_diamond": 0.6167929292929293,
   "qwen3-30b-a3b|or_gpqa_diamond": 0.604377,
   "qwen3-30b-a3b|or_tau2_airline": 0.423333,
   "qwen3-30b-a3b|otis_mock_aime": 0.6277777777777778,
   "qwen3-32b|aider_polyglot": 0.4,
   "qwen3-32b|bfcl_overall": 0.48710000000000003,
   "qwen3-32b|gpqa_diamond": 0.6571969696969697,
   "qwen3-32b|or_gpqa_diamond": 0.5572391666666667,
   "qwen3-32b|or_tau2_airline": 0.4516665,
   "qwen3-32b|otis_mock_aime": 0.6694444444444444,
   "qwen3-4b-instruct-2507|bfcl_overall": 0.3568,
   "qwen3-4b-instruct-2507|gpqa_diamond": 0.4583333333333333,
   "qwen3-4b-instruct-2507|otis_mock_aime": 0.5222222222222223,
   "qwen3-4b|gpqa_diamond": 0.5233585858585859,
   "qwen3-5-122b-a10b|mystery_game_puzzles": 0.17,
   "qwen3-5-122b-a10b|or_gpqa_diamond": 0.8073469346289753,
   "qwen3-5-122b-a10b|or_tau2_airline": 0.7471783002257337,
   "qwen3-5-35b-a3b|gpqa_diamond": 0.8345959595959596,
   "qwen3-5-35b-a3b|or_gpqa_diamond": 0.7500000000000001,
   "qwen3-5-35b-a3b|or_tau2_airline": 0.7351189375,
   "qwen3-5-35b-a3b|otis_mock_aime": 0.7,
   "qwen3-5-397b-a17b|frontiermath_t13": 0.312280701754386,
   "qwen3-5-397b-a17b|gpqa_diamond": 0.8636363636363636,
   "qwen3-5-397b-a17b|mystery_game_puzzles": 0.18,
   "qwen3-5-397b-a17b|or_gpqa_diamond": 0.8728152090966519,
   "qwen3-5-397b-a17b|or_tau2_airline": 0.7811111111111111,
   "qwen3-5-397b-a17b|otis_mock_aime": 0.8888888888888888,
   "qwen3-5-4b|otis_mock_aime": 0.5583333333333333,
   "qwen3-5-9b|gpqa_diamond": 0.7897727272727273,
   "qwen3-5-9b|or_gpqa_diamond": 0.7462993119730186,
   "qwen3-5-9b|or_tau2_airline": 0.650067849593496,
   "qwen3-5-9b|otis_mock_aime": 0.6166666666666667,
   "qwen3-6-27b|frontiermath_t13": 0.3508771929824561,
   "qwen3-6-27b|gpqa_diamond": 0.8585858585858586,
   "qwen3-6-27b|mystery_game_puzzles": 0.07,
   "qwen3-6-27b|or_gpqa_diamond": 0.801499818181818,
   "qwen3-6-27b|or_tau2_airline": 0.7627176144578314,
   "qwen3-6-27b|otis_mock_aime": 0.9111111111111111,
   "qwen3-7-flash|frontiermath_t13": 0.19298245614035087,
   "qwen3-7-flash|gpqa_diamond": 0.8232323232323232,
   "qwen3-7-flash|mystery_game_puzzles": 0.15,
   "qwen3-7-flash|otis_mock_aime": 0.8666666666666667,
   "qwen3-7-max|chess_puzzles": 0.26,
   "qwen3-7-max|frontiermath_t13": 0.6456140350877193,
   "qwen3-7-max|frontiermath_t4": 0.34146341463414637,
   "qwen3-7-max|gpqa_diamond": 0.9090909090909091,
   "qwen3-7-max|mystery_game_puzzles": 0.32,
   "qwen3-7-max|or_gpqa_diamond": 0.9090909999999999,
   "qwen3-7-max|or_tau2_airline": 0.72,
   "qwen3-7-max|otis_mock_aime": 0.9555555555555556,
   "qwen3-7-max|simpleqa_verified": 0.5576730190571715,
   "qwen3-7-max|swe_bench_verified": 0.7727272727272727,
   "qwen3-7-plus|frontiermath_t13": 0.34385964912280703,
   "qwen3-7-plus|gpqa_diamond": 0.8787878787878788,
   "qwen3-7-plus|mystery_game_puzzles": 0.17,
   "qwen3-7-plus|or_gpqa_diamond": 0.873737,
   "qwen3-7-plus|or_tau2_airline": 0.726667,
   "qwen3-7-plus|otis_mock_aime": 0.9333333333333333,
   "qwen3-8-flash|or_gpqa_diamond": 0.8962022556962025,
   "qwen3-8-flash|or_tau2_airline": 0.7,
   "qwen3-8-max-0902|chess_puzzles": 0.37,
   "qwen3-8-max-0902|frontiermath_t13": 0.656140350877193,
   "qwen3-8-max-0902|frontiermath_t4": 0.34146341463414637,
   "qwen3-8-max-0902|furniture_assembly": 0.2,
   "qwen3-8-max-0902|gpqa_diamond": 0.922979797979798,
   "qwen3-8-max-0902|otis_mock_aime": 1.0,
   "qwen3-8-max-0902|simpleqa_verified": 0.473,
   "qwen3-8b|bfcl_overall": 0.4257,
   "qwen3-8b|gpqa_diamond": 0.5675505050505051,
   "qwen3-8b|otis_mock_aime": 0.5611111111111111,
   "qwen3-coder-480b-a35b|or_gpqa_diamond": 0.6035354999999999,
   "qwen3-coder-480b-a35b|or_tau2_airline": 0.43333342857142854,
   "qwen3-coder-next|or_gpqa_diamond": 0.7575756666666668,
   "qwen3-coder-next|or_tau2_airline": 0.5762463812316716,
   "qwen3-max|frontiermath_t13": 0.18947368421052632,
   "qwen3-max|gpqa_diamond": 0.726010101010101,
   "qwen3-max|math_level_5": 0.9712990936555891,
   "qwen3-max|mystery_game_puzzles": 0.05,
   "qwen3-max|otis_mock_aime": 0.7333333333333333,
   "qwen3-max|simpleqa_verified": 0.4874874874874875,
   "qwq-32b|aider_polyglot": 0.209,
   "qwq-32b|gpqa_diamond": 0.6534090909090909,
   "qwq-32b|otis_mock_aime": 0.5916666666666667,
   "qwq-plus|gpqa_diamond": 0.6540404040404041,
   "seed-oss-36b-instruct|gpqa_diamond": 0.7152777777777778,
   "seed-oss-36b-instruct|otis_mock_aime": 0.675,
   "tencent-hy4-preview|or_gpqa_diamond": 0.8973063333333335,
   "tencent-hy4-preview|or_tau2_airline": 0.7777776666666667,
   "wizardlm-2-8x22b|gpqa_diamond": 0.43434343434343436,
   "wizardlm-2-8x22b|math_level_5": 0.25736404833836857,
   "yi-lightning|aider_polyglot": 0.129
  },
  "n_inputs": 1259,
  "reference_rule": "models released in 2025 that were in the fit set at the first calibration",
  "specs": {
   "aider_polyglot": [
    0.0,
    1.0,
    225,
    "aider_polyglot"
   ],
   "bfcl_overall": [
    0.0,
    1.0,
    100,
    "bfcl_overall"
   ],
   "chess_puzzles": [
    0.0496,
    1.0,
    100,
    "chess_puzzles"
   ],
   "frontiermath_t13": [
    0.0,
    1.0,
    285,
    "frontiermath_t13"
   ],
   "frontiermath_t4": [
    0.0,
    1.0,
    41,
    "frontiermath_t4"
   ],
   "gpqa_diamond": [
    0.25,
    1.0,
    198,
    "gpqa_diamond"
   ],
   "math_level_5": [
    0.0,
    1.0,
    1324,
    "math_level_5"
   ],
   "mystery_game_puzzles": [
    0.0922,
    1.0,
    100,
    "mystery_game_puzzles"
   ],
   "or_gpqa_diamond": [
    0.25,
    1.0,
    198,
    "gpqa_diamond"
   ],
   "or_tau2_airline": [
    0.0,
    1.0,
    50,
    "or_tau2_airline"
   ],
   "otis_mock_aime": [
    0.001,
    1.0,
    45,
    "otis_mock_aime"
   ],
   "simpleqa_verified": [
    0.0,
    1.0,
    1000,
    "simpleqa_verified"
   ],
   "swe_bench_verified": [
    0.0,
    1.0,
    483,
    "swe_bench_verified"
   ]
  }
 },
 "constants": {
  "iq_mean": 100.0,
  "iq_sd": 15.0,
  "lambda": 0.1,
  "kappa": 1.0,
  "shift": 0.004023947402038472,
  "scale": 0.9948319582200694,
  "z90": 1.644854,
  "domain_shrink": 1.0,
  "sigma2_floor": 0.1
 },
 "formulas": {
  "transform": "p = clip((s - g)/(c - g), 0, 1); p_star = (p*n + 0.5)/(n + 1); y = ln(p_star/(1 - p_star)); s_star = g + (c - g)*p_star; v = s_star*(1 - s_star)*n / ((n + 1)^2*(c - g)^2*p_star^2*(1 - p_star)^2)",
  "family_factor": "f = 1 / (number of the model's inputs whose benchmark has the same family)",
  "weight": "w = omega * f / (sigma2 + v)",
  "theta": "D = lambda + sum(w*alpha^2); theta0 = sum(w*alpha*(y - beta)) / D; theta = (theta0 - shift) / scale",
  "se": "se = kappa * sqrt(sum(w^2*alpha^2*(sigma2 + v))) / D / scale",
  "si_iq": "SI-IQ = 100 + 15*theta (displayed: Python round(), nearest integer); 90% interval = SI-IQ +/- 1.644854*15*se",
  "domain": "theta_d0 = (sum_{b in d} w*alpha*(y - beta) + 1*theta0) / (sum_{b in d} w*alpha^2 + 1); theta_d = (theta_d0 - shift) / scale; se_d = kappa*sqrt(sum_{b in d} w^2*alpha^2*(sigma2 + v)) / (sum_{b in d} w*alpha^2 + 1) / scale"
 },
 "benchmarks": {
  "aider_polyglot": {
   "name": "Aider Polyglot",
   "domain": "coding",
   "family": "aider_polyglot",
   "g": 0.0,
   "c": 1.0,
   "n": 225,
   "alpha": 1.0582758589264192,
   "beta": 0.277197405395563,
   "sigma2": 0.4760751508726718,
   "omega": 0.7071067811865475,
   "n_models": 27,
   "evaluator": "Aider"
  },
  "bfcl_overall": {
   "name": "Berkeley Function Calling Leaderboard",
   "domain": "agentic",
   "family": "bfcl_overall",
   "g": 0.0,
   "c": 1.0,
   "n": 100,
   "alpha": 0.46897419215453057,
   "beta": 0.07939224698196412,
   "sigma2": 0.1,
   "omega": 0.7071067811865475,
   "n_models": 26,
   "evaluator": "UC Berkeley (Gorilla)"
  },
  "chess_puzzles": {
   "name": "Chess Puzzles",
   "domain": "reasoning",
   "family": "chess_puzzles",
   "g": 0.0496,
   "c": 1.0,
   "n": 100,
   "alpha": 1.077555345242871,
   "beta": -2.505422238223403,
   "sigma2": 0.1,
   "omega": 0.7071067811865475,
   "n_models": 77,
   "evaluator": "Epoch AI"
  },
  "frontiermath_t13": {
   "name": "FrontierMath Tiers 1–3",
   "domain": "math",
   "family": "frontiermath_t13",
   "g": 0.0,
   "c": 1.0,
   "n": 285,
   "alpha": 1.4982055760227184,
   "beta": -1.9558132085895066,
   "sigma2": 0.1,
   "omega": 0.5,
   "n_models": 83,
   "evaluator": "Epoch AI"
  },
  "frontiermath_t4": {
   "name": "FrontierMath Tier 4",
   "domain": "math",
   "family": "frontiermath_t4",
   "g": 0.0,
   "c": 1.0,
   "n": 41,
   "alpha": 2.319275484803002,
   "beta": -4.717531465625672,
   "sigma2": 0.1,
   "omega": 0.5,
   "n_models": 65,
   "evaluator": "Epoch AI"
  },
  "gpqa_diamond": {
   "name": "GPQA Diamond",
   "domain": "knowledge",
   "family": "gpqa_diamond",
   "g": 0.25,
   "c": 1.0,
   "n": 198,
   "alpha": 0.7514541895791892,
   "beta": 0.6536741200073863,
   "sigma2": 0.1,
   "omega": 0.5773502691896258,
   "n_models": 134,
   "evaluator": "Epoch AI"
  },
  "math_level_5": {
   "name": "MATH Level 5",
   "domain": "math",
   "family": "math_level_5",
   "g": 0.0,
   "c": 1.0,
   "n": 1324,
   "alpha": 1.26992309639644,
   "beta": 2.5830225587453803,
   "sigma2": 0.1,
   "omega": 0.5,
   "n_models": 43,
   "evaluator": "Epoch AI"
  },
  "mystery_game_puzzles": {
   "name": "Mystery Game Puzzles",
   "domain": "reasoning",
   "family": "mystery_game_puzzles",
   "g": 0.0922,
   "c": 1.0,
   "n": 100,
   "alpha": 1.1546407429325607,
   "beta": -3.0303217284525816,
   "sigma2": 0.1,
   "omega": 0.7071067811865475,
   "n_models": 77,
   "evaluator": "Epoch AI"
  },
  "or_gpqa_diamond": {
   "name": "GPQA Diamond (OpenRouter run)",
   "domain": "knowledge",
   "family": "gpqa_diamond",
   "g": 0.25,
   "c": 1.0,
   "n": 198,
   "alpha": 0.6767935558477154,
   "beta": 0.5161164701723159,
   "sigma2": 0.15464938853231347,
   "omega": 0.5773502691896258,
   "n_models": 93,
   "evaluator": "OpenRouter"
  },
  "or_tau2_airline": {
   "name": "τ²-bench Airline (OpenRouter run)",
   "domain": "agentic",
   "family": "or_tau2_airline",
   "g": 0.0,
   "c": 1.0,
   "n": 50,
   "alpha": 0.4065176892579318,
   "beta": 0.28965775238487407,
   "sigma2": 0.1,
   "omega": 0.7071067811865475,
   "n_models": 92,
   "evaluator": "OpenRouter"
  },
  "otis_mock_aime": {
   "name": "OTIS Mock AIME 2024–2025",
   "domain": "math",
   "family": "otis_mock_aime",
   "g": 0.001,
   "c": 1.0,
   "n": 45,
   "alpha": 1.3759995626974122,
   "beta": 0.6346502858710217,
   "sigma2": 0.1,
   "omega": 0.5,
   "n_models": 136,
   "evaluator": "Epoch AI"
  },
  "simpleqa_verified": {
   "name": "SimpleQA Verified",
   "domain": "knowledge",
   "family": "simpleqa_verified",
   "g": 0.0,
   "c": 1.0,
   "n": 1000,
   "alpha": 0.6277165647729661,
   "beta": -1.2106020979707044,
   "sigma2": 0.3373458171014145,
   "omega": 0.5773502691896258,
   "n_models": 79,
   "evaluator": "Epoch AI"
  },
  "swe_bench_verified": {
   "name": "SWE-bench Verified (Epoch AI run)",
   "domain": "coding",
   "family": "swe_bench_verified",
   "g": 0.0,
   "c": 1.0,
   "n": 483,
   "alpha": 0.46856978897928453,
   "beta": 0.43227851130367834,
   "sigma2": 0.1,
   "omega": 0.7071067811865475,
   "n_models": 31,
   "evaluator": "Epoch AI"
  }
 },
 "excluded_benchmarks": {
  "furniture_assembly": "fewer than 3 reference-group models"
 },
 "reference_cohort": [
  "claude-3-7-sonnet",
  "claude-haiku-4-5",
  "claude-opus-4",
  "claude-opus-4-1",
  "claude-opus-4-5",
  "claude-sonnet-4",
  "claude-sonnet-4-5",
  "deepseek-r1",
  "deepseek-r1-may-2025",
  "deepseek-v3-2-exp",
  "deepseek-v3-mar-2025",
  "gemini-2-5-pro-jun-2025",
  "gemini-3-flash",
  "gemini-3-pro",
  "gemma-3-12b",
  "gemma-3-27b",
  "gemma-3-4b",
  "glm-4-7",
  "gpt-4-1",
  "gpt-4-1-mini",
  "gpt-4-1-nano",
  "gpt-5",
  "gpt-5-1",
  "gpt-5-2",
  "gpt-5-mini",
  "gpt-5-nano",
  "gpt-oss-120b",
  "gpt-oss-20b",
  "grok-3",
  "grok-3-mini",
  "grok-4",
  "llama-4-maverick",
  "llama-4-scout",
  "mistral-medium-3",
  "o3",
  "o3-mini",
  "o4-mini",
  "qwen2-5-max",
  "qwen3-14b",
  "qwen3-235b-a22b-thinking-jul-2025",
  "qwen3-30b-a3b",
  "qwen3-30b-a3b-instruct-jul-2025",
  "qwen3-32b",
  "qwen3-max"
 ],
 "models": [
  {
   "slug": "gpt-6-astra",
   "name": "GPT-6 Astra",
   "tier": "main",
   "rank": 1,
   "theta": 3.3095586346641253,
   "se": 0.15567975311697724,
   "si_iq": 149.64337951996188,
   "si_iq_low": 145.8023225504598,
   "si_iq_high": 153.48443648946397,
   "si_iq_display": 150,
   "domains": {
    "reasoning": {
     "si_iq": 153.57414196202598,
     "n": 2
    },
    "math": {
     "si_iq": 148.21616069804037,
     "n": 3
    },
    "knowledge": {
     "si_iq": 148.5536955946998,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.74,
     "source_value_text": "0.74",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "KaEir82ukWPm2Fq4FanY2M",
     "source_model_name": "gpt-6-astra_max",
     "p": 0.7264309764309764,
     "p_star": 0.7241890855752242,
     "y": 0.9653369879388152,
     "v": 0.05261564173766769,
     "family_factor": 1.0,
     "w": 4.633252353005855
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.84,
     "source_value_text": "0.84",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "FA7pM9hKdkgTXmGHptcno7",
     "source_model_name": "gpt-6-astra_max",
     "p": 0.8237497246089448,
     "p_star": 0.8205442817910344,
     "y": 1.5200393960705627,
     "v": 0.0748131483117406,
     "family_factor": 1.0,
     "w": 4.044929045757924
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.976,
     "source_value_text": "0.976",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "AfKJ2DGMhkjZmeFZxGoY3w",
     "source_model_name": "gpt-6-astra_xhigh",
     "p": 0.976,
     "p_star": 0.9646666666666667,
     "y": 3.3069558130793624,
     "v": 0.6819042438792943,
     "family_factor": 1.0,
     "w": 0.6394644918658186
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.9368421052631579,
     "source_value_text": "0.9368421052631579",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "csK2fe5T8p2R7WgoJUu6bZ",
     "source_model_name": "gpt-6-astra_max",
     "p": 0.9368421052631579,
     "p_star": 0.9353146853146853,
     "y": 2.671348834251782,
     "v": 0.0575903005809548,
     "family_factor": 1.0,
     "w": 3.172784100016028
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "L7kW8yxFKCjVXhxNnt3VTq",
     "source_model_name": "gpt-6-astra_max",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9577020202020202,
     "source_value_text": "0.9577020202020202",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "3h8STJpG2VzY9LiBUzwotv",
     "source_model_name": "gpt-6-astra_max",
     "p": 0.9436026936026937,
     "p_star": 0.9413735343383585,
     "y": 2.7761537884042773,
     "v": 0.12267376118771112,
     "family_factor": 0.5,
     "w": 1.2964039097155389
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9472503333333333,
     "source_value_text": "0.94725",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-6-astra-20260903",
     "source_model_name": "openai/gpt-6-astra-20260903",
     "p": 0.9296671111111111,
     "p_star": 0.9275079798994974,
     "y": 2.5490249098863313,
     "v": 0.10108668537641989,
     "family_factor": 0.5,
     "w": 1.1288009946451074
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.756,
     "source_value_text": "0.756",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "PppwnX7EjXx2SeTcFN8Ujn",
     "source_model_name": "gpt-6-astra_max",
     "p": 0.756,
     "p_star": 0.7557442557442557,
     "y": 1.129487224313484,
     "v": 0.005406450165369794,
     "family_factor": 1.0,
     "w": 1.6844535378091026
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6766665000000001,
     "source_value_text": "0.676667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-6-astra-20260903",
     "source_model_name": "openai/gpt-6-astra-20260903",
     "p": 0.6766665000000001,
     "p_star": 0.6732024509803922,
     "y": 0.722705240083139,
     "v": 0.08737861829580298,
     "family_factor": 1.0,
     "w": 3.773679129548719
    }
   ]
  },
  {
   "slug": "gpt-6-1-sol",
   "name": "GPT-6.1 Sol",
   "tier": "main",
   "rank": 2,
   "theta": 3.195594556613456,
   "se": 0.16230759078878862,
   "si_iq": 147.93391834920183,
   "si_iq_low": 143.9293340001123,
   "si_iq_high": 151.93850269829136,
   "si_iq_display": 148,
   "domains": {
    "reasoning": {
     "si_iq": 149.9995623644839,
     "n": 2
    },
    "math": {
     "si_iq": 148.14647435531015,
     "n": 3
    },
    "knowledge": {
     "si_iq": 146.74872703027182,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.68,
     "source_value_text": "0.68",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "KkGEgrjYDnofMoUJBCykcH",
     "source_model_name": "gpt-6.1-sol_max",
     "p": 0.6632996632996634,
     "p_star": 0.6616828349501618,
     "y": 0.6708025262117152,
     "v": 0.047244739385146485,
     "family_factor": 1.0,
     "w": 4.802254967744388
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.8,
     "source_value_text": "0.8",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "fQzkNRV69sKaJX7o9KKneQ",
     "source_model_name": "gpt-6.1-sol_max",
     "p": 0.7796871557611809,
     "p_star": 0.7769179760011692,
     "y": 1.247795255349955,
     "v": 0.0639551174573166,
     "family_factor": 1.0,
     "w": 4.312807017875686
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "HgAUm5zxrWbkfYUdeJMGzL",
     "source_model_name": "gpt-6.1-sol_max",
     "p": 1.0,
     "p_star": 0.9880952380952381,
     "y": 4.418840607796602,
     "v": 1.9759036144578381,
     "family_factor": 1.0,
     "w": 0.2408589669181652
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.9368421052631579,
     "source_value_text": "0.9368421052631579",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "aBoQLaqnXsLPrsbN8wYgUp",
     "source_model_name": "gpt-6.1-sol_max",
     "p": 0.9368421052631579,
     "p_star": 0.9353146853146853,
     "y": 2.671348834251782,
     "v": 0.0575903005809548,
     "family_factor": 1.0,
     "w": 3.172784100016028
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "Di7y6sES4PGQbXNkXYhdqM",
     "source_model_name": "gpt-6.1-sol_max",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9539141414141414,
     "source_value_text": "0.9539141414141414",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "LspviLnbeZ82WCngWp6rwR",
     "source_model_name": "gpt-6.1-sol_max",
     "p": 0.9385521885521886,
     "p_star": 0.9363484087102178,
     "y": 2.688563313428715,
     "v": 0.11375478997544118,
     "family_factor": 0.5,
     "w": 1.3504966818660744
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.944444,
     "source_value_text": "0.944444",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-6.1-sol-20260929",
     "source_model_name": "openai/gpt-6.1-sol-20260929",
     "p": 0.9259253333333333,
     "p_star": 0.9237850050251256,
     "y": 2.494921138243344,
     "v": 0.09663911785674031,
     "family_factor": 0.5,
     "w": 1.1487796984549539
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.739,
     "source_value_text": "0.739",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "dfT5VD7cQug8XW6GQHyJUF",
     "source_model_name": "gpt-6.1-sol_max",
     "p": 0.739,
     "p_star": 0.7387612387612388,
     "y": 1.0395399986458769,
     "v": 0.0051711856365147775,
     "family_factor": 1.0,
     "w": 1.685610537796791
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6822223333333333,
     "source_value_text": "0.682222",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-6.1-sol-20260929",
     "source_model_name": "openai/gpt-6.1-sol-20260929",
     "p": 0.6822223333333333,
     "p_star": 0.6786493464052287,
     "y": 0.7475716619443719,
     "v": 0.08814649123272188,
     "family_factor": 1.0,
     "w": 3.7582778002057666
    }
   ]
  },
  {
   "slug": "claude-opus-5-5",
   "name": "Claude Opus 5.5",
   "tier": "main",
   "rank": 3,
   "theta": 2.9616009093147344,
   "se": 0.1434930419939202,
   "si_iq": 144.424013639721,
   "si_iq_low": 140.88363707828302,
   "si_iq_high": 147.96439020115903,
   "si_iq_display": 144,
   "domains": {
    "reasoning": {
     "si_iq": 146.47867019475126,
     "n": 2
    },
    "math": {
     "si_iq": 145.04912950647645,
     "n": 3
    },
    "knowledge": {
     "si_iq": 137.4892280637899,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.67,
     "source_value_text": "0.67",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "F2tuCm5VmNDAaYYh6qYdRy",
     "source_model_name": "claude-opus-5-5_max",
     "p": 0.6527777777777778,
     "p_star": 0.6512651265126513,
     "y": 0.6246048610067254,
     "v": 0.046621015763339275,
     "family_factor": 1.0,
     "w": 4.822683689000541
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.71,
     "source_value_text": "0.71",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "fREi6AAmnfqUWkDqUhLLtw",
     "source_model_name": "claude-opus-5-5_max",
     "p": 0.6805463758537122,
     "p_star": 0.6787587879739725,
     "y": 0.748073538181378,
     "v": 0.051685590056178315,
     "family_factor": 1.0,
     "w": 4.661660879749112
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.95,
     "source_value_text": "0.95",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "9qKrTxPhpfW985gieKU56x",
     "source_model_name": "claude-opus-5-5_max",
     "p": 0.95,
     "p_star": 0.9392857142857142,
     "y": 2.7389406881215463,
     "v": 0.40756480031809855,
     "family_factor": 1.0,
     "w": 0.9850958925572506
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.9122807017543859,
     "source_value_text": "0.9122807017543859",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "LPxhvBNEn7S3xkRZUgcvc9",
     "source_model_name": "claude-opus-5-5_max",
     "p": 0.9122807017543859,
     "p_star": 0.9108391608391608,
     "y": 2.323924409029041,
     "v": 0.04290391780512589,
     "family_factor": 1.0,
     "w": 3.4988543888757206
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "LSfona7P3jCAnZFXJ2YA7F",
     "source_model_name": "claude-opus-5-5_max",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9059343434343434,
     "source_value_text": "0.9059343434343434",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "6gmbahPSxHf9xVhAYqpnhi",
     "source_model_name": "claude-opus-5-5_max",
     "p": 0.8745791245791246,
     "p_star": 0.8726968174204355,
     "y": 1.9250167014670354,
     "v": 0.06219438206887648,
     "family_factor": 0.5,
     "w": 1.7798097006357834
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9020199999999999,
     "source_value_text": "0.90202",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-opus-5.5-20260921",
     "source_model_name": "anthropic/claude-opus-5.5-20260921",
     "p": 0.8693599999999999,
     "p_star": 0.8675039195979899,
     "y": 1.8790669669622804,
     "v": 0.060213970782031966,
     "family_factor": 0.5,
     "w": 1.3435289084002486
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.722,
     "source_value_text": "0.722",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "CgLfiGcNwMPVzxr8GdNUAK",
     "source_model_name": "claude-opus-5-5_max",
     "p": 0.722,
     "p_star": 0.7217782217782218,
     "y": 0.9532993606192487,
     "v": 0.004969777540332852,
     "family_factor": 1.0,
     "w": 1.686602299827607
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.756,
     "source_value_text": "0.756",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-opus-5.5-20260921",
     "source_model_name": "anthropic/claude-opus-5.5-20260921",
     "p": 0.756,
     "p_star": 0.7509803921568627,
     "y": 1.1038479027220547,
     "v": 0.10279393926934069,
     "family_factor": 1.0,
     "w": 3.4868240329776516
    }
   ]
  },
  {
   "slug": "claude-sonnet-5-5",
   "name": "Claude Sonnet 5.5",
   "tier": "main",
   "rank": 4,
   "theta": 2.6861593309793705,
   "se": 0.12888506679691783,
   "si_iq": 140.29238996469056,
   "si_iq_low": 137.1124331997729,
   "si_iq_high": 143.4723467296082,
   "si_iq_display": 140,
   "domains": {
    "reasoning": {
     "si_iq": 142.19985108629936,
     "n": 2
    },
    "math": {
     "si_iq": 139.93347756468063,
     "n": 3
    },
    "knowledge": {
     "si_iq": 136.98018579009783,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.59,
     "source_value_text": "0.59",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "kXU32N6tFkQLx5ei6nRJFS",
     "source_model_name": "claude-sonnet-5-5_max",
     "p": 0.5686026936026936,
     "p_star": 0.5679234590125679,
     "y": 0.2733839036197291,
     "v": 0.043620143680307207,
     "family_factor": 1.0,
     "w": 4.923451286614358
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.65,
     "source_value_text": "0.65",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "3PVdaSEYFJKgYUgHnF4DBu",
     "source_model_name": "claude-sonnet-5-5_max",
     "p": 0.6144525225820666,
     "p_star": 0.6133193292891749,
     "y": 0.46128651686150857,
     "v": 0.04817999927339512,
     "family_factor": 1.0,
     "w": 4.771944828275515
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.8048780487804879,
     "source_value_text": "0.8048780487804879",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "Xo7ecFEMqPJ4HicvJTvWZZ",
     "source_model_name": "claude-sonnet-5-5_max",
     "p": 0.8048780487804879,
     "p_star": 0.7976190476190477,
     "y": 1.3714792753347502,
     "v": 0.14398595258999128,
     "family_factor": 1.0,
     "w": 2.049298308744152
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.887719298245614,
     "source_value_text": "0.887719298245614",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "4tZWwV9tqEgsCaKeSuSoG4",
     "source_model_name": "claude-sonnet-5-5_max",
     "p": 0.887719298245614,
     "p_star": 0.8863636363636364,
     "y": 2.054123733695546,
     "v": 0.03459262630860264,
     "family_factor": 1.0,
     "w": 3.714913763949949
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "bSEaZLPehiNVDQL7HP9EJS",
     "source_model_name": "claude-sonnet-5-5_max",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9558080808080808,
     "source_value_text": "0.9558080808080808",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "QPk8jbJvo4986sbWtdte6J",
     "source_model_name": "claude-sonnet-5-5_max",
     "p": 0.9410774410774411,
     "p_star": 0.9388609715242882,
     "y": 2.7315169819237695,
     "v": 0.11802972074074458,
     "family_factor": 0.5,
     "w": 1.3240173569642444
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.92929275,
     "source_value_text": "0.929293",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-sonnet-5.5-20260928",
     "source_model_name": "anthropic/claude-sonnet-5.5-20260928",
     "p": 0.9057236666666667,
     "p_star": 0.9036848542713568,
     "y": 2.2388551041260096,
     "v": 0.07863330491593591,
     "family_factor": 0.5,
     "w": 1.2374477091625815
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.465,
     "source_value_text": "0.465",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-29",
     "source_row_id": "GtJ5yd3ZPQ7HVcm6Q9ssQz",
     "source_model_name": "claude-sonnet-5-5_max",
     "p": 0.465,
     "p_star": 0.46503496503496505,
     "y": -0.14008879317068168,
     "v": 0.004011629714542459,
     "family_factor": 1.0,
     "w": 1.6913363823608178
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.775,
     "source_value_text": "0.775",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-sonnet-5.5-20260928",
     "source_model_name": "anthropic/claude-sonnet-5.5-20260928",
     "p": 0.775,
     "p_star": 0.7696078431372549,
     "y": 1.2060982036382497,
     "v": 0.10841577449518908,
     "family_factor": 1.0,
     "w": 3.3927699709835055
    }
   ]
  },
  {
   "slug": "gpt-6-sol",
   "name": "GPT-6 Sol",
   "tier": "main",
   "rank": 5,
   "theta": 2.686015209956208,
   "se": 0.13573428753269662,
   "si_iq": 140.2902281493431,
   "si_iq_low": 136.94128186256353,
   "si_iq_high": 143.63917443612272,
   "si_iq_display": 140,
   "domains": {
    "reasoning": {
     "si_iq": 138.88508999554466,
     "n": 2
    },
    "math": {
     "si_iq": 142.64020382643577,
     "n": 3
    },
    "knowledge": {
     "si_iq": 138.16928842394947,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.56,
     "source_value_text": "0.56",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "N9uFn7EZFsvHNcHEwEy3J6",
     "source_model_name": "gpt-6-sol_max",
     "p": 0.5370370370370371,
     "p_star": 0.5366703337000367,
     "y": 0.1469451793036918,
     "v": 0.04325767759042059,
     "family_factor": 1.0,
     "w": 4.935908448887423
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.56,
     "source_value_text": "0.56",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "DnFTaE9qNsmBdYNqohhynY",
     "source_model_name": "gpt-6-sol_max",
     "p": 0.515311742674598,
     "p_star": 0.5151601412619783,
     "y": 0.06065915799000418,
     "v": 0.04698568187340877,
     "family_factor": 1.0,
     "w": 4.810718786851241
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.9,
     "source_value_text": "0.9",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "jwS3LYLCPbZpHDzzkX6LyV",
     "source_model_name": "gpt-6-sol_max",
     "p": 0.9,
     "p_star": 0.8904761904761904,
     "y": 2.0956144009254363,
     "v": 0.23831667054173442,
     "family_factor": 1.0,
     "w": 1.477905298604907
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8982456140350877,
     "source_value_text": "0.8982456140350877",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "RHjHEPHEsWZqFuMjBTeC6r",
     "source_model_name": "gpt-6-sol_max",
     "p": 0.8982456140350877,
     "p_star": 0.8968531468531469,
     "y": 2.1627384012650506,
     "v": 0.037664783427495296,
     "family_factor": 1.0,
     "w": 3.6320109439124484
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "VZAUcNkzeMSMm9paxBhj6B",
     "source_model_name": "gpt-6-sol_max",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9431818181818182,
     "source_value_text": "0.9431818181818182",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "aJD7ZfFftu2cZoToJhhzF7",
     "source_model_name": "gpt-6-sol_max",
     "p": 0.9242424242424243,
     "p_star": 0.9221105527638191,
     "y": 2.471374643569425,
     "v": 0.09477891601656295,
     "family_factor": 0.5,
     "w": 1.4820656182841965
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9208749999999999,
     "source_value_text": "0.920875",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-6-sol-20260922",
     "source_model_name": "openai/gpt-6-sol-20260922",
     "p": 0.8944999999999999,
     "p_star": 0.8925175879396983,
     "y": 2.11671899439367,
     "v": 0.07158560917056943,
     "family_factor": 0.5,
     "w": 1.2759968065327072
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.607,
     "source_value_text": "0.607",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "donMeEKBZZdqpQsojKWJEm",
     "source_model_name": "gpt-6-sol_max",
     "p": 0.607,
     "p_star": 0.6068931068931069,
     "y": 0.43427110735724583,
     "v": 0.004183203392577953,
     "family_factor": 1.0,
     "w": 1.6904867069701375
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7022223333333333,
     "source_value_text": "0.702222",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-6-sol-20260922",
     "source_model_name": "openai/gpt-6-sol-20260922",
     "p": 0.7022223333333333,
     "p_star": 0.6982571895424835,
     "y": 0.8390124677504543,
     "v": 0.09123832527625465,
     "family_factor": 1.0,
     "w": 3.69751607145216
    }
   ]
  },
  {
   "slug": "gemini-4-argon",
   "name": "Gemini 4 Argon",
   "tier": "main",
   "rank": 6,
   "theta": 2.6770414062510657,
   "se": 0.12754242062448393,
   "si_iq": 140.155621093766,
   "si_iq_low": 137.00879118275802,
   "si_iq_high": 143.30245100477396,
   "si_iq_display": 140,
   "domains": {
    "reasoning": {
     "si_iq": 141.90223328121442,
     "n": 2
    },
    "math": {
     "si_iq": 138.4159330008676,
     "n": 3
    },
    "knowledge": {
     "si_iq": 147.7202895962101,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.59,
     "source_value_text": "0.59",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "GJtYeC7ZV4fYgN3wu4rRvq",
     "source_model_name": "gemini-4-argon_high",
     "p": 0.5686026936026936,
     "p_star": 0.5679234590125679,
     "y": 0.2733839036197291,
     "v": 0.043620143680307207,
     "family_factor": 1.0,
     "w": 4.923451286614358
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.64,
     "source_value_text": "0.64",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "9ipFgNR5MDw7ustUsuSviu",
     "source_model_name": "gemini-4-argon_high",
     "p": 0.6034368803701257,
     "p_star": 0.6024127528417086,
     "y": 0.4155284466011199,
     "v": 0.04782940153067131,
     "family_factor": 1.0,
     "w": 4.783262151269946
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.7804878048780488,
     "source_value_text": "0.7804878048780488",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "6FQCa8tMipf2ncdgGgMaPc",
     "source_model_name": "gemini-4-argon_high",
     "p": 0.7804878048780488,
     "p_star": 0.7738095238095238,
     "y": 1.2299482907291968,
     "v": 0.1327935222672065,
     "family_factor": 1.0,
     "w": 2.1478260869565213
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8596491228070176,
     "source_value_text": "0.8596491228070176",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "N8daAyKM6Sah39YBcPRi4W",
     "source_model_name": "gemini-4-argon_high",
     "p": 0.8596491228070176,
     "p_star": 0.8583916083916084,
     "y": 1.8019949731220821,
     "v": 0.0286641019838576,
     "family_factor": 1.0,
     "w": 3.886087823181098
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "43f36RTDoJGxXWQDVvTLJj",
     "source_model_name": "gemini-4-argon_high",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9640151515151515,
     "source_value_text": "0.9640151515151515",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "QEouTvczNsxgkR4i7i8wBF",
     "source_model_name": "gemini-4-argon_high",
     "p": 0.952020202020202,
     "p_star": 0.949748743718593,
     "y": 2.9391619220655967,
     "v": 0.14153019232384315,
     "family_factor": 0.5,
     "w": 1.195192749268207
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.964646,
     "source_value_text": "0.964646",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-14",
     "source_row_id": "google/gemini-4-argon-20261013",
     "source_model_name": "google/gemini-4-argon-20261013",
     "p": 0.9528613333333333,
     "p_star": 0.950585648241206,
     "y": 2.9568373630529576,
     "v": 0.14376760842709574,
     "family_factor": 0.5,
     "w": 0.9673548676387177
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.76,
     "source_value_text": "0.76",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "iq4Y9tXpiyLP25yotySxJW",
     "source_model_name": "gemini-4-argon_high",
     "p": 0.76,
     "p_star": 0.7597402597402597,
     "y": 1.1512560221535315,
     "v": 0.005467461088762863,
     "family_factor": 1.0,
     "w": 1.6841537534299882
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.786667,
     "source_value_text": "0.786667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-14",
     "source_row_id": "google/gemini-4-argon-20261013",
     "source_model_name": "google/gemini-4-argon-20261013",
     "p": 0.786667,
     "p_star": 0.7810460784313726,
     "y": 1.2717728434889266,
     "v": 0.11240878869870048,
     "family_factor": 1.0,
     "w": 3.3289902245503153
    }
   ]
  },
  {
   "slug": "gpt-5-6-sol",
   "name": "GPT-5.6 Sol",
   "tier": "main",
   "rank": 7,
   "theta": 2.667332839342068,
   "se": 0.1297703790432378,
   "si_iq": 140.00999259013102,
   "si_iq_low": 136.80819268436923,
   "si_iq_high": 143.2117924958928,
   "si_iq_display": 140,
   "domains": {
    "reasoning": {
     "si_iq": 140.194625202822,
     "n": 2
    },
    "math": {
     "si_iq": 140.5957161038774,
     "n": 3
    },
    "knowledge": {
     "si_iq": 139.42552053160745,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.59,
     "source_value_text": "0.59",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "oWqwMmwEd7LU3eU5Ftak64",
     "source_model_name": "gpt-5.6-sol_max",
     "p": 0.5686026936026936,
     "p_star": 0.5679234590125679,
     "y": 0.2733839036197291,
     "v": 0.043620143680307207,
     "family_factor": 1.0,
     "w": 4.923451286614358
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.58,
     "source_value_text": "0.58",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-28",
     "source_row_id": "5kMRXeasRvtghXpDotCdgV",
     "source_model_name": "gpt-5.6-sol_max",
     "p": 0.5373430270984798,
     "p_star": 0.5369732941569108,
     "y": 0.14816362929135468,
     "v": 0.04688482032295081,
     "family_factor": 1.0,
     "w": 4.814022168062398
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.8292682926829268,
     "source_value_text": "0.8292682926829268",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "QJ5rJMVypB4PMxPcBGftc8",
     "source_model_name": "gpt-5.6-sol_max",
     "p": 0.8292682926829268,
     "p_star": 0.8214285714285714,
     "y": 1.526056303495049,
     "v": 0.15845410628019319,
     "family_factor": 1.0,
     "w": 1.934579439252337
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8912280701754386,
     "source_value_text": "0.8912280701754386",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "VBpT2WWYKBZtUxG9Z3svGh",
     "source_model_name": "gpt-5.6-sol_max",
     "p": 0.8912280701754386,
     "p_star": 0.8898601398601399,
     "y": 2.0893132901589904,
     "v": 0.03555056600243242,
     "family_factor": 1.0,
     "w": 3.688660363034025
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "7RjsANKwwsePSstcZeSMhX",
     "source_model_name": "gpt-5.6-sol_max",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9349747474747475,
     "source_value_text": "0.9349747474747475",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "nuKCgZReCBsXKCkNj9bK37",
     "source_model_name": "gpt-5.6-sol_max",
     "p": 0.9132996632996634,
     "p_star": 0.9112227805695143,
     "y": 2.328657333303822,
     "v": 0.08441562581608679,
     "family_factor": 0.5,
     "w": 1.5653507305433088
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9234005000000001,
     "source_value_text": "0.923401",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.6-sol-20260709",
     "source_model_name": "openai/gpt-5.6-sol-20260709",
     "p": 0.8978673333333335,
     "p_star": 0.8958680000000001,
     "y": 2.1521337555753557,
     "v": 0.07353765931683934,
     "family_factor": 0.5,
     "w": 1.2650811573917502
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.697,
     "source_value_text": "0.697",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "UnRUSuZzm2X27TUbpeMPva",
     "source_model_name": "gpt-5.6-sol_max",
     "p": 0.697,
     "p_star": 0.6968031968031968,
     "y": 0.8321209031959678,
     "v": 0.00472386081144119,
     "family_factor": 1.0,
     "w": 1.6878148122111813
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.73333325,
     "source_value_text": "0.733333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.6-sol-20260709",
     "source_model_name": "openai/gpt-5.6-sol-20260709",
     "p": 0.73333325,
     "p_star": 0.7287580882352941,
     "y": 0.9883307503511172,
     "v": 0.09724996810336443,
     "family_factor": 1.0,
     "w": 3.5848258328538942
    }
   ]
  },
  {
   "slug": "claude-fable-5-1",
   "name": "Claude Fable 5.1",
   "tier": "main",
   "rank": 8,
   "theta": 2.6504977510162475,
   "se": 0.13575011021273498,
   "si_iq": 139.75746626524372,
   "si_iq_low": 136.40812958848585,
   "si_iq_high": 143.1068029420016,
   "si_iq_display": 140,
   "domains": {
    "reasoning": {
     "si_iq": 137.37759208159258,
     "n": 2
    },
    "math": {
     "si_iq": 142.22798910551452,
     "n": 3
    },
    "knowledge": {
     "si_iq": 136.7422011551218,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.48,
     "source_value_text": "0.48",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "aLrHd8RCiNo3Yb4GqSawM7",
     "source_model_name": "claude-fable-5-1_max",
     "p": 0.45286195286195285,
     "p_star": 0.4533286661999533,
     "y": -0.1872303746909695,
     "v": 0.04411035357981414,
     "family_factor": 1.0,
     "w": 4.906703533933967
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.58,
     "source_value_text": "0.58",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-01",
     "source_row_id": "dBHxnnTzLGz3nHis5LET6t",
     "source_model_name": "claude-fable-5-1_max",
     "p": 0.5373430270984798,
     "p_star": 0.5369732941569108,
     "y": 0.14816362929135468,
     "v": 0.04688482032295081,
     "family_factor": 1.0,
     "w": 4.814022168062398
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.8780487804878049,
     "source_value_text": "0.8780487804878049",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-01",
     "source_row_id": "T56N3X4KLA3xz7tf5aCMGb",
     "source_model_name": "claude-fable-5-1_max",
     "p": 0.8780487804878049,
     "p_star": 0.8690476190476191,
     "y": 1.8925641683500207,
     "v": 0.20423412204234123,
     "family_factor": 1.0,
     "w": 1.643471142038477
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.9017543859649123,
     "source_value_text": "0.9017543859649123",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-01",
     "source_row_id": "g7dXwZH2tWvqLg3X5idGs2",
     "source_model_name": "claude-fable-5-1_max",
     "p": 0.9017543859649123,
     "p_star": 0.9003496503496503,
     "y": 2.2011156328291857,
     "v": 0.03883495145631066,
     "family_factor": 1.0,
     "w": 3.6013986013986017
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-01",
     "source_row_id": "mRAASXsUuoJmc2oR5G89zR",
     "source_model_name": "claude-fable-5-1_max",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8894498333333334,
     "source_value_text": "0.88945",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "anthropic/claude-fable-5.1-20260831",
     "source_model_name": "anthropic/claude-fable-5.1-20260831",
     "p": 0.8525997777777778,
     "p_star": 0.8508279195979901,
     "y": 1.7411093569021143,
     "v": 0.05482755407390603,
     "family_factor": 1.0,
     "w": 2.7561518800422093
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.708,
     "source_value_text": "0.708",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-01",
     "source_row_id": "ExyL3GN8s34tizrXV3VmS3",
     "source_model_name": "claude-fable-5-1_max",
     "p": 0.708,
     "p_star": 0.7077922077922078,
     "y": 0.8846853924588237,
     "v": 0.004825410612284289,
     "family_factor": 1.0,
     "w": 1.687313901426878
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7906666,
     "source_value_text": "0.790667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "anthropic/claude-fable-5.1-20260831",
     "source_model_name": "anthropic/claude-fable-5.1-20260831",
     "p": 0.7906666,
     "p_star": 0.7849672549019607,
     "y": 1.2948516840993396,
     "v": 0.11388683207020839,
     "family_factor": 1.0,
     "w": 3.30598557350384
    }
   ]
  },
  {
   "slug": "gpt-5-5",
   "name": "GPT-5.5",
   "tier": "main",
   "rank": 9,
   "theta": 2.5266215194956603,
   "se": 0.12303872205123649,
   "si_iq": 137.8993227924349,
   "si_iq_low": 134.86361178062194,
   "si_iq_high": 140.93503380424787,
   "si_iq_display": 138,
   "domains": {
    "reasoning": {
     "si_iq": 140.52218154069348,
     "n": 2
    },
    "math": {
     "si_iq": 137.07712425559288,
     "n": 3
    },
    "knowledge": {
     "si_iq": 138.51276039496844,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.63,
     "source_value_text": "0.63",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "DFWQcrbMegFAcEWZKWoJxC",
     "source_model_name": "gpt-5.5_xhigh",
     "p": 0.6106902356902357,
     "p_star": 0.6095942927626096,
     "y": 0.44560716868223443,
     "v": 0.044717221912141905,
     "family_factor": 1.0,
     "w": 4.886127385832719
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.56,
     "source_value_text": "0.56",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-24",
     "source_row_id": "EatRQnSaUpUwKzdtjYnQHo",
     "source_model_name": "gpt-5.5_xhigh",
     "p": 0.515311742674598,
     "p_star": 0.5151601412619783,
     "y": 0.06065915799000418,
     "v": 0.04698568187340877,
     "family_factor": 1.0,
     "w": 4.810718786851241
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.725,
     "source_value_text": "0.725",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "PKSMspJiJdNThB6qNvaBSM",
     "source_model_name": "gpt-5.5_xhigh",
     "p": 0.725,
     "p_star": 0.7196428571428571,
     "y": 0.942690756598375,
     "v": 0.11520110143492102,
     "family_factor": 1.0,
     "w": 2.323408182700241
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8526315789473684,
     "source_value_text": "0.8526315789473684",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "5FGXKvXQwGPtcCX2PNrLR5",
     "source_model_name": "gpt-5.5_xhigh",
     "p": 0.8526315789473684,
     "p_star": 0.8513986013986014,
     "y": 1.745612866592273,
     "v": 0.027539557917622894,
     "family_factor": 1.0,
     "w": 3.920352306089592
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-24",
     "source_row_id": "dP6L7ViZSdcTiWxooLCTUh",
     "source_model_name": "gpt-5.5-pre-release_xhigh",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.8057851239669421,
     "source_value_text": "0.8057851239669421",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-24",
     "source_row_id": "LbhPRqUkXrs5KJ7vyT4CR7",
     "source_model_name": "gpt-5.5-pre-release_xhigh",
     "p": 0.8057851239669421,
     "p_star": 0.8051533365207295,
     "y": 1.4188198313260538,
     "v": 0.013142707336681317,
     "family_factor": 1.0,
     "w": 6.2496894217176
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9400252525252525,
     "source_value_text": "0.9400252525252525",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-24",
     "source_row_id": "FUv4EUwR78nAsdGbiwiLEr",
     "source_model_name": "gpt-5.5-pre-release_xhigh",
     "p": 0.92003367003367,
     "p_star": 0.9179229480737018,
     "y": 2.414454988837388,
     "v": 0.0904630246792093,
     "family_factor": 0.5,
     "w": 1.5156492189548028
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9360266666666668,
     "source_value_text": "0.936027",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.5-20260423",
     "source_model_name": "openai/gpt-5.5-20260423",
     "p": 0.9147022222222224,
     "p_star": 0.9126182914572866,
     "y": 2.346031735178424,
     "v": 0.08559755271601369,
     "family_factor": 0.5,
     "w": 1.2015767322358073
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.63,
     "source_value_text": "0.63",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "TijCafTTJUFrJ6jPGvBbgq",
     "source_model_name": "gpt-5.5_xhigh",
     "p": 0.63,
     "p_star": 0.6298701298701299,
     "y": 0.5316597106688329,
     "v": 0.0042808173364540505,
     "family_factor": 1.0,
     "w": 1.6900036794251425
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.75,
     "source_value_text": "0.75",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.5-20260423",
     "source_model_name": "openai/gpt-5.5-20260423",
     "p": 0.75,
     "p_star": 0.7450980392156863,
     "y": 1.0726368022648491,
     "v": 0.10121457489878542,
     "family_factor": 1.0,
     "w": 3.5141926549914935
    }
   ]
  },
  {
   "slug": "claude-fable-5",
   "name": "Claude Fable 5",
   "tier": "main",
   "rank": 10,
   "theta": 2.5151572873324897,
   "se": 0.1340140884794921,
   "si_iq": 137.72735930998735,
   "si_iq_low": 134.42085516760966,
   "si_iq_high": 141.03386345236504,
   "si_iq_display": 138,
   "domains": {
    "reasoning": {
     "si_iq": 135.28629261684364,
     "n": 2
    },
    "math": {
     "si_iq": 141.20418641702017,
     "n": 3
    },
    "knowledge": {
     "si_iq": 129.8979076735358,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.47,
     "source_value_text": "0.47",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "bxS76CJuVws8iwWU2Wr2PM",
     "source_model_name": "claude-fable-5_max",
     "p": 0.4423400673400673,
     "p_star": 0.4429109577624429,
     "y": -0.22935633597819632,
     "v": 0.04441117696268944,
     "family_factor": 1.0,
     "w": 4.896482364167961
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.52,
     "source_value_text": "0.52",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-31",
     "source_row_id": "X29V6KG3aVe5Nv5r3tsLHX",
     "source_model_name": "claude-fable-5_max",
     "p": 0.4712491738268342,
     "p_star": 0.4715338354721131,
     "y": -0.11398792071445124,
     "v": 0.04781270105527065,
     "family_factor": 1.0,
     "w": 4.783802583528621
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.902,
     "source_value_text": "0.902",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-09",
     "source_row_id": "ReDAtJGGfRtrEGGWf4Zbsd",
     "source_model_name": "claude-fable-5_max",
     "p": 0.902,
     "p_star": 0.8924285714285715,
     "y": 2.1157913996936766,
     "v": 0.24211119640511408,
     "family_factor": 1.0,
     "w": 1.4615131140224957
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8701754385964913,
     "source_value_text": "0.8701754385964913",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-09",
     "source_row_id": "E28uZiJvrPgKtawbJpoZQ8",
     "source_model_name": "claude-fable-5_max",
     "p": 0.8701754385964913,
     "p_star": 0.8688811188811189,
     "y": 1.8911019125603181,
     "v": 0.03058350100603621,
     "family_factor": 1.0,
     "w": 3.8289676425269645
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "hwrnvtEbDAocFtjcsHqsQh",
     "source_model_name": "claude-fable-5_high",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8585858585858586,
     "source_value_text": "0.8585858585858586",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "S5pm7ctk9zgPfbyHrbD9AV",
     "source_model_name": "claude-fable-5_max",
     "p": 0.8114478114478114,
     "p_star": 0.8098827470686767,
     "y": 1.4492484779718915,
     "v": 0.045837564812730984,
     "family_factor": 0.5,
     "w": 1.979429202383478
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8615317499999998,
     "source_value_text": "0.861532",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-5-fable-20260609",
     "source_model_name": "anthropic/claude-5-fable-20260609",
     "p": 0.8153756666666664,
     "p_star": 0.8137908643216077,
     "y": 1.4748329821211246,
     "v": 0.04650962885695339,
     "family_factor": 0.5,
     "w": 1.4350593790990331
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.707,
     "source_value_text": "0.707",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "SEnvgtunRa5GwAtU2sHa87",
     "source_model_name": "claude-fable-5_xhigh",
     "p": 0.707,
     "p_star": 0.7067932067932068,
     "y": 0.8798599902492414,
     "v": 0.004815766820570548,
     "family_factor": 1.0,
     "w": 1.687361458208778
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7957576363636364,
     "source_value_text": "0.795758",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-5-fable-20260609",
     "source_model_name": "anthropic/claude-5-fable-20260609",
     "p": 0.7957576363636364,
     "p_star": 0.7899584670231729,
     "y": 1.324675083448162,
     "v": 0.1158564493305607,
     "family_factor": 1.0,
     "w": 3.275819570735597
    }
   ]
  },
  {
   "slug": "claude-opus-5",
   "name": "Claude Opus 5",
   "tier": "main",
   "rank": 11,
   "theta": 2.4293753897132953,
   "se": 0.1241269101201041,
   "si_iq": 136.44063084569945,
   "si_iq_low": 133.37807117641904,
   "si_iq_high": 139.50319051497985,
   "si_iq_display": 136,
   "domains": {
    "reasoning": {
     "si_iq": 136.15004192007626,
     "n": 2
    },
    "math": {
     "si_iq": 137.04175585078818,
     "n": 3
    },
    "knowledge": {
     "si_iq": 134.94126234823077,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.43,
     "source_value_text": "0.43",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "RLN98bmQSMnc5Zv39BF4M2",
     "source_model_name": "claude-opus-5_max",
     "p": 0.40025252525252525,
     "p_star": 0.4012401240124012,
     "y": -0.40030058184352585,
     "v": 0.04611103107832251,
     "family_factor": 1.0,
     "w": 4.839516742630503
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.59,
     "source_value_text": "0.59",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-25",
     "source_row_id": "FfAvNS5H9bMDSBF4JNNiDz",
     "source_model_name": "claude-opus-5_max",
     "p": 0.5483586693104208,
     "p_star": 0.547879870604377,
     "y": 0.192108131171466,
     "v": 0.04691097834555796,
     "family_factor": 1.0,
     "w": 4.8131650142804165
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.7317073170731707,
     "source_value_text": "0.7317073170731707",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-24",
     "source_row_id": "ji3kMn49Jcr9t4whxcpjj4",
     "source_model_name": "claude-opus-5_max",
     "p": 0.7317073170731707,
     "p_star": 0.7261904761904762,
     "y": 0.9753796482441615,
     "v": 0.11689237348538846,
     "family_factor": 1.0,
     "w": 2.3052908314163654
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.856140350877193,
     "source_value_text": "0.856140350877193",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-24",
     "source_row_id": "ff7GeS7rdperjxSBZ7MHZY",
     "source_model_name": "claude-opus-5_max",
     "p": 0.856140350877193,
     "p_star": 0.8548951048951049,
     "y": 1.773521881678274,
     "v": 0.028087811368172073,
     "family_factor": 1.0,
     "w": 3.9035720468578683
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9888888888888889,
     "source_value_text": "0.9888888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-24",
     "source_row_id": "KxvHAT9SV2dTDn7jBnTk6f",
     "source_model_name": "claude-opus-5_max",
     "p": 0.9888777666555445,
     "p_star": 0.9782499891195543,
     "y": 3.8061509921832197,
     "v": 1.0005336230075845,
     "family_factor": 1.0,
     "w": 0.45432505608831736
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9387626262626263,
     "source_value_text": "0.9387626262626263",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-24",
     "source_row_id": "D3mtasTumfvjR4fjmnHWRy",
     "source_model_name": "claude-opus-5_max",
     "p": 0.9183501683501684,
     "p_star": 0.916247906197655,
     "y": 2.392425796993835,
     "v": 0.08885909180539356,
     "family_factor": 0.5,
     "w": 1.5285212474296603
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8957629166666667,
     "source_value_text": "0.895763",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-opus-5-20260723",
     "source_model_name": "anthropic/claude-opus-5-20260723",
     "p": 0.8610172222222223,
     "p_star": 0.8592030653266333,
     "y": 1.8086866186990693,
     "v": 0.05736484779485615,
     "family_factor": 0.5,
     "w": 1.3615837294498663
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.599,
     "source_value_text": "0.599",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "Zftz2yk4X5NF28JQzjN3hZ",
     "source_model_name": "claude-opus-5_max",
     "p": 0.599,
     "p_star": 0.5989010989010989,
     "y": 0.40088844108075256,
     "v": 0.0041545621766582155,
     "family_factor": 1.0,
     "w": 1.6906284860067702
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7727272727272727,
     "source_value_text": "0.772727",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-opus-5-20260723",
     "source_model_name": "anthropic/claude-opus-5-20260723",
     "p": 0.7727272727272727,
     "p_star": 0.767379679144385,
     "y": 1.1935740971050373,
     "v": 0.10768909002718927,
     "family_factor": 1.0,
     "w": 3.4046409519824934
    }
   ]
  },
  {
   "slug": "gpt-5-6-terra",
   "name": "GPT-5.6 Terra",
   "tier": "main",
   "rank": 12,
   "theta": 2.2519195775229806,
   "se": 0.12479742724876378,
   "si_iq": 133.7787936628447,
   "si_iq_low": 130.69969045184715,
   "si_iq_high": 136.85789687384226,
   "si_iq_display": 134,
   "domains": {
    "reasoning": {
     "si_iq": 130.00567156543056,
     "n": 2
    },
    "math": {
     "si_iq": 136.77115936802932,
     "n": 3
    },
    "knowledge": {
     "si_iq": 130.03414531930162,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.47,
     "source_value_text": "0.47",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "J2ZgtxyaQZfyDMPTPxS8nm",
     "source_model_name": "gpt-5.6-terra_max",
     "p": 0.4423400673400673,
     "p_star": 0.4429109577624429,
     "y": -0.22935633597819632,
     "v": 0.04441117696268944,
     "family_factor": 1.0,
     "w": 4.896482364167961
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.35,
     "source_value_text": "0.35",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-28",
     "source_row_id": "MFTd4BUbtzbfcCky6d79d4",
     "source_model_name": "gpt-5.6-terra_max",
     "p": 0.28398325622383785,
     "p_star": 0.28612203586518603,
     "y": -0.9142936105135304,
     "v": 0.06502959796176043,
     "family_factor": 1.0,
     "w": 4.284727042420558
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.7073170731707317,
     "source_value_text": "0.7073170731707317",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "ZUygpkXqg3NjchXXfedAWV",
     "source_model_name": "gpt-5.6-terra_max",
     "p": 0.7073170731707317,
     "p_star": 0.7023809523809523,
     "y": 0.8586616190375185,
     "v": 0.11118644067796606,
     "family_factor": 1.0,
     "w": 2.367576243980739
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8596491228070176,
     "source_value_text": "0.8596491228070176",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "J6evjTMgHkrun8txnEvzdN",
     "source_model_name": "gpt-5.6-terra_max",
     "p": 0.8596491228070176,
     "p_star": 0.8583916083916084,
     "y": 1.8019949731220821,
     "v": 0.0286641019838576,
     "family_factor": 1.0,
     "w": 3.886087823181098
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9972222222222222,
     "source_value_text": "0.9972222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "jUmmCNezoW7jWiK72SVCaP",
     "source_model_name": "gpt-5.6-terra_max",
     "p": 0.9972194416638861,
     "p_star": 0.9864103233668452,
     "y": 4.284761984085626,
     "v": 1.5880735549487481,
     "family_factor": 1.0,
     "w": 0.2961956240201752
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9330808080808081,
     "source_value_text": "0.9330808080808081",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "4bLcFNu5zF6YuZf3qVKoHE",
     "source_model_name": "gpt-5.6-terra_max",
     "p": 0.9107744107744108,
     "p_star": 0.9087102177554439,
     "y": 2.2979873837454163,
     "v": 0.08238020488627729,
     "family_factor": 0.5,
     "w": 1.5828205411591436
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.89267675,
     "source_value_text": "0.892677",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.6-terra-20260709",
     "source_model_name": "openai/gpt-5.6-terra-20260709",
     "p": 0.8569023333333333,
     "p_star": 0.8551088542713567,
     "y": 1.775246034393094,
     "v": 0.05608573867991792,
     "family_factor": 0.5,
     "w": 1.3698481995556826
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.432,
     "source_value_text": "0.432",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "DienatPbgfgn3EzM7Gvzxr",
     "source_model_name": "gpt-5.6-terra_max",
     "p": 0.432,
     "p_star": 0.4320679320679321,
     "y": -0.2734189868186565,
     "v": 0.004067086593357432,
     "family_factor": 1.0,
     "w": 1.6910616527422917
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.715,
     "source_value_text": "0.715",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.6-terra-20260709",
     "source_model_name": "openai/gpt-5.6-terra-20260709",
     "p": 0.715,
     "p_star": 0.7107843137254902,
     "y": 0.8991962985148552,
     "v": 0.0935125657510228,
     "family_factor": 1.0,
     "w": 3.6540613186656072
    }
   ]
  },
  {
   "slug": "claude-opus-4-8",
   "name": "Claude Opus 4.8",
   "tier": "main",
   "rank": 13,
   "theta": 2.135064403847525,
   "se": 0.12070626282880755,
   "si_iq": 132.02596605771288,
   "si_iq_low": 129.04780336912765,
   "si_iq_high": 135.0041287462981,
   "si_iq_display": 132,
   "domains": {
    "reasoning": {
     "si_iq": 131.5175907293962,
     "n": 2
    },
    "math": {
     "si_iq": 132.65308319879375,
     "n": 3
    },
    "knowledge": {
     "si_iq": 129.72627185908712,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.52,
     "source_value_text": "0.52",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "PEZpuEuU65bu3ZtvjLytHq",
     "source_model_name": "claude-opus-4-8_max",
     "p": 0.494949494949495,
     "p_star": 0.494999499949995,
     "y": -0.020002667106749764,
     "v": 0.043350342177989235,
     "family_factor": 1.0,
     "w": 4.932717776903362
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.36,
     "source_value_text": "0.36",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-25",
     "source_row_id": "Q3WpHdurYNvawj6ycXyj6e",
     "source_model_name": "claude-opus-4-8_max",
     "p": 0.2949988984357788,
     "p_star": 0.2970286123126523,
     "y": -0.861487718764338,
     "v": 0.06300173610271916,
     "family_factor": 1.0,
     "w": 4.33803220807997
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.5609756097560976,
     "source_value_text": "0.5609756097560976",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "JiqgqBTfkGx797uowZgJbk",
     "source_model_name": "claude-opus-4-8_max",
     "p": 0.5609756097560976,
     "p_star": 0.5595238095238096,
     "y": 0.23922968906583458,
     "v": 0.09430707303047728,
     "family_factor": 1.0,
     "w": 2.573246522639834
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8,
     "source_value_text": "0.8",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "GVmgtgKMwEqc54f3jA7auP",
     "source_model_name": "claude-opus-4-8_max",
     "p": 0.8,
     "p_star": 0.798951048951049,
     "y": 1.3797512625309547,
     "v": 0.021691561221577397,
     "family_factor": 1.0,
     "w": 4.108748338675631
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9833333333333333,
     "source_value_text": "0.9833333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-07",
     "source_row_id": "37pJqPpXTE6ia9ikmmGPJ4",
     "source_model_name": "claude-opus-4-8_max",
     "p": 0.9833166499833166,
     "p_star": 0.9728097662880271,
     "y": 3.57733069640059,
     "v": 0.8048271865249628,
     "family_factor": 1.0,
     "w": 0.5525917075063547
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9103535353535354,
     "source_value_text": "0.9103535353535354",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-07",
     "source_row_id": "dqgqP2uEPswfECCVj2Kbr9",
     "source_model_name": "claude-opus-4-8_max",
     "p": 0.8804713804713805,
     "p_star": 0.8785594639865997,
     "y": 1.978858865975723,
     "v": 0.06464236595380321,
     "family_factor": 0.5,
     "w": 1.7533466123525696
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8959834999999999,
     "source_value_text": "0.895983",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.8-opus-20260528",
     "source_model_name": "anthropic/claude-4.8-opus-20260528",
     "p": 0.8613113333333332,
     "p_star": 0.8594956984924622,
     "y": 1.8111077161305802,
     "v": 0.05745928305916009,
     "family_factor": 0.5,
     "w": 1.360977523591342
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.53,
     "source_value_text": "0.53",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "ViC6pxQZUVS3E9M9iEubF7",
     "source_model_name": "claude-opus-4-8_max",
     "p": 0.53,
     "p_star": 0.52997002997003,
     "y": 0.12002399902860343,
     "v": 0.004006406243583489,
     "family_factor": 1.0,
     "w": 1.691362263681843
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7776190714285715,
     "source_value_text": "0.777619",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.8-opus-20260528",
     "source_model_name": "anthropic/claude-4.8-opus-20260528",
     "p": 0.7776190714285715,
     "p_star": 0.7721755602240896,
     "y": 1.2206366024192565,
     "v": 0.1092731063921323,
     "family_factor": 1.0,
     "w": 3.378870765465597
    }
   ]
  },
  {
   "slug": "gemini-3-7-flash",
   "name": "Gemini 3.7 Flash",
   "tier": "main",
   "rank": 14,
   "theta": 2.0712709330145054,
   "se": 0.12082370239446853,
   "si_iq": 131.0690639952176,
   "si_iq_low": 128.0880037425423,
   "si_iq_high": 134.05012424789285,
   "si_iq_display": 131,
   "domains": {
    "reasoning": {
     "si_iq": 135.49155067231732,
     "n": 2
    },
    "math": {
     "si_iq": 128.0084636671472,
     "n": 3
    },
    "knowledge": {
     "si_iq": 138.8042255835009,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.66,
     "source_value_text": "0.66",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "Xu34dKTAdpBWL6advf6DMg",
     "source_model_name": "gemini-3.7-flash_high",
     "p": 0.6422558922558923,
     "p_star": 0.6408474180751409,
     "y": 0.5790440737785506,
     "v": 0.04606008741460433,
     "family_factor": 1.0,
     "w": 4.841204696662703
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.37,
     "source_value_text": "0.37",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "ZavSMMq9jk5s9WSbARZr6X",
     "source_model_name": "gemini-3.7-flash_high",
     "p": 0.30601454064771977,
     "p_star": 0.3079351887601186,
     "y": -0.8097902743657617,
     "v": 0.06117093589888807,
     "family_factor": 1.0,
     "w": 4.387309518573229
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.36585365853658536,
     "source_value_text": "0.36585365853658536",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "KptKXK5nE2Ns2WbiaSSnbc",
     "source_model_name": "gemini-3.7-flash_high",
     "p": 0.36585365853658536,
     "p_star": 0.36904761904761907,
     "y": -0.5363047090669755,
     "v": 0.09981740718198419,
     "family_factor": 1.0,
     "w": 2.502284495887907
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.7157894736842105,
     "source_value_text": "0.7157894736842105",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "axMdgNDC8UYYLnZYLHZpF5",
     "source_model_name": "gemini-3.7-flash_high",
     "p": 0.7157894736842105,
     "p_star": 0.715034965034965,
     "y": 0.9199649552360393,
     "v": 0.017099914500427492,
     "family_factor": 1.0,
     "w": 4.269857942536539
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9722222222222222,
     "source_value_text": "0.9722222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "kQjrYCaa7yYyMXofeR23Dd",
     "source_model_name": "gemini-3.7-flash_high",
     "p": 0.9721944166388611,
     "p_star": 0.9619293206249727,
     "y": 3.2294965610305137,
     "v": 0.58131932486383,
     "family_factor": 1.0,
     "w": 0.7338702745587484
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9482323232323232,
     "source_value_text": "0.9482323232323232",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "XyVL3VffJ6UboY97vxpohL",
     "source_model_name": "gemini-3.7-flash_high",
     "p": 0.9309764309764309,
     "p_star": 0.9288107202680066,
     "y": 2.568562730860049,
     "v": 0.10275404454481638,
     "family_factor": 0.5,
     "w": 1.423770042382581
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9391951653543308,
     "source_value_text": "0.9391951653543308",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-15",
     "source_row_id": "google/gemini-3.7-flash-20260813",
     "source_model_name": "google/gemini-3.7-flash-20260813",
     "p": 0.9189268871391078,
     "p_star": 0.9168217269022277,
     "y": 2.3999268712355217,
     "v": 0.08940117518111365,
     "family_factor": 0.5,
     "w": 1.1828496939420536
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.692,
     "source_value_text": "0.692",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "84ARuGyhQsjgh8umRmBvas",
     "source_model_name": "gemini-3.7-flash_high",
     "p": 0.692,
     "p_star": 0.6918081918081919,
     "y": 0.8085863947160514,
     "v": 0.0046808535536455075,
     "family_factor": 1.0,
     "w": 1.6880270421130226
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7831052054794521,
     "source_value_text": "0.7831052054794521",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-15",
     "source_row_id": "google/gemini-3.7-flash-20260813",
     "source_model_name": "google/gemini-3.7-flash-20260813",
     "p": 0.7831052054794521,
     "p_star": 0.7775541230190706,
     "y": 1.2514694307382868,
     "v": 0.1111410928840043,
     "family_factor": 1.0,
     "w": 3.348977555851785
    }
   ]
  },
  {
   "slug": "gpt-5-4",
   "name": "GPT-5.4",
   "tier": "main",
   "rank": 15,
   "theta": 2.0372157928982593,
   "se": 0.11871408172907445,
   "si_iq": 130.5582368934739,
   "si_iq_low": 127.62922691064796,
   "si_iq_high": 133.48724687629982,
   "si_iq_display": 131,
   "domains": {
    "reasoning": {
     "si_iq": 130.62800765394448,
     "n": 2
    },
    "math": {
     "si_iq": 131.19175242810664,
     "n": 3
    },
    "knowledge": {
     "si_iq": 129.73515501852097,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.48,
     "source_value_text": "0.48",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "92ZBraB6bB98s8raSiPgUw",
     "source_model_name": "gpt-5.4-2026-03-05_xhigh",
     "p": 0.45286195286195285,
     "p_star": 0.4533286661999533,
     "y": -0.1872303746909695,
     "v": 0.04411035357981414,
     "family_factor": 1.0,
     "w": 4.906703533933967
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.37,
     "source_value_text": "0.37",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-24",
     "source_row_id": "T6DyawEuhVmDAaDTzDRNNx",
     "source_model_name": "gpt-5.4-2026-03-05_xhigh",
     "p": 0.30601454064771977,
     "p_star": 0.3079351887601186,
     "y": -0.8097902743657617,
     "v": 0.06117093589888807,
     "family_factor": 1.0,
     "w": 4.387309518573229
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.49,
     "source_value_text": "0.49",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "doiQDghqnLzbE8CFijLNQJ",
     "source_model_name": "gpt-5.4-2026-03-05_xhigh",
     "p": 0.49,
     "p_star": 0.49023809523809525,
     "y": -0.03905258156189325,
     "v": 0.09300597347877955,
     "family_factor": 1.0,
     "w": 2.590593394535395
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.7859649122807018,
     "source_value_text": "0.7859649122807018",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "PaYEQ37A2n6giYBwZGBnXY",
     "source_model_name": "gpt-5.4-2026-03-05_xhigh",
     "p": 0.7859649122807018,
     "p_star": 0.784965034965035,
     "y": 1.294838532369837,
     "v": 0.020642077244825904,
     "family_factor": 1.0,
     "w": 4.144490972128416
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9777777777777777,
     "source_value_text": "0.9777777777777777",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-15",
     "source_row_id": "DpPahiEawokzgidE3cNZbS",
     "source_model_name": "gpt-5.4-2026-03-05_high",
     "p": 0.9777555333110889,
     "p_star": 0.9673695434565,
     "y": 3.3893344749741634,
     "v": 0.6744200157422331,
     "family_factor": 1.0,
     "w": 0.6456444691977407
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.768595041322314,
     "source_value_text": "0.768595041322314",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-03-06",
     "source_row_id": "i9HTMbAxcwsrTf2w2FuJ6N",
     "source_model_name": "gpt-5.4-2026-03-05_high",
     "p": 0.768595041322314,
     "p_star": 0.7680400928898299,
     "y": 1.1972773935167909,
     "v": 0.011573363394192042,
     "family_factor": 1.0,
     "w": 6.3375949211848885
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.933,
     "source_value_text": "0.933",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-03-06",
     "source_row_id": "fFatyce8UvpN7ZivdmrhAy",
     "source_model_name": "gpt-5.4-2026-03-05_xhigh",
     "p": 0.9106666666666667,
     "p_star": 0.908603015075377,
     "y": 2.296695781474227,
     "v": 0.08229589241165733,
     "family_factor": 0.5,
     "w": 1.5835526010807301
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.899551,
     "source_value_text": "0.899551",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "openai/gpt-5.4-20260305",
     "source_model_name": "openai/gpt-5.4-20260305",
     "p": 0.866068,
     "p_star": 0.8642284623115577,
     "y": 1.850863554587456,
     "v": 0.059046084435913956,
     "family_factor": 0.5,
     "w": 1.3508715490558547
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.451,
     "source_value_text": "0.451",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "AzCkm282PLhDdLJ8DnAQQc",
     "source_model_name": "gpt-5.4-2026-03-05_xhigh",
     "p": 0.451,
     "p_star": 0.45104895104895104,
     "y": -0.19643340098663603,
     "v": 0.004030644993888534,
     "family_factor": 1.0,
     "w": 1.6912421719000805
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.73166675,
     "source_value_text": "0.731667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.4-20260305",
     "source_model_name": "openai/gpt-5.4-20260305",
     "p": 0.73166675,
     "p_star": 0.7271242647058823,
     "y": 0.9800808815102715,
     "v": 0.09688490004306469,
     "family_factor": 1.0,
     "w": 3.5914728911759193
    }
   ]
  },
  {
   "slug": "gpt-5-6-luna",
   "name": "GPT-5.6 Luna",
   "tier": "main",
   "rank": 16,
   "theta": 2.0265517900545564,
   "se": 0.12378230991098986,
   "si_iq": 130.39827685081835,
   "si_iq_low": 127.34421943702338,
   "si_iq_high": 133.4523342646133,
   "si_iq_display": 130,
   "domains": {
    "reasoning": {
     "si_iq": 124.28704545343025,
     "n": 2
    },
    "math": {
     "si_iq": 133.79104124376119,
     "n": 3
    },
    "knowledge": {
     "si_iq": 126.27266183238855,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.43,
     "source_value_text": "0.43",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "LUfGWqWQim7rdBPgSpbrXS",
     "source_model_name": "gpt-5.6-luna_max",
     "p": 0.40025252525252525,
     "p_star": 0.4012401240124012,
     "y": -0.40030058184352585,
     "v": 0.04611103107832251,
     "family_factor": 1.0,
     "w": 4.839516742630503
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.21,
     "source_value_text": "0.21",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-28",
     "source_row_id": "Epg7eNLwwGPXtX3sSAwPf8",
     "source_model_name": "gpt-5.6-luna_max",
     "p": 0.12976426525666446,
     "p_star": 0.13342996560065787,
     "y": -1.8709661924088827,
     "v": 0.1493151779008844,
     "family_factor": 1.0,
     "w": 2.8361962843179116
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.6097560975609756,
     "source_value_text": "0.6097560975609756",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "NLiiJJSyA9wmg2FHENFpAq",
     "source_model_name": "gpt-5.6-luna_max",
     "p": 0.6097560975609756,
     "p_star": 0.6071428571428571,
     "y": 0.4353180712578454,
     "v": 0.09744503862150918,
     "family_factor": 1.0,
     "w": 2.5323502858862477
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8210526315789474,
     "source_value_text": "0.8210526315789474",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "YLAk5J3Wd8EruVXee8bAQb",
     "source_model_name": "gpt-5.6-luna_max",
     "p": 0.8210526315789474,
     "p_star": 0.8199300699300699,
     "y": 1.5158737802166435,
     "v": 0.023599064317800726,
     "family_factor": 1.0,
     "w": 4.045338067563267
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9833333333333333,
     "source_value_text": "0.9833333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "AhtQ5ggs4pTfLDqHFjueGy",
     "source_model_name": "gpt-5.6-luna_max",
     "p": 0.9833166499833166,
     "p_star": 0.9728097662880271,
     "y": 3.57733069640059,
     "v": 0.8048271865249628,
     "family_factor": 1.0,
     "w": 0.5525917075063547
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9160353535353535,
     "source_value_text": "0.9160353535353535",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "LWkDtkmd3TNmLzMhfZD5HW",
     "source_model_name": "gpt-5.6-luna_max",
     "p": 0.888047138047138,
     "p_star": 0.8860971524288106,
     "y": 2.0514807266821915,
     "v": 0.06817400721460098,
     "family_factor": 0.5,
     "w": 1.7165264678889685
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8724745,
     "source_value_text": "0.872475",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.6-luna-20260709",
     "source_model_name": "openai/gpt-5.6-luna-20260709",
     "p": 0.8299660000000001,
     "p_star": 0.8283078793969851,
     "y": 1.5736820439309736,
     "v": 0.049305696594927576,
     "family_factor": 0.5,
     "w": 1.4153858160227668
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.41,
     "source_value_text": "0.41",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "CeDghdBk8CqtiFSbUzxNH5",
     "source_model_name": "gpt-5.6-luna_max",
     "p": 0.41,
     "p_star": 0.4100899100899101,
     "y": -0.3635937067449343,
     "v": 0.004125408286501354,
     "family_factor": 1.0,
     "w": 1.69077282729679
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.72333325,
     "source_value_text": "0.723333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.6-luna-20260709",
     "source_model_name": "openai/gpt-5.6-luna-20260709",
     "p": 0.72333325,
     "p_star": 0.7189541666666667,
     "y": 0.9392798457648515,
     "v": 0.09513740387366576,
     "family_factor": 1.0,
     "w": 3.623635280319383
    }
   ]
  },
  {
   "slug": "gpt-6-luna",
   "name": "GPT-6 Luna",
   "tier": "main",
   "rank": 17,
   "theta": 2.0137115792558795,
   "se": 0.1281940559264183,
   "si_iq": 130.2056736888382,
   "si_iq_low": 127.0427661038363,
   "si_iq_high": 133.36858127384008,
   "si_iq_display": 130,
   "domains": {
    "reasoning": {
     "si_iq": 125.60544071121473,
     "n": 2
    },
    "math": {
     "si_iq": 132.43253378644852,
     "n": 3
    },
    "knowledge": {
     "si_iq": 125.83439180238219,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.36,
     "source_value_text": "0.36",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "Jevnk9hi9oRBbGcFu2JxBC",
     "source_model_name": "gpt-6-luna_max",
     "p": 0.3265993265993266,
     "p_star": 0.32831616494982835,
     "y": -0.7158106846108149,
     "v": 0.051519052676884676,
     "family_factor": 1.0,
     "w": 4.6667845970134
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.07,
     "source_value_text": "0.07",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "bAERV8wdmoHMLz2K4bZCSK",
     "source_model_name": "gpt-6-luna_max",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.5609756097560976,
     "source_value_text": "0.5609756097560976",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "7n3HBUK684GmdT6Tkycu6m",
     "source_model_name": "gpt-6-luna_max",
     "p": 0.5609756097560976,
     "p_star": 0.5595238095238096,
     "y": 0.23922968906583458,
     "v": 0.09430707303047728,
     "family_factor": 1.0,
     "w": 2.573246522639834
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.7894736842105263,
     "source_value_text": "0.7894736842105263",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "iBQxysYR7zPxB6hxvJyTLc",
     "source_model_name": "gpt-6-luna_max",
     "p": 0.7894736842105263,
     "p_star": 0.7884615384615384,
     "y": 1.315676793905937,
     "v": 0.02089021641531216,
     "family_factor": 1.0,
     "w": 4.135983992966606
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9888888888888889,
     "source_value_text": "0.9888888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "4uDz9b6SosxDSZf7swMD9D",
     "source_model_name": "gpt-6-luna_max",
     "p": 0.9888777666555445,
     "p_star": 0.9782499891195543,
     "y": 3.8061509921832197,
     "v": 1.0005336230075845,
     "family_factor": 1.0,
     "w": 0.45432505608831736
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9046717171717171,
     "source_value_text": "0.9046717171717171",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "7F3QFMAkwnCV62HcvxP96q",
     "source_model_name": "gpt-6-luna_max",
     "p": 0.8728956228956228,
     "p_star": 0.8710217755443885,
     "y": 1.9100233897217884,
     "v": 0.06153740490278947,
     "family_factor": 0.5,
     "w": 1.7870482367135514
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8815936666666665,
     "source_value_text": "0.881594",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-6-luna-20260922",
     "source_model_name": "openai/gpt-6-luna-20260922",
     "p": 0.8421248888888887,
     "p_star": 0.8404056683417084,
     "y": 1.6612495453026144,
     "v": 0.05206371632513499,
     "family_factor": 0.5,
     "w": 1.3965013722467492
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.414,
     "source_value_text": "0.414",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "HX9sRVWJtZiNvneALnVzs8",
     "source_model_name": "gpt-6-luna_max",
     "p": 0.414,
     "p_star": 0.4140859140859141,
     "y": -0.34709969351818043,
     "v": 0.004113461611633692,
     "family_factor": 1.0,
     "w": 1.690831982559224
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.68,
     "source_value_text": "0.68",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-6-luna-20260922",
     "source_model_name": "openai/gpt-6-luna-20260922",
     "p": 0.68,
     "p_star": 0.6764705882352942,
     "y": 0.7375989431307793,
     "v": 0.08783487044356611,
     "family_factor": 1.0,
     "w": 3.7645128378811514
    }
   ]
  },
  {
   "slug": "gemini-3-8-flash",
   "name": "Gemini 3.8 Flash",
   "tier": "main",
   "rank": 18,
   "theta": 1.9931756466523205,
   "se": 0.12455759519155232,
   "si_iq": 129.89763469978482,
   "si_iq_low": 126.82444881956673,
   "si_iq_high": 132.9708205800029,
   "si_iq_display": 130,
   "domains": {
    "reasoning": {
     "si_iq": 136.09453667296276,
     "n": 2
    },
    "math": {
     "si_iq": 125.37260304903685,
     "n": 3
    },
    "knowledge": {
     "si_iq": 139.79256606208116,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.58,
     "source_value_text": "0.58",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "Hpyy6CpmXmd5q7Zbdq63CR",
     "source_model_name": "gemini-3.8-flash_high",
     "p": 0.5580808080808081,
     "p_star": 0.5575057505750575,
     "y": 0.23104534950022124,
     "v": 0.04345733154339696,
     "family_factor": 1.0,
     "w": 4.929038994236709
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.47,
     "source_value_text": "0.47",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "5yyuCCi2Dpfh6xLBMxqFyB",
     "source_model_name": "gemini-3.8-flash_high",
     "p": 0.41617096276712934,
     "p_star": 0.41700095323478154,
     "y": -0.3350970435671557,
     "v": 0.05014396360145319,
     "family_factor": 1.0,
     "w": 4.7095252065112225
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.21951219512195122,
     "source_value_text": "0.21951219512195122",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "Lgy52ZT4YpFrUqqKVu2qUs",
     "source_model_name": "gemini-3.8-flash_high",
     "p": 0.21951219512195122,
     "p_star": 0.2261904761904762,
     "y": -1.2299482907291965,
     "v": 0.13279352226720645,
     "family_factor": 1.0,
     "w": 2.1478260869565218
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6842105263157895,
     "source_value_text": "0.6842105263157895",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "Utgs6DuaQDDdi98ZWH22qL",
     "source_model_name": "gemini-3.8-flash_high",
     "p": 0.6842105263157895,
     "p_star": 0.6835664335664335,
     "y": 0.77021052871954,
     "v": 0.01610829294485029,
     "family_factor": 1.0,
     "w": 4.306324615740346
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9888888888888889,
     "source_value_text": "0.9888888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "NeYuqgQyWtFWAHEjQYPm5Z",
     "source_model_name": "gemini-3.8-flash_high",
     "p": 0.9888777666555445,
     "p_star": 0.9782499891195543,
     "y": 3.8061509921832197,
     "v": 1.0005336230075845,
     "family_factor": 1.0,
     "w": 0.45432505608831736
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9539141414141414,
     "source_value_text": "0.9539141414141414",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "Br3mjs2GrYcCwX9AMwcihU",
     "source_model_name": "gemini-3.8-flash_high",
     "p": 0.9385521885521886,
     "p_star": 0.9363484087102178,
     "y": 2.688563313428715,
     "v": 0.11375478997544118,
     "family_factor": 0.5,
     "w": 1.3504966818660744
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9482614885496183,
     "source_value_text": "0.9482614885496183",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-15",
     "source_row_id": "google/gemini-3.8-flash-20260902",
     "source_model_name": "google/gemini-3.8-flash-20260902",
     "p": 0.9310153180661578,
     "p_star": 0.9288494119452223,
     "y": 2.5691480392352863,
     "v": 0.10280450858779916,
     "family_factor": 0.5,
     "w": 1.1212692362552754
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.697,
     "source_value_text": "0.697",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "gZ4bwozTKtpmZTqnqX3a33",
     "source_model_name": "gemini-3.8-flash_high",
     "p": 0.697,
     "p_star": 0.6968031968031968,
     "y": 0.8321209031959678,
     "v": 0.00472386081144119,
     "family_factor": 1.0,
     "w": 1.6878148122111813
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.734694,
     "source_value_text": "0.734694",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.8-flash-20260902",
     "source_model_name": "google/gemini-3.8-flash-20260902",
     "p": 0.734694,
     "p_star": 0.730092156862745,
     "y": 0.9950901894312938,
     "v": 0.09755206441235541,
     "family_factor": 1.0,
     "w": 3.5793439227776718
    }
   ]
  },
  {
   "slug": "claude-haiku-5-5",
   "name": "Claude Haiku 5.5",
   "tier": "main",
   "rank": 19,
   "theta": 1.9602396498893975,
   "se": 0.1209147027131527,
   "si_iq": 129.40359474834096,
   "si_iq_low": 126.42028926209287,
   "si_iq_high": 132.38690023458906,
   "si_iq_display": 129,
   "domains": {
    "reasoning": {
     "si_iq": 130.34448958647914,
     "n": 2
    },
    "math": {
     "si_iq": 130.21380830090467,
     "n": 3
    },
    "knowledge": {
     "si_iq": 120.62427324441457,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.55,
     "source_value_text": "0.55",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "KEyuvehfRGtcdgNfNavy62",
     "source_model_name": "claude-haiku-5-5_max",
     "p": 0.5265151515151516,
     "p_star": 0.5262526252625264,
     "y": 0.10510715867648664,
     "v": 0.043219634202063456,
     "family_factor": 1.0,
     "w": 4.937219572764135
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.3,
     "source_value_text": "0.3",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-07",
     "source_row_id": "CKm7NWXfSePfcUycRK87cB",
     "source_model_name": "claude-haiku-5-5_max",
     "p": 0.22890504516413307,
     "p_star": 0.23158915362785454,
     "y": -1.1993596340706725,
     "v": 0.07924494200326306,
     "family_factor": 1.0,
     "w": 3.9449190213338063
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.4634146341463415,
     "source_value_text": "0.4634146341463415",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-07",
     "source_row_id": "WmUXFQoq7GqiSgpTmfLaVv",
     "source_model_name": "claude-haiku-5-5_max",
     "p": 0.4634146341463415,
     "p_star": 0.4642857142857143,
     "y": -0.1431008436406733,
     "v": 0.09344729344729347,
     "family_factor": 1.0,
     "w": 2.584683357879234
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.7508771929824561,
     "source_value_text": "0.7508771929824561",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-07",
     "source_row_id": "2QAt4ptgGkLtcbVL3hdAvL",
     "source_model_name": "claude-haiku-5-5_max",
     "p": 0.7508771929824561,
     "p_star": 0.75,
     "y": 1.0986122886681098,
     "v": 0.018582815785612987,
     "family_factor": 1.0,
     "w": 4.216462534537507
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9888888888888889,
     "source_value_text": "0.9888888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-07",
     "source_row_id": "iiEPrSjWXHH6Zq9CK4Zmcr",
     "source_model_name": "claude-haiku-5-5_xhigh",
     "p": 0.9888777666555445,
     "p_star": 0.9782499891195543,
     "y": 3.8061509921832197,
     "v": 1.0005336230075845,
     "family_factor": 1.0,
     "w": 0.45432505608831736
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8964646464646465,
     "source_value_text": "0.8964646464646465",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-09",
     "source_row_id": "ZEKWTGJiWFscHimMkiUmec",
     "source_model_name": "claude-haiku-5-5_max",
     "p": 0.861952861952862,
     "p_star": 0.8601340033500838,
     "y": 1.8164033975118037,
     "v": 0.05766671295756349,
     "family_factor": 0.5,
     "w": 1.8309199778428233
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8692479999999999,
     "source_value_text": "0.869248",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-haiku-5.5-20261007",
     "source_model_name": "anthropic/claude-haiku-5.5-20261007",
     "p": 0.8256639999999998,
     "p_star": 0.824027497487437,
     "y": 1.5438761529818559,
     "v": 0.048428341817573835,
     "family_factor": 0.5,
     "w": 1.4215006938350545
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.238,
     "source_value_text": "0.238",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-09",
     "source_row_id": "NwnrUMtveqHDYB2Um4ycmA",
     "source_model_name": "claude-haiku-5-5_max",
     "p": 0.238,
     "p_star": 0.23826173826173827,
     "y": -1.1622331981531708,
     "v": 0.0054988486785579275,
     "family_factor": 1.0,
     "w": 1.6839995683647364
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7577776666666667,
     "source_value_text": "0.757778",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-haiku-5.5-20261007",
     "source_model_name": "anthropic/claude-haiku-5.5-20261007",
     "p": 0.7577776666666667,
     "p_star": 0.7527232026143791,
     "y": 1.1131892210399192,
     "v": 0.10327875203444499,
     "family_factor": 1.0,
     "w": 3.478508078732844
    }
   ]
  },
  {
   "slug": "deepseek-v4-1-flash",
   "name": "DeepSeek V4.1 Flash",
   "tier": "main",
   "rank": 20,
   "theta": 1.8474873207487585,
   "se": 0.1218678124203594,
   "si_iq": 127.71230981123138,
   "si_iq_low": 124.70548843026822,
   "si_iq_high": 130.71913119219454,
   "si_iq_display": 128,
   "domains": {
    "reasoning": {
     "si_iq": 132.19232863796827,
     "n": 2
    },
    "math": {
     "si_iq": 125.80630580926733,
     "n": 3
    },
    "knowledge": {
     "si_iq": 125.02333912329827,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.48,
     "source_value_text": "0.48",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "ACpDTbhRPwce2BWQTWD8iC",
     "source_model_name": "deepseek-v4.1-flash_max",
     "p": 0.45286195286195285,
     "p_star": 0.4533286661999533,
     "y": -0.1872303746909695,
     "v": 0.04411035357981414,
     "family_factor": 1.0,
     "w": 4.906703533933967
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.43,
     "source_value_text": "0.43",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-08",
     "source_row_id": "K3JABAsJCbXU5YrCPH2yVW",
     "source_model_name": "deepseek-v4.1-flash_max",
     "p": 0.3721083939193655,
     "p_star": 0.3733746474449164,
     "y": -0.5177665059115792,
     "v": 0.05329633593361754,
     "family_factor": 1.0,
     "w": 4.612678945521232
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2682926829268293,
     "source_value_text": "0.2682926829268293",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-08",
     "source_row_id": "KansJcyeGR4m7G4p8GupDn",
     "source_model_name": "deepseek-v4.1-flash_max",
     "p": 0.2682926829268293,
     "p_star": 0.27380952380952384,
     "y": -0.9753796482441615,
     "v": 0.11689237348538843,
     "family_factor": 1.0,
     "w": 2.305290831416366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6736842105263158,
     "source_value_text": "0.6736842105263158",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-08",
     "source_row_id": "b6dXtaGSwvfRYADKYnj9Ci",
     "source_model_name": "deepseek-v4.1-flash_max",
     "p": 0.6736842105263158,
     "p_star": 0.6730769230769231,
     "y": 0.7221347174331979,
     "v": 0.015834432946732414,
     "family_factor": 1.0,
     "w": 4.316505785718568
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9833333333333333,
     "source_value_text": "0.9833333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-08",
     "source_row_id": "7eHNiVQCzLcAyj5LxmeeSU",
     "source_model_name": "deepseek-v4.1-flash_max",
     "p": 0.9833166499833166,
     "p_star": 0.9728097662880271,
     "y": 3.57733069640059,
     "v": 0.8048271865249628,
     "family_factor": 1.0,
     "w": 0.5525917075063547
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8983585858585859,
     "source_value_text": "0.8983585858585859",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-09",
     "source_row_id": "ZU5ebpDaDPiDZLgv7cG8B9",
     "source_model_name": "deepseek-v4.1-flash_max",
     "p": 0.8644781144781145,
     "p_star": 0.8626465661641542,
     "y": 1.8374476533994843,
     "v": 0.058502927794854415,
     "family_factor": 0.5,
     "w": 1.8212605824444863
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8838381666666666,
     "source_value_text": "0.8838381666666666",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "deepseek/deepseek-v4.1-flash-20260910",
     "source_model_name": "deepseek/deepseek-v4.1-flash-20260910",
     "p": 0.8451175555555555,
     "p_star": 0.843383296482412,
     "y": 1.683620094684677,
     "v": 0.05281324578635494,
     "family_factor": 0.5,
     "w": 1.3914560351692047
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.429,
     "source_value_text": "0.429",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "3JJ4ChNxMo8CGAh3HrKNrw",
     "source_model_name": "deepseek-v4.1-flash_max",
     "p": 0.429,
     "p_star": 0.4290709290709291,
     "y": -0.28564274181055516,
     "v": 0.004073995989150949,
     "family_factor": 1.0,
     "w": 1.6910274303163457
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.745,
     "source_value_text": "0.745",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "deepseek/deepseek-v4.1-flash-20260910",
     "source_model_name": "deepseek/deepseek-v4.1-flash-20260910",
     "p": 0.745,
     "p_star": 0.7401960784313726,
     "y": 1.0469879232628028,
     "v": 0.09996251405722854,
     "family_factor": 1.0,
     "w": 3.536196694267287
    }
   ]
  },
  {
   "slug": "deepseek-v4-pro-0813",
   "name": "DeepSeek V4 Pro 0813",
   "tier": "main",
   "rank": 21,
   "theta": 1.84114970855268,
   "se": 0.12215958747874299,
   "si_iq": 127.61724562829019,
   "si_iq_low": 124.60322533674879,
   "si_iq_high": 130.6312659198316,
   "si_iq_display": 128,
   "domains": {
    "reasoning": {
     "si_iq": 131.66177240879728,
     "n": 2
    },
    "math": {
     "si_iq": 125.32067373109126,
     "n": 3
    },
    "knowledge": {
     "si_iq": 128.7001178195968,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.46,
     "source_value_text": "0.46",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "C56VHYLMeww2wXebeJh3gg",
     "source_model_name": "deepseek-v4-pro-0813_max",
     "p": 0.4318181818181819,
     "p_star": 0.43249324932493255,
     "y": -0.27168592699462696,
     "v": 0.044759401196877796,
     "family_factor": 1.0,
     "w": 4.8847036899859635
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.43,
     "source_value_text": "0.43",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-19",
     "source_row_id": "c2KVkMCWnpo6BbnMWgdaDH",
     "source_model_name": "deepseek-v4-pro-0813_max",
     "p": 0.3721083939193655,
     "p_star": 0.3733746474449164,
     "y": -0.5177665059115792,
     "v": 0.05329633593361754,
     "family_factor": 1.0,
     "w": 4.612678945521232
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2682926829268293,
     "source_value_text": "0.2682926829268293",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-19",
     "source_row_id": "a4uV8HMMBAcHXLVSmZfBgX",
     "source_model_name": "deepseek-v4-pro-0813_max",
     "p": 0.2682926829268293,
     "p_star": 0.27380952380952384,
     "y": -0.9753796482441615,
     "v": 0.11689237348538843,
     "family_factor": 1.0,
     "w": 2.305290831416366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6456140350877193,
     "source_value_text": "0.6456140350877193",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-19",
     "source_row_id": "b6yWmeFgsWeEiG9Qzs3NSf",
     "source_model_name": "deepseek-v4-pro-0813_max",
     "p": 0.6456140350877193,
     "p_star": 0.6451048951048951,
     "y": 0.5975906649987398,
     "v": 0.015218871400536663,
     "family_factor": 1.0,
     "w": 4.339566894921616
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9861111111111112,
     "source_value_text": "0.9861111111111112",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-18",
     "source_row_id": "4HVvM9ZWKKPLQPcC8WYYMT",
     "source_model_name": "deepseek-v4-pro-0813_max",
     "p": 0.9860972083194306,
     "p_star": 0.9755298777037907,
     "y": 3.685527912442322,
     "v": 0.8917960427026593,
     "family_factor": 1.0,
     "w": 0.5041359094733756
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9166666666666666,
     "source_value_text": "0.9166666666666666",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-18",
     "source_row_id": "nEJGtXGN588zynPkynZkxz",
     "source_model_name": "deepseek-v4-pro-0813_max",
     "p": 0.8888888888888888,
     "p_star": 0.8869346733668342,
     "y": 2.059805567162977,
     "v": 0.06859643631947404,
     "family_factor": 0.5,
     "w": 1.7122256015411932
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.892567903763697,
     "source_value_text": "0.892567903763697",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-09-19",
     "source_row_id": "deepseek/deepseek-v4-pro-20260813",
     "source_model_name": "deepseek/deepseek-v4-pro-20260813",
     "p": 0.8567572050182627,
     "p_star": 0.8549644552443015,
     "y": 1.774081046633114,
     "v": 0.05604201690900755,
     "family_factor": 0.5,
     "w": 1.3701324645404716
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.5290581162324649,
     "source_value_text": "0.5290581162324649",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "2xfFf6KZAp2gUWYhHGkFgs",
     "source_model_name": "deepseek-v4-pro-0813_max",
     "p": 0.5290581162324649,
     "p_star": 0.5290290871453196,
     "y": 0.11624707953625127,
     "v": 0.004005513575320669,
     "family_factor": 1.0,
     "w": 1.6913666867652706
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.767500125,
     "source_value_text": "0.767500125",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "deepseek/deepseek-v4-pro-20260813",
     "source_model_name": "deepseek/deepseek-v4-pro-20260813",
     "p": 0.767500125,
     "p_star": 0.7622550245098039,
     "y": 1.1650826099115927,
     "v": 0.1060762135782726,
     "family_factor": 1.0,
     "w": 3.431287720734308
    }
   ]
  },
  {
   "slug": "muse-spark-open",
   "name": "Muse Spark Open",
   "tier": "main",
   "rank": 22,
   "theta": 1.8046966337784915,
   "se": 0.13612370671490628,
   "si_iq": 127.07044950667738,
   "si_iq_low": 123.71189515440477,
   "si_iq_high": 130.42900385894998,
   "si_iq_display": 127,
   "domains": {
    "math": {
     "si_iq": 126.93629281535382,
     "n": 3
    },
    "knowledge": {
     "si_iq": 127.56405144447001,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "frontiermath_t4",
     "score": 0.3170731707317073,
     "source_value_text": "0.3170731707317073",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-15",
     "source_row_id": "YifYkfNddMSuE8uBNdbvLi",
     "source_model_name": "Muse-Spark-Open-816B-A42B_xhigh",
     "p": 0.3170731707317073,
     "p_star": 0.32142857142857145,
     "y": -0.747214401830221,
     "v": 0.10656270305393112,
     "family_factor": 1.0,
     "w": 2.4205725070776976
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6982456140350877,
     "source_value_text": "0.6982456140350877",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-15",
     "source_row_id": "e3e3h9r7Fouu4wsAeVzTnV",
     "source_model_name": "Muse-Spark-Open-816B-A42B_xhigh",
     "p": 0.6982456140350877,
     "p_star": 0.6975524475524476,
     "y": 0.8356698223920849,
     "v": 0.016515276630883566,
     "family_factor": 1.0,
     "w": 4.291282778171509
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9805555555555555,
     "source_value_text": "0.9805555555555555",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-15",
     "source_row_id": "hB4XzBdWkdpG3WJVYqeRM8",
     "source_model_name": "Muse-Spark-Open-816B-A42B_xhigh",
     "p": 0.9805360916472027,
     "p_star": 0.9700896548722635,
     "y": 3.479184083479825,
     "v": 0.7336880657732289,
     "family_factor": 1.0,
     "w": 0.5997447013185443
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8857323232323232,
     "source_value_text": "0.8857323232323232",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-15",
     "source_row_id": "JnKpor8c3EKWGvmyjLFVzH",
     "source_model_name": "Muse-Spark-Open-816B-A42B_xhigh",
     "p": 0.8476430976430976,
     "p_star": 0.8458961474036851,
     "y": 1.7027698522263197,
     "v": 0.05346994966392894,
     "family_factor": 0.5,
     "w": 1.8809880059709312
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.905724,
     "source_value_text": "0.905724",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "meta/muse-spark-open-20261015",
     "source_model_name": "meta/muse-spark-open-20261015",
     "p": 0.8742986666666667,
     "p_star": 0.8724177688442211,
     "y": 1.9225072949431128,
     "v": 0.0620836879492237,
     "family_factor": 0.5,
     "w": 1.3319385267869082
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.566,
     "source_value_text": "0.566",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-15",
     "source_row_id": "dNuxLdV4DWqfSvtTq6NnK8",
     "source_model_name": "Muse-Spark-Open-816B-A42B_xhigh",
     "p": 0.566,
     "p_star": 0.5659340659340659,
     "y": 0.26528113576261414,
     "v": 0.004062658380197791,
     "family_factor": 1.0,
     "w": 1.6910835865312928
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.78,
     "source_value_text": "0.78",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "meta/muse-spark-open-20261015",
     "source_model_name": "meta/muse-spark-open-20261015",
     "p": 0.78,
     "p_star": 0.7745098039215687,
     "y": 1.233953636537872,
     "v": 0.1100715465052284,
     "family_factor": 1.0,
     "w": 3.3660283505788753
    }
   ]
  },
  {
   "slug": "kimi-k3",
   "name": "Kimi K3",
   "tier": "main",
   "rank": 23,
   "theta": 1.8038530074614834,
   "se": 0.12164086115538673,
   "si_iq": 127.05779511192225,
   "si_iq_low": 124.05657325639902,
   "si_iq_high": 130.05901696744547,
   "si_iq_display": 127,
   "domains": {
    "reasoning": {
     "si_iq": 123.5477062356924,
     "n": 2
    },
    "math": {
     "si_iq": 128.30698573370825,
     "n": 3
    },
    "knowledge": {
     "si_iq": 130.41212651822633,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.37,
     "source_value_text": "0.37",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "X2QNPHFXuWosA6AiuvVtDv",
     "source_model_name": "kimi-k3_high",
     "p": 0.33712121212121215,
     "p_star": 0.3387338733873388,
     "y": -0.6689416061231427,
     "v": 0.050507317607186304,
     "family_factor": 1.0,
     "w": 4.698155494552413
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.26,
     "source_value_text": "0.26",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-29",
     "source_row_id": "eCq63CuekohAswYftWXJVj",
     "source_model_name": "kimi-k3_max",
     "p": 0.18484247631636927,
     "p_star": 0.18796284783798936,
     "y": -1.463301767591175,
     "v": 0.0989296548749219,
     "family_factor": 1.0,
     "w": 3.554556919284581
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.3902439024390244,
     "source_value_text": "0.3902439024390244",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-17",
     "source_row_id": "gZERSAQwxBAevQzBsWfUie",
     "source_model_name": "kimi-k3_max",
     "p": 0.3902439024390244,
     "p_star": 0.39285714285714285,
     "y": -0.43531807125784566,
     "v": 0.09744503862150919,
     "family_factor": 1.0,
     "w": 2.5323502858862477
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.721830985915493,
     "source_value_text": "0.721830985915493",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-17",
     "source_row_id": "bcntamvGsSH6QgETdoaSph",
     "source_model_name": "kimi-k3_max",
     "p": 0.721830985915493,
     "p_star": 0.7210553530976067,
     "y": 0.9497025430730643,
     "v": 0.017323121717514902,
     "family_factor": 1.0,
     "w": 4.261734538600809
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9722222222222222,
     "source_value_text": "0.9722222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-16",
     "source_row_id": "A33om9MTYMC7xYeLv9X7Ha",
     "source_model_name": "kimi-k3_max",
     "p": 0.9721944166388611,
     "p_star": 0.9619293206249727,
     "y": 3.2294965610305137,
     "v": 0.58131932486383,
     "family_factor": 1.0,
     "w": 0.7338702745587484
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9311868686868687,
     "source_value_text": "0.9311868686868687",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-16",
     "source_row_id": "B8MaPUe3EYwUZASsNqE7C9",
     "source_model_name": "kimi-k3_max",
     "p": 0.9082491582491583,
     "p_star": 0.9061976549413736,
     "y": 2.2680675881113332,
     "v": 0.08045570823817458,
     "family_factor": 0.5,
     "w": 1.5997007654299573
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9157357830756013,
     "source_value_text": "0.915736",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "moonshotai/kimi-k3-20260715",
     "source_model_name": "moonshotai/kimi-k3-20260715",
     "p": 0.8876477107674684,
     "p_star": 0.8856997323214008,
     "y": 2.0475490778998147,
     "v": 0.06797578770821587,
     "family_factor": 0.5,
     "w": 1.2966868324134269
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.506,
     "source_value_text": "0.506",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "mZLWt2JSYvJyGhMvji7CT8",
     "source_model_name": "kimi-k3_max",
     "p": 0.506,
     "p_star": 0.505994005994006,
     "y": 0.02397717262597127,
     "v": 0.0039925857682284,
     "family_factor": 1.0,
     "w": 1.6914307453712316
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7347416579476861,
     "source_value_text": "0.734742",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "moonshotai/kimi-k3-20260715",
     "source_model_name": "moonshotai/kimi-k3-20260715",
     "p": 0.7347416579476861,
     "p_star": 0.7301388803408687,
     "y": 0.9953273080589911,
     "v": 0.09756271078685266,
     "family_factor": 1.0,
     "w": 3.5791510370063406
    }
   ]
  },
  {
   "slug": "claude-opus-4-7",
   "name": "Claude Opus 4.7",
   "tier": "main",
   "rank": 24,
   "theta": 1.7966022175990601,
   "se": 0.12056373877761423,
   "si_iq": 126.94903326398591,
   "si_iq_low": 123.9743870442362,
   "si_iq_high": 129.9236794837356,
   "si_iq_display": 127,
   "domains": {
    "reasoning": {
     "si_iq": 125.4764383084259,
     "n": 2
    },
    "math": {
     "si_iq": 126.96478693703476,
     "n": 3
    },
    "knowledge": {
     "si_iq": 127.0965682604141,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.41,
     "source_value_text": "0.41",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "XXPqVNR7WCFFA2Rnzjcbk6",
     "source_model_name": "claude-opus-4-7_max",
     "p": 0.3792087542087542,
     "p_star": 0.3804047071373804,
     "y": -0.487830806682605,
     "v": 0.04729738458946777,
     "family_factor": 1.0,
     "w": 4.80053860533453
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.28,
     "source_value_text": "0.28",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-25",
     "source_row_id": "VFYhE54autgdYcMJNXicwU",
     "source_model_name": "claude-opus-4-7_max",
     "p": 0.20687376074025118,
     "p_star": 0.20977600073292196,
     "y": -1.3262761503954121,
     "v": 0.08776688096588997,
     "family_factor": 1.0,
     "w": 3.7658759497368526
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.3170731707317073,
     "source_value_text": "0.3170731707317073",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "P4LXQ9PyDDziEANMB5jVRd",
     "source_model_name": "claude-opus-4-7_max",
     "p": 0.3170731707317073,
     "p_star": 0.32142857142857145,
     "y": -0.747214401830221,
     "v": 0.10656270305393112,
     "family_factor": 1.0,
     "w": 2.4205725070776976
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.7017543859649122,
     "source_value_text": "0.7017543859649122",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "ZkNQ7GER7Mc9FSPmpUzgKH",
     "source_model_name": "claude-opus-4-7_max",
     "p": 0.7017543859649122,
     "p_star": 0.701048951048951,
     "y": 0.8522978708039094,
     "v": 0.016625103906899415,
     "family_factor": 1.0,
     "w": 4.287241625089095
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.978,
     "source_value_text": "0.978",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-17",
     "source_row_id": "jyCZnpXG2bh9G43X8pT75m",
     "source_model_name": "claude-opus-4-7_xhigh",
     "p": 0.9779779779779779,
     "p_star": 0.967587152369761,
     "y": 3.396250624817898,
     "v": 0.6787949918125092,
     "family_factor": 1.0,
     "w": 0.6420174824652344
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.8347107438016529,
     "source_value_text": "0.8347107438016529",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-20",
     "source_row_id": "nCmGWWMBip2s9AVEZNYXDX",
     "source_model_name": "claude-opus-4-7_max",
     "p": 0.8347107438016529,
     "p_star": 0.8340191926780957,
     "y": 1.614384251767969,
     "v": 0.014894382063559843,
     "family_factor": 1.0,
     "w": 6.154406929969599
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9015151515151515,
     "source_value_text": "0.9015151515151515",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-17",
     "source_row_id": "VJezHrJ5YPCbpui8pZgcJg",
     "source_model_name": "claude-opus-4-7_xhigh",
     "p": 0.8686868686868686,
     "p_star": 0.8668341708542714,
     "y": 1.8732525034792382,
     "v": 0.059970277371568556,
     "family_factor": 0.5,
     "w": 1.8045548169195025
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.892375117408907,
     "source_value_text": "0.892375",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.7-opus-20260416",
     "source_model_name": "anthropic/claude-4.7-opus-20260416",
     "p": 0.8565001565452093,
     "p_star": 0.8547086984721177,
     "y": 1.7720200041615317,
     "v": 0.05596480326033475,
     "family_factor": 0.5,
     "w": 1.370634771274181
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.517,
     "source_value_text": "0.517",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "2c4rvmf5N7QXTugrFLMZ83",
     "source_model_name": "claude-opus-4-7_xhigh",
     "p": 0.517,
     "p_star": 0.516983016983017,
     "y": 0.067958210246175,
     "v": 0.003996622853688633,
     "family_factor": 1.0,
     "w": 1.6914107406789642
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7757142142857143,
     "source_value_text": "0.775714",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.7-opus-20260416",
     "source_model_name": "anthropic/claude-4.7-opus-20260416",
     "p": 0.7757142142857143,
     "p_star": 0.7703080532212885,
     "y": 1.2100514546152206,
     "v": 0.10864742686369105,
     "family_factor": 1.0,
     "w": 3.3890031227104416
    }
   ]
  },
  {
   "slug": "gemini-3-1-pro",
   "name": "Gemini 3.1 Pro",
   "tier": "main",
   "rank": 25,
   "theta": 1.7898411201884359,
   "se": 0.1200150886415381,
   "si_iq": 126.84761680282654,
   "si_iq_low": 123.88650732364071,
   "si_iq_high": 129.80872628201237,
   "si_iq_display": 127,
   "domains": {
    "reasoning": {
     "si_iq": 130.22993267600876,
     "n": 2
    },
    "math": {
     "si_iq": 124.09399316157572,
     "n": 3
    },
    "knowledge": {
     "si_iq": 138.7251854034216,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.51,
     "source_value_text": "0.51",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "FTDFCpXzDTgfgWBNdHLHGc",
     "source_model_name": "gemini-3.1-pro-preview_high",
     "p": 0.48442760942760943,
     "p_star": 0.48458179151248454,
     "y": -0.06169239302658756,
     "v": 0.04347622485648207,
     "family_factor": 1.0,
     "w": 4.928389925883956
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.34,
     "source_value_text": "0.34",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-27",
     "source_row_id": "g4bbCaiFDqw2YYNDAcmn2a",
     "source_model_name": "gemini-3.1-pro-preview_high",
     "p": 0.27296761401189695,
     "p_star": 0.27521545941771974,
     "y": -0.9683201455914322,
     "v": 0.06728064615894949,
     "family_factor": 1.0,
     "w": 4.227068686204482
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2682926829268293,
     "source_value_text": "0.2682926829268293",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "eXVWr3RBeSsWy5DAU8ed46",
     "source_model_name": "gemini-3.1-pro-preview",
     "p": 0.2682926829268293,
     "p_star": 0.27380952380952384,
     "y": -0.9753796482441615,
     "v": 0.11689237348538843,
     "family_factor": 1.0,
     "w": 2.305290831416366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5964912280701754,
     "source_value_text": "0.5964912280701754",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "hVifTUdQZrFEYabgCRu8Qq",
     "source_model_name": "gemini-3.1-pro-preview",
     "p": 0.5964912280701754,
     "p_star": 0.5961538461538461,
     "y": 0.38946476676172315,
     "v": 0.014472331187873706,
     "family_factor": 1.0,
     "w": 4.367867718002461
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.956,
     "source_value_text": "0.956",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-20",
     "source_row_id": "bXgZZgzRE3wXoSRUgrbsVf",
     "source_model_name": "gemini-3.1-pro-preview",
     "p": 0.955955955955956,
     "p_star": 0.9460438699569135,
     "y": 2.864117632364596,
     "v": 0.41706530404714953,
     "family_factor": 1.0,
     "w": 0.9669958438255732
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.756198347107438,
     "source_value_text": "0.756198347107438",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-24",
     "source_row_id": "8QQQWDgmmEsmQVUJWcxx4P",
     "source_model_name": "gemini-3.1-pro-preview-customtools",
     "p": 0.756198347107438,
     "p_star": 0.75566901167953,
     "y": 1.129079649496242,
     "v": 0.011167250099544836,
     "family_factor": 1.0,
     "w": 6.360747257428495
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9444444444444444,
     "source_value_text": "0.9444444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "BgmrBFsbsaD8rNpebv49Da",
     "source_model_name": "gemini-3.1-pro-preview_high",
     "p": 0.9259259259259259,
     "p_star": 0.9237855946398661,
     "y": 2.494929512736654,
     "v": 0.09663978744595443,
     "family_factor": 0.5,
     "w": 1.4680403103779491
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9483723333333332,
     "source_value_text": "0.9483723333333332",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.1-pro-preview-20260219",
     "source_model_name": "google/gemini-3.1-pro-preview-20260219",
     "p": 0.9311631111111108,
     "p_star": 0.9289964623115575,
     "y": 2.5713752283480384,
     "v": 0.10299680733821182,
     "family_factor": 0.5,
     "w": 1.1204323573241524
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.735,
     "source_value_text": "0.735",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "VGeF8Xac4WcSAGgSXVdEBi",
     "source_model_name": "gemini-3.1-pro-preview_high",
     "p": 0.735,
     "p_star": 0.7347652347652348,
     "y": 1.018935699359499,
     "v": 0.005120976672671014,
     "family_factor": 1.0,
     "w": 1.6858576647010206
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7422223333333333,
     "source_value_text": "0.7422223333333333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.1-pro-preview-20260219",
     "source_model_name": "google/gemini-3.1-pro-preview-20260219",
     "p": 0.7422223333333333,
     "p_star": 0.7374728758169935,
     "y": 1.0328749020699421,
     "v": 0.09929089361218921,
     "family_factor": 1.0,
     "w": 3.5481138569359034
    }
   ]
  },
  {
   "slug": "gemini-3-5-flash",
   "name": "Gemini 3.5 Flash",
   "tier": "main",
   "rank": 26,
   "theta": 1.7547827467505512,
   "se": 0.11999131374358102,
   "si_iq": 126.32174120125828,
   "si_iq_low": 123.3612183156125,
   "si_iq_high": 129.28226408690404,
   "si_iq_display": 126,
   "domains": {
    "reasoning": {
     "si_iq": 127.90317852351028,
     "n": 2
    },
    "math": {
     "si_iq": 124.5880806975216,
     "n": 3
    },
    "knowledge": {
     "si_iq": 133.63726760052032,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.45,
     "source_value_text": "0.45",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "XUDdWKUZBhdWPPQBRgx8Pw",
     "source_model_name": "gemini-3.5-flash_high",
     "p": 0.42129629629629634,
     "p_star": 0.4220755408874221,
     "y": -0.3142588616959415,
     "v": 0.04515710075908147,
     "family_factor": 1.0,
     "w": 4.871320641489932
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.32,
     "source_value_text": "0.32",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-27",
     "source_row_id": "GQKsxFbdBWB546zE8ci49f",
     "source_model_name": "gemini-3.5-flash_high",
     "p": 0.250936329588015,
     "p_star": 0.2534023065227871,
     "y": -1.0805481069613732,
     "v": 0.07258332910159537,
     "family_factor": 1.0,
     "w": 4.097190527425113
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2682926829268293,
     "source_value_text": "0.2682926829268293",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "cXn5zzns6VFwbTgotDwZjV",
     "source_model_name": "gemini-3.5-flash_high",
     "p": 0.2682926829268293,
     "p_star": 0.27380952380952384,
     "y": -0.9753796482441615,
     "v": 0.11689237348538843,
     "family_factor": 1.0,
     "w": 2.305290831416366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6280701754385964,
     "source_value_text": "0.6280701754385964",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "72DQVwbYiQW5pjhshjBaGU",
     "source_model_name": "gemini-3.5-flash_high",
     "p": 0.6280701754385964,
     "p_star": 0.6276223776223776,
     "y": 0.5220302227788537,
     "v": 0.014908391855310132,
     "family_factor": 1.0,
     "w": 4.351292294035303
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9555555555555556,
     "source_value_text": "0.9555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-05-25",
     "source_row_id": "eYmgjYJfM7Utm46nfoRfZ6",
     "source_model_name": "gemini-3.5-flash_high",
     "p": 0.9555110666221778,
     "p_star": 0.9456086521303912,
     "y": 2.8556237017959454,
     "v": 0.4139187345337018,
     "family_factor": 1.0,
     "w": 0.9729164679191334
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7933884297520661,
     "source_value_text": "0.7933884297520661",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-01",
     "source_row_id": "dwRzFGTghYEy4HNZajJXoc",
     "source_model_name": "gemini-3.5-flash_high",
     "p": 0.7933884297520661,
     "p_star": 0.7927822553104297,
     "y": 1.3417784533505257,
     "v": 0.012550919497048849,
     "family_factor": 1.0,
     "w": 6.282550016884475
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.928030303030303,
     "source_value_text": "0.928030303030303",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-05-22",
     "source_row_id": "dYYtcwENFRtm9jZTDA2p9C",
     "source_model_name": "gemini-3.5-flash_high",
     "p": 0.904040404040404,
     "p_star": 0.9020100502512562,
     "y": 2.219760742358632,
     "v": 0.07747158529663317,
     "family_factor": 0.5,
     "w": 1.6265991770587367
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9242421666666667,
     "source_value_text": "0.9242421666666667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.5-flash-20260519",
     "source_model_name": "google/gemini-3.5-flash-20260519",
     "p": 0.8989895555555556,
     "p_star": 0.8969845829145728,
     "y": 2.164160017055208,
     "v": 0.0742171380951308,
     "family_factor": 0.5,
     "w": 1.2613252748171726
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.662,
     "source_value_text": "0.662",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "GJ6YsSuzyRD9YXe6SBwvsu",
     "source_model_name": "gemini-3.5-flash_high",
     "p": 0.662,
     "p_star": 0.6618381618381618,
     "y": 0.6714964655080474,
     "v": 0.004459184526629692,
     "family_factor": 1.0,
     "w": 1.6891217695459722
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7333336666666668,
     "source_value_text": "0.7333336666666668",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.5-flash-20260519",
     "source_model_name": "google/gemini-3.5-flash-20260519",
     "p": 0.7333336666666668,
     "p_star": 0.7287584967320262,
     "y": 0.9883328169139168,
     "v": 0.09725006005196464,
     "family_factor": 1.0,
     "w": 3.584824161778523
    }
   ]
  },
  {
   "slug": "grok-4-6",
   "name": "Grok 4.6",
   "tier": "main",
   "rank": 27,
   "theta": 1.7518427731476849,
   "se": 0.12287311949779535,
   "si_iq": 126.27764159721528,
   "si_iq_low": 123.24601646573888,
   "si_iq_high": 129.30926672869168,
   "si_iq_display": 126,
   "domains": {
    "reasoning": {
     "si_iq": 125.0771908457059,
     "n": 2
    },
    "math": {
     "si_iq": 126.29829735169642,
     "n": 3
    },
    "knowledge": {
     "si_iq": 131.16096884099792,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.33,
     "source_value_text": "0.33",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "NiuExVccWkWbWqi6ex6vvf",
     "source_model_name": "grok-4.6_xhigh",
     "p": 0.2950336700336701,
     "p_star": 0.29706303963729713,
     "y": -0.8613228445241748,
     "v": 0.0551927491039482,
     "family_factor": 1.0,
     "w": 4.556313263791254
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.34,
     "source_value_text": "0.34",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "9cXtChGrowgGDwa9AcAecB",
     "source_model_name": "grok-4.6_xhigh",
     "p": 0.27296761401189695,
     "p_star": 0.27521545941771974,
     "y": -0.9683201455914322,
     "v": 0.06728064615894949,
     "family_factor": 1.0,
     "w": 4.227068686204482
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.3170731707317073,
     "source_value_text": "0.3170731707317073",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "bg3JRdd33iWfvRoGSvyXXE",
     "source_model_name": "grok-4.6_xhigh",
     "p": 0.3170731707317073,
     "p_star": 0.32142857142857145,
     "y": -0.747214401830221,
     "v": 0.10656270305393112,
     "family_factor": 1.0,
     "w": 2.4205725070776976
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6596491228070176,
     "source_value_text": "0.6596491228070176",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "Zb2AKwa942D7dBTTcebAba",
     "source_model_name": "grok-4.6_xhigh",
     "p": 0.6596491228070176,
     "p_star": 0.6590909090909092,
     "y": 0.6592456288842643,
     "v": 0.015507039379718427,
     "family_factor": 1.0,
     "w": 4.328740505211093
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9916666666666667,
     "source_value_text": "0.9916666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "7crLvnfQc987dC6mr3iGbf",
     "source_model_name": "grok-4.6_xhigh",
     "p": 0.9916583249916584,
     "p_star": 0.9809701005353181,
     "y": 3.942530582240475,
     "v": 1.1403745660112583,
     "family_factor": 1.0,
     "w": 0.403104041070334
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9400252525252525,
     "source_value_text": "0.9400252525252525",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-12",
     "source_row_id": "hnP6Z88x8bPEBRZ2PW6kps",
     "source_model_name": "grok-4.6_high",
     "p": 0.92003367003367,
     "p_star": 0.9179229480737018,
     "y": 2.414454988837388,
     "v": 0.0904630246792093,
     "family_factor": 0.5,
     "w": 1.5156492189548028
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9246375695652174,
     "source_value_text": "0.924638",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "x-ai/grok-4.6-20260810",
     "source_model_name": "x-ai/grok-4.6-20260810",
     "p": 0.8995167594202899,
     "p_star": 0.8975091375136551,
     "y": 2.1698496532543223,
     "v": 0.07454158196394645,
     "family_factor": 0.5,
     "w": 1.2595397365339212
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.493,
     "source_value_text": "0.493",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "TpHYtuPG6kYZFvMK7Z6Hqj",
     "source_model_name": "grok-4.6_high",
     "p": 0.493,
     "p_star": 0.493006993006993,
     "y": -0.027973852042406065,
     "v": 0.003992793008619442,
     "family_factor": 1.0,
     "w": 1.6914297184356355
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.747619,
     "source_value_text": "0.747619",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "x-ai/grok-4.6-20260810",
     "source_model_name": "x-ai/grok-4.6-20260810",
     "p": 0.747619,
     "p_star": 0.7427637254901961,
     "y": 1.0603829748431326,
     "v": 0.10061129873736904,
     "family_factor": 1.0,
     "w": 3.524760497723803
    }
   ]
  },
  {
   "slug": "claude-sonnet-5",
   "name": "Claude Sonnet 5",
   "tier": "main",
   "rank": 28,
   "theta": 1.7399027018778956,
   "se": 0.1200577384925327,
   "si_iq": 126.09854052816843,
   "si_iq_low": 123.13637875731249,
   "si_iq_high": 129.06070229902437,
   "si_iq_display": 126,
   "domains": {
    "reasoning": {
     "si_iq": 128.83722871376966,
     "n": 2
    },
    "math": {
     "si_iq": 125.28757609313438,
     "n": 3
    },
    "knowledge": {
     "si_iq": 122.09617963111188,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.45,
     "source_value_text": "0.45",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "PN9exWpeJGXJB8tZGX32e4",
     "source_model_name": "claude-sonnet-5_max",
     "p": 0.42129629629629634,
     "p_star": 0.4220755408874221,
     "y": -0.3142588616959415,
     "v": 0.04515710075908147,
     "family_factor": 1.0,
     "w": 4.871320641489932
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.35,
     "source_value_text": "0.35",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-28",
     "source_row_id": "YdcyYXLzqfPUSSgGv4MTED",
     "source_model_name": "claude-sonnet-5_max",
     "p": 0.28398325622383785,
     "p_star": 0.28612203586518603,
     "y": -0.9142936105135304,
     "v": 0.06502959796176043,
     "family_factor": 1.0,
     "w": 4.284727042420558
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2926829268292683,
     "source_value_text": "0.2926829268292683",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-30",
     "source_row_id": "bqiVinHXFcgyFGPstJwXJN",
     "source_model_name": "claude-sonnet-5_max",
     "p": 0.2926829268292683,
     "p_star": 0.2976190476190476,
     "y": -0.8586616190375186,
     "v": 0.11118644067796613,
     "family_factor": 1.0,
     "w": 2.367576243980738
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.656140350877193,
     "source_value_text": "0.656140350877193",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-30",
     "source_row_id": "V6YuGpcu8MCbJNXKoJMA6b",
     "source_model_name": "claude-sonnet-5_max",
     "p": 0.656140350877193,
     "p_star": 0.6555944055944056,
     "y": 0.6437222972324225,
     "v": 0.015431472081218277,
     "family_factor": 1.0,
     "w": 4.331574318381706
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9472222222222222,
     "source_value_text": "0.9472222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-01",
     "source_row_id": "T2wFfuSkUdyjpyqurxNmNK",
     "source_model_name": "claude-sonnet-5_xhigh",
     "p": 0.9471693916138361,
     "p_star": 0.9374483178831005,
     "y": 2.7071684998257903,
     "v": 0.36305632941479177,
     "family_factor": 1.0,
     "w": 1.079782238657438
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9053030303030303,
     "source_value_text": "0.9053030303030303",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-01",
     "source_row_id": "HhiYxEx3Bf8YDPUh34K4DC",
     "source_model_name": "claude-sonnet-5_xhigh",
     "p": 0.8737373737373737,
     "p_star": 0.871859296482412,
     "y": 1.917499147222533,
     "v": 0.06186365783679448,
     "family_factor": 0.5,
     "w": 1.7834462562676126
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8576035833333334,
     "source_value_text": "0.857604",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-sonnet-5-20260630",
     "source_model_name": "anthropic/claude-sonnet-5-20260630",
     "p": 0.8101381111111112,
     "p_star": 0.8085796281407036,
     "y": 1.4408072534991347,
     "v": 0.04562031649315283,
     "family_factor": 0.5,
     "w": 1.441431865883584
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.337,
     "source_value_text": "0.337",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "LPo74T9L3CawnKX5LLUrSZ",
     "source_model_name": "claude-sonnet-5_max",
     "p": 0.337,
     "p_star": 0.3371628371628372,
     "y": -0.6759633434596776,
     "v": 0.0044656563119260945,
     "family_factor": 1.0,
     "w": 1.6890897880758278
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.76,
     "source_value_text": "0.76",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-sonnet-5-20260630",
     "source_model_name": "anthropic/claude-sonnet-5-20260630",
     "p": 0.76,
     "p_star": 0.7549019607843137,
     "y": 1.124929596985483,
     "v": 0.10389610389610388,
     "family_factor": 1.0,
     "w": 3.4679759332079083
    }
   ]
  },
  {
   "slug": "glm-5-3",
   "name": "GLM-5.3",
   "tier": "main",
   "rank": 29,
   "theta": 1.6878000927329657,
   "se": 0.11939417789941922,
   "si_iq": 125.31700139099448,
   "si_iq_low": 122.37121152457591,
   "si_iq_high": 128.26279125741306,
   "si_iq_display": 125,
   "domains": {
    "reasoning": {
     "si_iq": 125.84417305757418,
     "n": 2
    },
    "math": {
     "si_iq": 125.14646258872402,
     "n": 3
    },
    "knowledge": {
     "si_iq": 123.87415051373148,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.37,
     "source_value_text": "0.37",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "kG3hbd8qLEd6fLAJHyQTiN",
     "source_model_name": "glm-5.3_max",
     "p": 0.33712121212121215,
     "p_star": 0.3387338733873388,
     "y": -0.6689416061231427,
     "v": 0.050507317607186304,
     "family_factor": 1.0,
     "w": 4.698155494552413
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.33,
     "source_value_text": "0.33",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "UUq99Qhq3qizcoJo5vdhuK",
     "source_model_name": "glm-5.3_max",
     "p": 0.26195197179995594,
     "p_star": 0.2643088829702534,
     "y": -1.0236919222231944,
     "v": 0.06978606437003237,
     "family_factor": 1.0,
     "w": 4.164692690240327
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2926829268292683,
     "source_value_text": "0.2926829268292683",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-25",
     "source_row_id": "4S3ZrJDkwh4gmGrmJQdvzR",
     "source_model_name": "glm-5.3_max",
     "p": 0.2926829268292683,
     "p_star": 0.2976190476190476,
     "y": -0.8586616190375186,
     "v": 0.11118644067796613,
     "family_factor": 1.0,
     "w": 2.367576243980738
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6877192982456141,
     "source_value_text": "0.6877192982456141",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-25",
     "source_row_id": "iXvqUzwxAiA3Rg3dwnutFs",
     "source_model_name": "glm-5.3_max",
     "p": 0.6877192982456141,
     "p_star": 0.6870629370629371,
     "y": 0.7864238060285065,
     "v": 0.016205381892618026,
     "family_factor": 1.0,
     "w": 4.302726705567176
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9111111111111111,
     "source_value_text": "0.9111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-24",
     "source_row_id": "goZR5yGxZic9TZ23ezCL3w",
     "source_model_name": "glm-5.3_max",
     "p": 0.9110221332443554,
     "p_star": 0.9020868694781738,
     "y": 2.2206301607323202,
     "v": 0.24104004547939525,
     "family_factor": 1.0,
     "w": 1.4661034873401948
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9090909090909091,
     "source_value_text": "0.9090909090909091",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-24",
     "source_row_id": "dLDBahYBTGRNjbsXA5pyr3",
     "source_model_name": "glm-5.3_max",
     "p": 0.8787878787878788,
     "p_star": 0.8768844221105527,
     "y": 1.9632516240918003,
     "v": 0.06391824469790049,
     "family_factor": 0.5,
     "w": 1.7610921537552942
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8639263412162163,
     "source_value_text": "0.863926",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5.3-20260816",
     "source_model_name": "z-ai/glm-5.3-20260816",
     "p": 0.818568454954955,
     "p_star": 0.8169676084476437,
     "y": 1.4959363069345584,
     "v": 0.04707961286129565,
     "family_factor": 0.5,
     "w": 1.4310046279937532
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.41,
     "source_value_text": "0.41",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "TY8R8FV7zCwByEipkqyg2P",
     "source_model_name": "glm-5.3_max",
     "p": 0.41,
     "p_star": 0.4100899100899101,
     "y": -0.3635937067449343,
     "v": 0.004125408286501354,
     "family_factor": 1.0,
     "w": 1.69077282729679
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.78083325,
     "source_value_text": "0.780833",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5.3-20260816",
     "source_model_name": "z-ai/glm-5.3-20260816",
     "p": 0.78083325,
     "p_star": 0.7753267156862745,
     "y": 1.2386372319329757,
     "v": 0.11035536952600518,
     "family_factor": 1.0,
     "w": 3.361486720210065
    }
   ]
  },
  {
   "slug": "gpt-5-2",
   "name": "GPT-5.2",
   "tier": "main",
   "rank": 30,
   "theta": 1.670511087149762,
   "se": 0.11912327790613039,
   "si_iq": 125.05766630724642,
   "si_iq_low": 122.11856030489128,
   "si_iq_high": 127.99677230960158,
   "si_iq_display": 125,
   "domains": {
    "reasoning": {
     "si_iq": 125.91700253766585,
     "n": 2
    },
    "math": {
     "si_iq": 126.14526259601624,
     "n": 3
    },
    "knowledge": {
     "si_iq": 123.96283890994556,
     "n": 2
    },
    "agentic": {
     "si_iq": 116.68390537306652,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.48,
     "source_value_text": "0.48",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "YGX23vJ7GJBaYUVLvHnXn5",
     "source_model_name": "gpt-5.2-2025-12-11_xhigh",
     "p": 0.45286195286195285,
     "p_star": 0.4533286661999533,
     "y": -0.1872303746909695,
     "v": 0.04411035357981414,
     "family_factor": 1.0,
     "w": 4.906703533933967
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.23,
     "source_value_text": "0.23",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "AsFSc8AQu4F46Tzp4xVwYu",
     "source_model_name": "gpt-5.2-2025-12-11_high",
     "p": 0.1517955496805464,
     "p_star": 0.1552431184955905,
     "y": -1.6940564772425524,
     "v": 0.12365401711155612,
     "family_factor": 1.0,
     "w": 3.1616100185397094
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.317,
     "source_value_text": "0.317",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "J3NUxsK2GXq9Whkjn7mEVm",
     "source_model_name": "gpt-5.2-2025-12-11_xhigh",
     "p": 0.317,
     "p_star": 0.32135714285714284,
     "y": -0.7475419063655772,
     "v": 0.10657517047913734,
     "family_factor": 1.0,
     "w": 2.42042641833616
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.674,
     "source_value_text": "0.674",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "PeZ84GTQdSYQzDxRMWA2Ha",
     "source_model_name": "gpt-5.2-2025-12-11_xhigh",
     "p": 0.674,
     "p_star": 0.6733916083916084,
     "y": 0.7235651710513634,
     "v": 0.015842282550733562,
     "family_factor": 1.0,
     "w": 4.3162132944076195
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9611111111111111,
     "source_value_text": "0.9611111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-12-11",
     "source_row_id": "LiUMZyNSM8q93KDubWgYCh",
     "source_model_name": "gpt-5.2-2025-12-11_high",
     "p": 0.9610721832944056,
     "p_star": 0.9510488749619185,
     "y": 2.966743102329287,
     "v": 0.45728631146678794,
     "family_factor": 1.0,
     "w": 0.8972048832206029
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.737603305785124,
     "source_value_text": "0.737603305785124",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-12",
     "source_row_id": "9owdbpnWJ5pkQQC3GWKP5L",
     "source_model_name": "gpt-5.2-2025-12-11_high",
     "p": 0.737603305785124,
     "p_star": 0.7371123898640803,
     "y": 1.0310137740297143,
     "v": 0.010640268272991525,
     "family_factor": 1.0,
     "w": 6.39104362474833
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.914,
     "source_value_text": "0.914",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-12-13",
     "source_row_id": "Ejo6Fy7XYxUDcCwbejfcYX",
     "source_model_name": "gpt-5.2-2025-12-11_xhigh",
     "p": 0.8853333333333334,
     "p_star": 0.8833969849246233,
     "y": 2.0249995542598485,
     "v": 0.06685467187229532,
     "family_factor": 0.5,
     "w": 1.7300992016319128
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.878788,
     "source_value_text": "0.878788",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "openai/gpt-5.2-20251211",
     "source_model_name": "openai/gpt-5.2-20251211",
     "p": 0.838384,
     "p_star": 0.8366835778894472,
     "y": 1.63375639689285,
     "v": 0.051168045669825614,
     "family_factor": 0.5,
     "w": 1.4025786285494988
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.371,
     "source_value_text": "0.371",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "E3325ytkSNYP8ez53VA4fE",
     "source_model_name": "gpt-5.2-2025-12-11_xhigh",
     "p": 0.371,
     "p_star": 0.3711288711288711,
     "y": -0.5273769893265879,
     "v": 0.004276076315133996,
     "family_factor": 1.0,
     "w": 1.6900271332600092
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5587,
     "source_value_text": "55.87%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "16",
     "source_model_name": "GPT-5.2-2025-12-11 (FC)",
     "p": 0.5587,
     "p_star": 0.5581188118811881,
     "y": 0.23353082345230491,
     "v": 0.03974889667993763,
     "family_factor": 1.0,
     "w": 5.059838023666199
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.726667,
     "source_value_text": "0.726667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "openai/gpt-5.2-20251211",
     "source_model_name": "openai/gpt-5.2-20251211",
     "p": 0.726667,
     "p_star": 0.7222225490196078,
     "y": 0.9555130739873019,
     "v": 0.09582120325628546,
     "family_factor": 1.0,
     "w": 3.6109816987545793
    }
   ]
  },
  {
   "slug": "qwen3-7-max",
   "name": "Qwen3.7-Max",
   "tier": "main",
   "rank": 31,
   "theta": 1.6657047570778456,
   "se": 0.11924391799910913,
   "si_iq": 124.98557135616768,
   "si_iq_low": 122.04348882372008,
   "si_iq_high": 127.92765388861528,
   "si_iq_display": 125,
   "domains": {
    "reasoning": {
     "si_iq": 122.03132033257394,
     "n": 2
    },
    "math": {
     "si_iq": 125.93067458283271,
     "n": 3
    },
    "knowledge": {
     "si_iq": 128.65028216627405,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.26,
     "source_value_text": "0.26",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "cbQnfsMSA3aQaBtjm3aFx2",
     "source_model_name": "qwen3.7-max",
     "p": 0.22138047138047137,
     "p_star": 0.22413908057472415,
     "y": -1.2417065219731929,
     "v": 0.06949643389577817,
     "family_factor": 1.0,
     "w": 4.171809193468584
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.32,
     "source_value_text": "0.32",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-28",
     "source_row_id": "f7dotY9NheKNKK2zz6bfKZ",
     "source_model_name": "qwen3.7-max",
     "p": 0.250936329588015,
     "p_star": 0.2534023065227871,
     "y": -1.0805481069613732,
     "v": 0.07258332910159537,
     "family_factor": 1.0,
     "w": 4.097190527425113
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.34146341463414637,
     "source_value_text": "0.34146341463414637",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-13",
     "source_row_id": "FHZCKbtfvpKGXU99vZFnXN",
     "source_model_name": "qwen3.7-max",
     "p": 0.34146341463414637,
     "p_star": 0.3452380952380953,
     "y": -0.6400373552459966,
     "v": 0.10282131661442005,
     "family_factor": 1.0,
     "w": 2.465224111282844
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6456140350877193,
     "source_value_text": "0.6456140350877193",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-13",
     "source_row_id": "RG2biwnmGybSVTVxxMdRWa",
     "source_model_name": "qwen3.7-max",
     "p": 0.6456140350877193,
     "p_star": 0.6451048951048951,
     "y": 0.5975906649987398,
     "v": 0.015218871400536663,
     "family_factor": 1.0,
     "w": 4.339566894921616
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9555555555555556,
     "source_value_text": "0.9555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "D3YDUZSfEUDsS4frLbEKDu",
     "source_model_name": "qwen3.7-max",
     "p": 0.9555110666221778,
     "p_star": 0.9456086521303912,
     "y": 2.8556237017959454,
     "v": 0.4139187345337018,
     "family_factor": 1.0,
     "w": 0.9729164679191334
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7727272727272727,
     "source_value_text": "0.7727272727272727",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-18",
     "source_row_id": "83hhDhcT9UUrZ2NiUbWSUU",
     "source_model_name": "qwen3.7-max",
     "p": 0.7727272727272727,
     "p_star": 0.7721637866265965,
     "y": 1.2205696779538278,
     "v": 0.011719908563737164,
     "family_factor": 1.0,
     "w": 6.329281775084312
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9090909090909091,
     "source_value_text": "0.9090909090909091",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "W6mTanyjvXhasFBzHukv4S",
     "source_model_name": "qwen3.7-max",
     "p": 0.8787878787878788,
     "p_star": 0.8768844221105527,
     "y": 1.9632516240918003,
     "v": 0.06391824469790049,
     "family_factor": 0.5,
     "w": 1.7610921537552942
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9090909999999999,
     "source_value_text": "0.909091",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-09-27",
     "source_row_id": "qwen/qwen3.7-max-20260520",
     "source_model_name": "qwen/qwen3.7-max-20260520",
     "p": 0.8787879999999998,
     "p_star": 0.8768845427135676,
     "y": 1.9632527412199223,
     "v": 0.06391829609935486,
     "family_factor": 0.5,
     "w": 1.3207585333636587
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.5576730190571715,
     "source_value_text": "0.5576730190571715",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "DMjUrG6eZEqwcQ4SqUoViu",
     "source_model_name": "qwen3.7-max",
     "p": 0.5576730190571715,
     "p_star": 0.5576154036535179,
     "y": 0.2314898527644274,
     "v": 0.004045731772662464,
     "family_factor": 1.0,
     "w": 1.691167432508948
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.72,
     "source_value_text": "0.72",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-09-27",
     "source_row_id": "qwen/qwen3.7-max-20260520",
     "source_model_name": "qwen/qwen3.7-max-20260520",
     "p": 0.72,
     "p_star": 0.7156862745098039,
     "y": 0.923163611161917,
     "v": 0.0944733112895607,
     "family_factor": 1.0,
     "w": 3.6360093654892425
    }
   ]
  },
  {
   "slug": "gemini-3-6-flash",
   "name": "Gemini 3.6 Flash",
   "tier": "main",
   "rank": 32,
   "theta": 1.6486590666259981,
   "se": 0.12291979065290351,
   "si_iq": 124.72988599938998,
   "si_iq_low": 121.69710935937111,
   "si_iq_high": 127.76266263940883,
   "si_iq_display": 125,
   "domains": {
    "reasoning": {
     "si_iq": 126.2541697465731,
     "n": 2
    },
    "math": {
     "si_iq": 122.87076407566946,
     "n": 3
    },
    "knowledge": {
     "si_iq": 134.73486670539327,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.42,
     "source_value_text": "0.42",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "hJ6XXLBm9yfXtSbbhWuwpw",
     "source_model_name": "gemini-3.6-flash_low",
     "p": 0.3897306397306397,
     "p_star": 0.39082241557489084,
     "y": -0.4438565485451298,
     "v": 0.046673340679655534,
     "family_factor": 1.0,
     "w": 4.820963222832132
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.3,
     "source_value_text": "0.3",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-05",
     "source_row_id": "YBqiCXPjMUSAgAjDUoz5sy",
     "source_model_name": "gemini-3.6-flash_high",
     "p": 0.22890504516413307,
     "p_star": 0.23158915362785454,
     "y": -1.1993596340706725,
     "v": 0.07924494200326306,
     "family_factor": 1.0,
     "w": 3.9449190213338063
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.21951219512195122,
     "source_value_text": "0.21951219512195122",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "JCMjXU6FRiiLV3xvs9R2Xv",
     "source_model_name": "gemini-3.6-flash_high",
     "p": 0.21951219512195122,
     "p_star": 0.2261904761904762,
     "y": -1.2299482907291965,
     "v": 0.13279352226720645,
     "family_factor": 1.0,
     "w": 2.1478260869565218
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5894736842105263,
     "source_value_text": "0.5894736842105263",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "nb9LnDeeQyvRCqsbsTANGD",
     "source_model_name": "gemini-3.6-flash_high",
     "p": 0.5894736842105263,
     "p_star": 0.5891608391608391,
     "y": 0.36049741620820225,
     "v": 0.014394848159606035,
     "family_factor": 1.0,
     "w": 4.370826204536674
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9416666666666667,
     "source_value_text": "0.9416666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "ajQFZGMjvyMTH2ULDZhwtz",
     "source_model_name": "gemini-3.6-flash_high",
     "p": 0.9416082749416083,
     "p_star": 0.9320080950515733,
     "y": 2.6179528471119,
     "v": 0.3359588996215159,
     "family_factor": 1.0,
     "w": 1.1468971052869485
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9412878787878788,
     "source_value_text": "0.9412878787878788",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "86SY5JbPB49xXhHFQW6tHu",
     "source_model_name": "gemini-3.6-flash_high",
     "p": 0.9217171717171717,
     "p_star": 0.9195979899497487,
     "y": 2.4368974306016398,
     "v": 0.09213473080713072,
     "family_factor": 0.5,
     "w": 1.5024620139322529
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.930415,
     "source_value_text": "0.930415",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.6-flash-20260721",
     "source_model_name": "google/gemini-3.6-flash-20260721",
     "p": 0.90722,
     "p_star": 0.9051736683417085,
     "y": 2.256079693208503,
     "v": 0.0797011760490503,
     "family_factor": 0.5,
     "w": 1.2318089999505348
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.662,
     "source_value_text": "0.662",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "F83pa7Gfsb4UNVttTnS5Hk",
     "source_model_name": "gemini-3.6-flash_high",
     "p": 0.662,
     "p_star": 0.6618381618381618,
     "y": 0.6714964655080474,
     "v": 0.004459184526629692,
     "family_factor": 1.0,
     "w": 1.6891217695459722
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.72,
     "source_value_text": "0.72",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.6-flash-20260721",
     "source_model_name": "google/gemini-3.6-flash-20260721",
     "p": 0.72,
     "p_star": 0.7156862745098039,
     "y": 0.923163611161917,
     "v": 0.0944733112895607,
     "family_factor": 1.0,
     "w": 3.6360093654892425
    }
   ]
  },
  {
   "slug": "deepseek-v4-flash-0731",
   "name": "DeepSeek V4 Flash 0731",
   "tier": "main",
   "rank": 33,
   "theta": 1.5742719402001175,
   "se": 0.12174725486578784,
   "si_iq": 123.61407910300176,
   "si_iq_low": 120.6102322156766,
   "si_iq_high": 126.61792599032692,
   "si_iq_display": 124,
   "domains": {
    "reasoning": {
     "si_iq": 124.55060271978104,
     "n": 2
    },
    "math": {
     "si_iq": 123.0482463197187,
     "n": 3
    },
    "knowledge": {
     "si_iq": 123.42972501896743,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.32,
     "source_value_text": "0.32",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "Azz52eFkXwVJiRCGpaUBwB",
     "source_model_name": "deepseek-v4-flash-0731_max",
     "p": 0.28451178451178455,
     "p_star": 0.2866453311997867,
     "y": -0.9117330566710832,
     "v": 0.056669428479715706,
     "family_factor": 1.0,
     "w": 4.51336797515731
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.34,
     "source_value_text": "0.34",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-05",
     "source_row_id": "4S4GXbkRhLz8wWP97jYG57",
     "source_model_name": "deepseek-v4-flash-0731_max",
     "p": 0.27296761401189695,
     "p_star": 0.27521545941771974,
     "y": -0.9683201455914322,
     "v": 0.06728064615894949,
     "family_factor": 1.0,
     "w": 4.227068686204482
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.24390243902439024,
     "source_value_text": "0.24390243902439024",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "WYs83xB6NwrkMNyQJtuMcQ",
     "source_model_name": "deepseek-v4-flash-0731_max",
     "p": 0.24390243902439024,
     "p_star": 0.25,
     "y": -1.0986122886681098,
     "v": 0.12396069538926682,
     "family_factor": 1.0,
     "w": 2.2325345933175833
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5754385964912281,
     "source_value_text": "0.5754385964912281",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "mKhVMEicZeGjdvJdTRd7mK",
     "source_model_name": "deepseek-v4-flash-0731_max",
     "p": 0.5754385964912281,
     "p_star": 0.5751748251748252,
     "y": 0.30299630742482353,
     "v": 0.01425944688356036,
     "family_factor": 1.0,
     "w": 4.376005780156984
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9444444444444444,
     "source_value_text": "0.9444444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "FQ3Suh2vKacz7UNqJybTWk",
     "source_model_name": "deepseek-v4-flash-0731_max",
     "p": 0.9443888332777222,
     "p_star": 0.9347282064673369,
     "y": 2.661695807822798,
     "v": 0.34894002930671847,
     "family_factor": 1.0,
     "w": 1.1137345020717613
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9103535353535354,
     "source_value_text": "0.9103535353535354",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "EDFusDaaFkh5n2MqKNxMBD",
     "source_model_name": "deepseek-v4-flash-0731_max",
     "p": 0.8804713804713805,
     "p_star": 0.8785594639865997,
     "y": 1.978858865975723,
     "v": 0.06464236595380321,
     "family_factor": 0.5,
     "w": 1.7533466123525696
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8996633999999999,
     "source_value_text": "0.899663",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-08",
     "source_row_id": "deepseek/deepseek-v4-flash-20260731",
     "source_model_name": "deepseek/deepseek-v4-flash-20260731",
     "p": 0.8662178666666666,
     "p_star": 0.8643775758793969,
     "y": 1.8521349510078395,
     "v": 0.05909796910943851,
     "family_factor": 0.5,
     "w": 1.3505436407716558
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.33633633633633636,
     "source_value_text": "0.33633633633633636",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "TqFmiGvqozt7TSZYmhgF8m",
     "source_model_name": "deepseek-v4-flash-0731_max",
     "p": 0.33633633633633636,
     "p_star": 0.33649983649983656,
     "y": -0.6789314369928978,
     "v": 0.004469983842228909,
     "family_factor": 1.0,
     "w": 1.6890684034961159
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7766665,
     "source_value_text": "0.776667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-08",
     "source_row_id": "deepseek/deepseek-v4-flash-20260731",
     "source_model_name": "deepseek/deepseek-v4-flash-20260731",
     "p": 0.7766665,
     "p_star": 0.7712416666666667,
     "y": 1.215335636826363,
     "v": 0.10895878302919935,
     "family_factor": 1.0,
     "w": 3.383953385140735
    }
   ]
  },
  {
   "slug": "claude-opus-4-6",
   "name": "Claude Opus 4.6",
   "tier": "main",
   "rank": 34,
   "theta": 1.5303082763719629,
   "se": 0.12176840909461413,
   "si_iq": 122.95462414557944,
   "si_iq_low": 119.95025532398576,
   "si_iq_high": 125.95899296717313,
   "si_iq_display": 123,
   "domains": {
    "reasoning": {
     "si_iq": 116.99005391608785,
     "n": 2
    },
    "math": {
     "si_iq": 124.80499640914218,
     "n": 3
    },
    "knowledge": {
     "si_iq": 123.78320754709571,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.21,
     "source_value_text": "0.21",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "aKc2rzsA6YPYwCkE7nhvvB",
     "source_model_name": "claude-opus-4-6_max",
     "p": 0.16877104377104377,
     "p_star": 0.17205053838717205,
     "y": -1.5711638543360564,
     "v": 0.08969178678512194,
     "family_factor": 1.0,
     "w": 3.7276615565203155
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.25,
     "source_value_text": "0.25",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-25",
     "source_row_id": "64rokFyL2L8Vd4SZVdayCy",
     "source_model_name": "claude-opus-4-6_max",
     "p": 0.17382683410442828,
     "p_star": 0.17705627139052307,
     "y": -1.5364202253301036,
     "v": 0.10587112786656308,
     "family_factor": 1.0,
     "w": 3.434705917795642
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2682926829268293,
     "source_value_text": "0.2682926829268293",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "2hbbp8z6PhB7c2T33os9q5",
     "source_model_name": "claude-opus-4-6_max",
     "p": 0.2682926829268293,
     "p_star": 0.27380952380952384,
     "y": -0.9753796482441615,
     "v": 0.11689237348538843,
     "family_factor": 1.0,
     "w": 2.305290831416366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.6596491228070176,
     "source_value_text": "0.6596491228070176",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "kgJ2d6XbKj3dZutDcBYSKU",
     "source_model_name": "claude-opus-4-6_max",
     "p": 0.6596491228070176,
     "p_star": 0.6590909090909092,
     "y": 0.6592456288842643,
     "v": 0.015507039379718427,
     "family_factor": 1.0,
     "w": 4.328740505211093
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9444444444444444,
     "source_value_text": "0.9444444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-06",
     "source_row_id": "TUPC8VdX4jApFa4MGfNP4t",
     "source_model_name": "claude-opus-4-6_64K",
     "p": 0.9443888332777222,
     "p_star": 0.9347282064673369,
     "y": 2.661695807822798,
     "v": 0.34894002930671847,
     "family_factor": 1.0,
     "w": 1.1137345020717613
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7871900826446281,
     "source_value_text": "0.7871900826446281",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-18",
     "source_row_id": "2hH2GAPUFaJR7pfVKhhicg",
     "source_model_name": "claude-opus-4-6",
     "p": 0.7871900826446281,
     "p_star": 0.7865967147052796,
     "y": 1.3045319496557248,
     "v": 0.012282963979401288,
     "family_factor": 1.0,
     "w": 6.297542887416729
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9053030303030303,
     "source_value_text": "0.9053030303030303",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-06",
     "source_row_id": "DiXCMhdfhcjaCUSzYWgACy",
     "source_model_name": "claude-opus-4-6_32K",
     "p": 0.8737373737373737,
     "p_star": 0.871859296482412,
     "y": 1.917499147222533,
     "v": 0.06186365783679448,
     "family_factor": 0.5,
     "w": 1.7834462562676126
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.856643153846154,
     "source_value_text": "0.856643",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.6-opus-20260205",
     "source_model_name": "anthropic/claude-4.6-opus-20260205",
     "p": 0.8088575384615386,
     "p_star": 0.8073054905295711,
     "y": 1.4325960650941605,
     "v": 0.04541110129601412,
     "family_factor": 0.5,
     "w": 1.4429392572342785
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.47,
     "source_value_text": "0.47",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "85fhMxLaebWtLoi6oLpTbi",
     "source_model_name": "claude-opus-4-6_max",
     "p": 0.47,
     "p_star": 0.47002997002997005,
     "y": -0.12002399902860349,
     "v": 0.00400640624358349,
     "family_factor": 1.0,
     "w": 1.691362263681843
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7638095,
     "source_value_text": "0.76381",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.6-opus-20260205",
     "source_model_name": "anthropic/claude-4.6-opus-20260205",
     "p": 0.7638095,
     "p_star": 0.7586367647058824,
     "y": 1.1452200927743834,
     "v": 0.10498437040186419,
     "family_factor": 1.0,
     "w": 3.449564373128991
    }
   ]
  },
  {
   "slug": "gemini-3-flash",
   "name": "Gemini 3 Flash",
   "tier": "main",
   "rank": 35,
   "theta": 1.490404262627794,
   "se": 0.12396678039737048,
   "si_iq": 122.35606393941691,
   "si_iq_low": 119.29745512036087,
   "si_iq_high": 125.41467275847296,
   "si_iq_display": 122,
   "domains": {
    "reasoning": {
     "si_iq": 123.77118303401805,
     "n": 2
    },
    "math": {
     "si_iq": 120.80198987819404,
     "n": 3
    },
    "knowledge": {
     "si_iq": 127.8908687652901,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.39,
     "source_value_text": "0.39",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "UUNZJtgib9XbCjLEdhtGaT",
     "source_model_name": "gemini-3-flash-preview_high",
     "p": 0.3581649831649832,
     "p_star": 0.35956929026235956,
     "y": -0.5772340347312703,
     "v": 0.04874856067162985,
     "family_factor": 1.0,
     "w": 4.753705030783607
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.26,
     "source_value_text": "0.26",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-05",
     "source_row_id": "ZQMcTQjHcDSevCN2dYYHKY",
     "source_model_name": "gemini-3-flash-preview_low",
     "p": 0.18484247631636927,
     "p_star": 0.18796284783798936,
     "y": -1.463301767591175,
     "v": 0.0989296548749219,
     "family_factor": 1.0,
     "w": 3.554556919284581
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.17073170731707318,
     "source_value_text": "0.17073170731707318",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "ZczEhu69FQ9Cnns8NT6ew4",
     "source_model_name": "gemini-3-flash-preview",
     "p": 0.17073170731707318,
     "p_star": 0.1785714285714286,
     "y": -1.5260563034950492,
     "v": 0.1584541062801932,
     "family_factor": 1.0,
     "w": 1.9345794392523366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.512280701754386,
     "source_value_text": "0.512280701754386",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "EtgrDq6ei6kZe8K7QbXUe3",
     "source_model_name": "gemini-3-flash-preview",
     "p": 0.512280701754386,
     "p_star": 0.5122377622377622,
     "y": 0.048960827195701495,
     "v": 0.013945465888656465,
     "family_factor": 1.0,
     "w": 4.3880640278269825
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9555555555555556,
     "source_value_text": "0.9555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "a4uE6KgMhGSUjcnemRnbkA",
     "source_model_name": "gemini-3-flash-preview_high",
     "p": 0.9555110666221778,
     "p_star": 0.9456086521303912,
     "y": 2.8556237017959454,
     "v": 0.4139187345337018,
     "family_factor": 1.0,
     "w": 0.9729164679191334
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7541322314049587,
     "source_value_text": "0.7541322314049587",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-18",
     "source_row_id": "jxoyMNmTnYirjLJN6wRNmG",
     "source_model_name": "gemini-3-flash-preview",
     "p": 0.7541322314049587,
     "p_star": 0.7536071648111468,
     "y": 1.117944077393471,
     "v": 0.011104098709105273,
     "family_factor": 1.0,
     "w": 6.364362695906539
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8939393939393939,
     "source_value_text": "0.8939393939393939",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "gVdraDT3pXmaExP9VbqME4",
     "source_model_name": "gemini-3-flash-preview_high",
     "p": 0.8585858585858586,
     "p_star": 0.8567839195979899,
     "y": 1.7888312094489665,
     "v": 0.05659973412862398,
     "family_factor": 0.5,
     "w": 1.8433947937466364
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8855220000000001,
     "source_value_text": "0.8855220000000001",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3-flash-preview-20251217",
     "source_model_name": "google/gemini-3-flash-preview-20251217",
     "p": 0.8473626666666668,
     "p_star": 0.8456171256281408,
     "y": 1.7006309728277338,
     "v": 0.053395902466005854,
     "family_factor": 0.5,
     "w": 1.3875590897039096
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.668,
     "source_value_text": "0.668",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "7cc6cDCXjsPjtKt36bbeMR",
     "source_model_name": "gemini-3-flash-preview_high",
     "p": 0.668,
     "p_star": 0.6678321678321678,
     "y": 0.6983965364460888,
     "v": 0.004498906203429291,
     "family_factor": 1.0,
     "w": 1.6889254969566034
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7533333333333333,
     "source_value_text": "0.7533333333333333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3-flash-preview-20251217",
     "source_model_name": "google/gemini-3-flash-preview-20251217",
     "p": 0.7533333333333333,
     "p_star": 0.7483660130718954,
     "y": 1.0899165817005558,
     "v": 0.1020813247887484,
     "family_factor": 1.0,
     "w": 3.499119881195069
    }
   ]
  },
  {
   "slug": "kimi-k2-6",
   "name": "Kimi K2.6",
   "tier": "main",
   "rank": 36,
   "theta": 1.4031911225767286,
   "se": 0.12481158912580519,
   "si_iq": 121.04786683865093,
   "si_iq_low": 117.96841421435187,
   "si_iq_high": 124.12731946294998,
   "si_iq_display": 121,
   "domains": {
    "reasoning": {
     "si_iq": 112.69668996978375,
     "n": 2
    },
    "math": {
     "si_iq": 123.34102261935689,
     "n": 3
    },
    "knowledge": {
     "si_iq": 121.89442620419177,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.2,
     "source_value_text": "0.2",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "ehqiuEDETZTqJ8zt6Mc7Ja",
     "source_model_name": "kimi-k2.6",
     "p": 0.15824915824915825,
     "p_star": 0.16163282994966166,
     "y": -1.6461288738575033,
     "v": 0.09570066772788312,
     "family_factor": 1.0,
     "w": 3.61320576672616
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.18,
     "source_value_text": "0.18",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-17",
     "source_row_id": "RA5MRbmWJpFPR29BQxfvZt",
     "source_model_name": "kimi-k2.6",
     "p": 0.09671733862084159,
     "p_star": 0.10071023625825899,
     "y": -2.189357854798553,
     "v": 0.217395934326983,
     "family_factor": 1.0,
     "w": 2.227838181626115
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2564102564102564,
     "source_value_text": "0.2564102564102564",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "eVKA2eavdRAbSN6AnzyBxA",
     "source_model_name": "kimi-k2.6",
     "p": 0.2564102564102564,
     "p_star": 0.26221001221001217,
     "y": -1.034513458719228,
     "v": 0.1201443211477876,
     "family_factor": 1.0,
     "w": 2.2712373291897876
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5719298245614035,
     "source_value_text": "0.5719298245614035",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "BxrNfyMffkVUq4n7U5eK3Q",
     "source_model_name": "kimi-k2.6",
     "p": 0.5719298245614035,
     "p_star": 0.5716783216783217,
     "y": 0.28870196035252643,
     "v": 0.014229545029020782,
     "family_factor": 1.0,
     "w": 4.377151286674316
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9611111111111111,
     "source_value_text": "0.9611111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-05-02",
     "source_row_id": "BTeRdhgt6TFBj6QkGX2j6P",
     "source_model_name": "kimi-k2.6",
     "p": 0.9610721832944056,
     "p_star": 0.9510488749619185,
     "y": 2.966743102329287,
     "v": 0.45728631146678794,
     "family_factor": 1.0,
     "w": 0.8972048832206029
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7665289256198347,
     "source_value_text": "0.7665289256198347",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-05-08",
     "source_row_id": "bUPtAK7spEwvmiC8pi6afc",
     "source_model_name": "kimi-k2.6",
     "p": 0.7665289256198347,
     "p_star": 0.7659782460214466,
     "y": 1.1857396931305404,
     "v": 0.011502274869220038,
     "family_factor": 1.0,
     "w": 6.341635469015374
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9078282828282829,
     "source_value_text": "0.9078282828282829",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-05-01",
     "source_row_id": "LjgJoDosTLkiGVT59smA7q",
     "source_model_name": "kimi-k2.6",
     "p": 0.8771043771043772,
     "p_star": 0.875209380234506,
     "y": 1.9478258584534536,
     "v": 0.06321427666014855,
     "family_factor": 0.5,
     "w": 1.7686880124825362
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8799901428571427,
     "source_value_text": "0.87999",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "moonshotai/kimi-k2.6-20260420",
     "source_model_name": "moonshotai/kimi-k2.6-20260420",
     "p": 0.8399868571428569,
     "p_star": 0.8382783804737973,
     "y": 1.6454737824800032,
     "v": 0.05154637505316347,
     "family_factor": 0.5,
     "w": 1.4000051677838898
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.349,
     "source_value_text": "0.349",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "hHnQVatVTbQjM4sfrjw7GH",
     "source_model_name": "kimi-k2.6",
     "p": 0.349,
     "p_star": 0.34915084915084915,
     "y": -0.6227738348910349,
     "v": 0.004391757987784325,
     "family_factor": 1.0,
     "w": 1.6894550417492968
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7671130223214285,
     "source_value_text": "0.767113",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "moonshotai/kimi-k2.6-20260420",
     "source_model_name": "moonshotai/kimi-k2.6-20260420",
     "p": 0.7671130223214285,
     "p_star": 0.761875512079832,
     "y": 1.1629895769541774,
     "v": 0.10595990937706262,
     "family_factor": 1.0,
     "w": 3.4332253462590456
    }
   ]
  },
  {
   "slug": "gpt-5",
   "name": "GPT-5",
   "tier": "main",
   "rank": 37,
   "theta": 1.3918081475992718,
   "se": 0.11058263683458039,
   "si_iq": 120.87712221398908,
   "si_iq_low": 118.14873782607047,
   "si_iq_high": 123.60550660190768,
   "si_iq_display": 121,
   "domains": {
    "reasoning": {
     "si_iq": 121.58565562299859,
     "n": 2
    },
    "math": {
     "si_iq": 120.64470508876184,
     "n": 4
    },
    "coding": {
     "si_iq": 121.43304606124563,
     "n": 2
    },
    "knowledge": {
     "si_iq": 120.70813257159399,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.36,
     "source_value_text": "0.36",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "CxCwksDLsyrgTJ5ievyAoq",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.3265993265993266,
     "p_star": 0.32831616494982835,
     "y": -0.7158106846108149,
     "v": 0.051519052676884676,
     "family_factor": 1.0,
     "w": 4.6667845970134
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.23,
     "source_value_text": "0.23",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-05",
     "source_row_id": "NKdPCHXg9sphwKW2UEnmkD",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.1517955496805464,
     "p_star": 0.1552431184955905,
     "y": -1.6940564772425524,
     "v": 0.12365401711155612,
     "family_factor": 1.0,
     "w": 3.1616100185397094
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.21951219512195122,
     "source_value_text": "0.21951219512195122",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "mSS7C84hJyYi4VnJtgzYvW",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.21951219512195122,
     "p_star": 0.2261904761904762,
     "y": -1.2299482907291965,
     "v": 0.13279352226720645,
     "family_factor": 1.0,
     "w": 2.1478260869565218
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5543859649122806,
     "source_value_text": "0.5543859649122806",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-10",
     "source_row_id": "QRDHTGX3rYrVCjVPRarjjt",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.5543859649122806,
     "p_star": 0.554195804195804,
     "y": 0.21763822871885394,
     "v": 0.014102802004082387,
     "family_factor": 1.0,
     "w": 4.382013335501708
    },
    {
     "benchmark": "math_level_5",
     "score": 0.9813066465256798,
     "source_value_text": "0.9813066465256798",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-29",
     "source_row_id": "4wN6FKe2db9CLQ3NUFfYge",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.9813066465256798,
     "p_star": 0.9809433962264151,
     "y": 3.9411010615424584,
     "v": 0.04034286867809697,
     "family_factor": 1.0,
     "w": 3.5627032902316182
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9138888888888889,
     "source_value_text": "0.9138888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-29",
     "source_row_id": "3D8aaFBLZwQcnWHYKwvnmq",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.9138026915804693,
     "p_star": 0.9048069808939374,
     "y": 2.2518150297813584,
     "v": 0.24718152508278973,
     "family_factor": 1.0,
     "w": 1.4401687989612026
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.88,
     "source_value_text": "88.0",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-08-23",
     "source_row_id": "2025-08-23-15-47-21--gpt-5-high",
     "source_model_name": "gpt-5 (high)",
     "p": 0.88,
     "p_star": 0.8783185840707964,
     "y": 1.9766030954547193,
     "v": 0.041218227616212494,
     "family_factor": 1.0,
     "w": 1.3669356898635459
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7355371900826446,
     "source_value_text": "0.7355371900826446",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-06",
     "source_row_id": "C85Bnci9xVzq5jmt8zNnbw",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.7355371900826446,
     "p_star": 0.735050542995697,
     "y": 1.0204001833194847,
     "v": 0.010587079418315794,
     "family_factor": 1.0,
     "w": 6.394117512695918
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8617424242424242,
     "source_value_text": "0.8617424242424242",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-29",
     "source_row_id": "9nPyNrZxwtoT7eS4DZbQF6",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.8156565656565656,
     "p_star": 0.8140703517587939,
     "y": 1.4766784225881593,
     "v": 0.04655890458359592,
     "family_factor": 0.5,
     "w": 1.9696867646152139
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8501685000000001,
     "source_value_text": "0.850169",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "openai/gpt-5-2025-08-07",
     "source_model_name": "openai/gpt-5-2025-08-07",
     "p": 0.8002246666666668,
     "p_star": 0.7987160000000001,
     "y": 1.378288592146989,
     "v": 0.04407886139146306,
     "family_factor": 0.5,
     "w": 1.4526124730909475
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.501,
     "source_value_text": "0.501",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "gTLurbyKU63i2opsGkJGwh",
     "source_model_name": "gpt-5-2025-08-07_high",
     "p": 0.501,
     "p_star": 0.500999000999001,
     "y": 0.003996009313381923,
     "v": 0.003992027920243275,
     "family_factor": 1.0,
     "w": 1.6914335096742443
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7066666666666667,
     "source_value_text": "0.706667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5-2025-08-07",
     "source_model_name": "openai/gpt-5-2025-08-07",
     "p": 0.7066666666666667,
     "p_star": 0.7026143790849674,
     "y": 0.8597785216108129,
     "v": 0.09200102223358038,
     "family_factor": 1.0,
     "w": 3.6828282108118726
    }
   ]
  },
  {
   "slug": "glm-5-2",
   "name": "GLM-5.2",
   "tier": "main",
   "rank": 38,
   "theta": 1.3885803011440119,
   "se": 0.12005080996269138,
   "si_iq": 120.82870451716018,
   "si_iq_low": 117.86671369260458,
   "si_iq_high": 123.79069534171578,
   "si_iq_display": 121,
   "domains": {
    "reasoning": {
     "si_iq": 114.19910042558575,
     "n": 2
    },
    "math": {
     "si_iq": 122.65529965675232,
     "n": 3
    },
    "knowledge": {
     "si_iq": 120.64300441104656,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.22,
     "source_value_text": "0.22",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "Hui8iZgjwKPxz7DkRU8sJX",
     "source_model_name": "glm-5.2_max",
     "p": 0.17929292929292928,
     "p_star": 0.18246824682468246,
     "y": -1.499713575938965,
     "v": 0.08451059630927527,
     "family_factor": 1.0,
     "w": 3.8323369786378034
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.19,
     "source_value_text": "0.19",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "7DQNxGG5q6i7VtnzF7vNxA",
     "source_model_name": "glm-5.2_low",
     "p": 0.10773298083278256,
     "p_star": 0.11161681270572531,
     "y": -2.0743314770532617,
     "v": 0.18881924298033745,
     "family_factor": 1.0,
     "w": 2.4482675527083444
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2926829268292683,
     "source_value_text": "0.2926829268292683",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-19",
     "source_row_id": "JebA8dYLVov6H49ZQSLXh5",
     "source_model_name": "glm-5.2_max",
     "p": 0.2926829268292683,
     "p_star": 0.2976190476190476,
     "y": -0.8586616190375186,
     "v": 0.11118644067796613,
     "family_factor": 1.0,
     "w": 2.367576243980738
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.592057761732852,
     "source_value_text": "0.592057761732852",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-19",
     "source_row_id": "TTuCPacMDpNaCSs3Hpbdjp",
     "source_model_name": "glm-5.2_max",
     "p": 0.592057761732852,
     "p_star": 0.5917358814470727,
     "y": 0.3711460747685529,
     "v": 0.01442260391363861,
     "family_factor": 1.0,
     "w": 4.369765963177861
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8638888888888889,
     "source_value_text": "0.8638888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-25",
     "source_row_id": "XjFqou6MyT2XLpkUsCrgxM",
     "source_model_name": "glm-5.2_max",
     "p": 0.8637526415304193,
     "p_star": 0.8558449754101928,
     "y": 1.7811999760950923,
     "v": 0.17257568940490417,
     "family_factor": 1.0,
     "w": 1.834352876779348
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.787,
     "source_value_text": "0.787",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-25",
     "source_row_id": "4AfhcmYVNrw6gM5u8CQsyy",
     "source_model_name": "glm-5.2_max",
     "p": 0.787,
     "p_star": 0.7864070247933885,
     "y": 1.3034022827075145,
     "v": 0.01227501574768315,
     "family_factor": 1.0,
     "w": 6.297988706371114
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9185606060606061,
     "source_value_text": "0.9185606060606061",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-24",
     "source_row_id": "c5kpB4axzmygRywWqBKFmv",
     "source_model_name": "glm-5.2_max",
     "p": 0.8914141414141414,
     "p_star": 0.8894472361809045,
     "y": 2.085107279215513,
     "v": 0.06990328449679213,
     "family_factor": 0.5,
     "w": 1.6990556448028127
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8334862727272728,
     "source_value_text": "0.833486",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5.2-20260616",
     "source_model_name": "z-ai/glm-5.2-20260616",
     "p": 0.7779816969696971,
     "p_star": 0.7765848040201007,
     "y": 1.2458739440692734,
     "v": 0.04118693746874177,
     "family_factor": 0.5,
     "w": 1.4740632674719267
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.342,
     "source_value_text": "0.342",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "WgjFZzojpiv54XqUhvfuUG",
     "source_model_name": "glm-5.2_max",
     "p": 0.342,
     "p_star": 0.3421578421578422,
     "y": -0.6536928634810556,
     "v": 0.004433877037505058,
     "family_factor": 1.0,
     "w": 1.6892468426019376
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7169697272727272,
     "source_value_text": "0.71697",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5.2-20260616",
     "source_model_name": "z-ai/glm-5.2-20260616",
     "p": 0.7169697272727272,
     "p_star": 0.7127154188948306,
     "y": 0.9086089124830556,
     "v": 0.09388607431849048,
     "family_factor": 1.0,
     "w": 3.647022013685241
    }
   ]
  },
  {
   "slug": "glm-5-3-flash",
   "name": "GLM-5.3-Flash",
   "tier": "main",
   "rank": 39,
   "theta": 1.365667300836018,
   "se": 0.13452219817590383,
   "si_iq": 120.48500951254027,
   "si_iq_low": 117.16596887616384,
   "si_iq_high": 123.80405014891669,
   "si_iq_display": 120,
   "domains": {
    "reasoning": {
     "si_iq": 114.23334139377525,
     "n": 2
    },
    "math": {
     "si_iq": 121.2598111298445,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.21,
     "source_value_text": "0.21",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "fWNxmiSUC7BX8whqvzssY8",
     "source_model_name": "glm-5.3-flash_max",
     "p": 0.16877104377104377,
     "p_star": 0.17205053838717205,
     "y": -1.5711638543360564,
     "v": 0.08969178678512194,
     "family_factor": 1.0,
     "w": 3.7276615565203155
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.08,
     "source_value_text": "0.08",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "TMM3rPrAHcpBG5Pvw9kr4L",
     "source_model_name": "glm-5.3-flash_max",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.17073170731707318,
     "source_value_text": "0.17073170731707318",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "iCysWvFJevNyw2dbYosU6J",
     "source_model_name": "glm-5.3-flash_max",
     "p": 0.17073170731707318,
     "p_star": 0.1785714285714286,
     "y": -1.5260563034950492,
     "v": 0.1584541062801932,
     "family_factor": 1.0,
     "w": 1.9345794392523366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5578947368421052,
     "source_value_text": "0.5578947368421052",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "YC2u9wykbYQg4gdkf76j26",
     "source_model_name": "glm-5.3-flash_max",
     "p": 0.5578947368421052,
     "p_star": 0.5576923076923077,
     "y": 0.23180161405732438,
     "v": 0.014125168820548404,
     "family_factor": 1.0,
     "w": 4.381154526800351
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9388888888888889,
     "source_value_text": "0.9388888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-26",
     "source_row_id": "NCikvVWc5SEyMEbCqvVNb2",
     "source_model_name": "glm-5.3-flash_max",
     "p": 0.9388277166054944,
     "p_star": 0.9292879836358097,
     "y": 2.575803162746415,
     "v": 0.3239819870611169,
     "family_factor": 1.0,
     "w": 1.1792953834331767
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9015151515151515,
     "source_value_text": "0.9015151515151515",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-26",
     "source_row_id": "Jvt5BNr4ERbE9QGgMcEbmT",
     "source_model_name": "glm-5.3-flash_max",
     "p": 0.8686868686868686,
     "p_star": 0.8668341708542714,
     "y": 1.8732525034792382,
     "v": 0.059970277371568556,
     "family_factor": 0.5,
     "w": 1.8045548169195025
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9090909999999999,
     "source_value_text": "0.909091",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "z-ai/glm-5.3-flash",
     "source_model_name": "z-ai/glm-5.3-flash",
     "p": 0.8787879999999998,
     "p_star": 0.8768845427135676,
     "y": 1.9632527412199223,
     "v": 0.06391829609935486,
     "family_factor": 0.5,
     "w": 1.3207585333636587
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.762499875,
     "source_value_text": "0.7625",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5.3-flash-20260826",
     "source_model_name": "z-ai/glm-5.3-flash-20260826",
     "p": 0.762499875,
     "p_star": 0.757352818627451,
     "y": 1.1382207599004672,
     "v": 0.10460589394391735,
     "family_factor": 1.0,
     "w": 3.4559453178820254
    }
   ]
  },
  {
   "slug": "gpt-5-1",
   "name": "GPT-5.1",
   "tier": "main",
   "rank": 40,
   "theta": 1.3454644209047697,
   "se": 0.19371356225735886,
   "si_iq": 120.18196631357155,
   "si_iq_low": 115.40250839757256,
   "si_iq_high": 124.96142422957053,
   "si_iq_display": 120,
   "domains": {
    "reasoning": {
     "si_iq": 122.49793813679982,
     "n": 2
    },
    "knowledge": {
     "si_iq": 121.70563834763404,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.42,
     "source_value_text": "0.42",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "HKQxqBGokn83tHr5wGJiZX",
     "source_model_name": "gpt-5.1-2025-11-13_high",
     "p": 0.3897306397306397,
     "p_star": 0.39082241557489084,
     "y": -0.4438565485451298,
     "v": 0.046673340679655534,
     "family_factor": 1.0,
     "w": 4.820963222832132
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.19,
     "source_value_text": "0.19",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "iV2bSueom3C2SKw72ogiYr",
     "source_model_name": "gpt-5.1-2025-11-13_low",
     "p": 0.10773298083278256,
     "p_star": 0.11161681270572531,
     "y": -2.0743314770532617,
     "v": 0.18881924298033745,
     "family_factor": 1.0,
     "w": 2.4482675527083444
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8861111111111111,
     "source_value_text": "0.8861111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-11-13",
     "source_row_id": "mYKKTdV27TRJv9FpUg7rkn",
     "source_model_name": "gpt-5.1-2025-11-13_high",
     "p": 0.8859971082193304,
     "p_star": 0.8776058667363015,
     "y": 1.969951155838861,
     "v": 0.1982128505404483,
     "family_factor": 1.0,
     "w": 1.6766547755868157
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.6797520661157025,
     "source_value_text": "0.6797520661157025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-18",
     "source_row_id": "YoHtZpMNdsRE6qdj2K4Ucj",
     "source_model_name": "gpt-5.1-2025-11-13_high",
     "p": 0.6797520661157025,
     "p_star": 0.6793806775493477,
     "y": 0.7509271068469138,
     "v": 0.009465717186751427,
     "family_factor": 1.0,
     "w": 6.459618585243492
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8762626262626263,
     "source_value_text": "0.8762626262626263",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-11-13",
     "source_row_id": "CSVtMksEVjBNsGJGjW4GcQ",
     "source_model_name": "gpt-5.1-2025-11-13_high",
     "p": 0.8350168350168351,
     "p_star": 0.8333333333333334,
     "y": 1.6094379124341007,
     "v": 0.05039872730486606,
     "family_factor": 0.5,
     "w": 1.919398785932898
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8692479999999999,
     "source_value_text": "0.869248",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "openai/gpt-5.1-20251113",
     "source_model_name": "openai/gpt-5.1-20251113",
     "p": 0.8256639999999998,
     "p_star": 0.824027497487437,
     "y": 1.5438761529818559,
     "v": 0.048428341817573835,
     "family_factor": 0.5,
     "w": 1.4215006938350545
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.48,
     "source_value_text": "0.48",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "QCLnRy69NBH9ip3VYtQneh",
     "source_model_name": "gpt-5.1-2025-11-13_high",
     "p": 0.48,
     "p_star": 0.48001998001998003,
     "y": -0.07996265964467637,
     "v": 0.003998396642946179,
     "family_factor": 1.0,
     "w": 1.6914019512925296
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7583332500000001,
     "source_value_text": "0.758333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.1-20251113",
     "source_model_name": "openai/gpt-5.1-20251113",
     "p": 0.7583332500000001,
     "p_star": 0.7532678921568627,
     "y": 1.1161177665960755,
     "v": 0.10343190583105714,
     "family_factor": 1.0,
     "w": 3.475889282449992
    }
   ]
  },
  {
   "slug": "kimi-k2-5",
   "name": "Kimi K2.5",
   "tier": "main",
   "rank": 41,
   "theta": 1.2544330184919739,
   "se": 0.2687933660335299,
   "si_iq": 118.8164952773796,
   "si_iq_low": 112.18460762797388,
   "si_iq_high": 125.44838292678534,
   "si_iq_display": 119,
   "domains": {
    "knowledge": {
     "si_iq": 118.23748691132599,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.922,
     "source_value_text": "0.922",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-02",
     "source_row_id": "mbfZvrSNoXSJqCyD4VKqLe",
     "source_model_name": "fireworks/kimi-k2p5",
     "p": 0.921921921921922,
     "p_star": 0.9127497062279673,
     "y": 2.3476807705903497,
     "v": 0.2673340482193399,
     "family_factor": 1.0,
     "w": 1.361158875480673
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.737603305785124,
     "source_value_text": "0.737603305785124",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-17",
     "source_row_id": "5wVjUb3yn6bdjPSfPEMuiZ",
     "source_model_name": "kimi-k2.5",
     "p": 0.737603305785124,
     "p_star": 0.7371123898640803,
     "y": 1.0310137740297143,
     "v": 0.010640268272991525,
     "family_factor": 1.0,
     "w": 6.39104362474833
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.876,
     "source_value_text": "0.876",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-02",
     "source_row_id": "FmqGUq87N4JcuSbo6Uu3U5",
     "source_model_name": "fireworks/kimi-k2p5",
     "p": 0.8346666666666667,
     "p_star": 0.8329849246231156,
     "y": 1.6069314642513601,
     "v": 0.050320639837327916,
     "family_factor": 0.5,
     "w": 1.9203958611885084
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8592592,
     "source_value_text": "0.859259",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-29",
     "source_row_id": "moonshotai/kimi-k2.5-0127",
     "source_model_name": "moonshotai/kimi-k2.5-0127",
     "p": 0.8123456,
     "p_star": 0.810776024120603,
     "y": 1.4550604724989606,
     "v": 0.04598843352472318,
     "family_factor": 0.5,
     "w": 1.438787221846683
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.343,
     "source_value_text": "0.343",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "RbXXg4JEbTSBnzw3CMSHnD",
     "source_model_name": "kimi-k2.5",
     "p": 0.343,
     "p_star": 0.34315684315684314,
     "y": -0.6492576523895156,
     "v": 0.004427693005905435,
     "family_factor": 1.0,
     "w": 1.6892774077438966
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7277775,
     "source_value_text": "0.727777",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-29",
     "source_row_id": "moonshotai/kimi-k2.5-0127",
     "source_model_name": "moonshotai/kimi-k2.5-0127",
     "p": 0.7277775,
     "p_star": 0.7233112745098039,
     "y": 0.9609465217003182,
     "v": 0.09605344698396551,
     "family_factor": 1.0,
     "w": 3.6067041516713507
    }
   ]
  },
  {
   "slug": "kimi-k2-7-code",
   "name": "Kimi K2.7 Code",
   "tier": "main",
   "rank": 42,
   "theta": 1.230916637989814,
   "se": 0.13968436598248374,
   "si_iq": 118.46374956984721,
   "si_iq_low": 115.01734374799092,
   "si_iq_high": 121.9101553917035,
   "si_iq_display": 118,
   "domains": {
    "math": {
     "si_iq": 120.16757516135752,
     "n": 3
    },
    "knowledge": {
     "si_iq": 119.73833334281318,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.14,
     "source_value_text": "0.14",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "bSyTSKD8RiRNZCGNu6MnFp",
     "source_model_name": "kimi-k2.7-code",
     "p": 0.09511784511784513,
     "p_star": 0.09912657932459913,
     "y": -2.206967147657535,
     "v": 0.167569741192018,
     "family_factor": 1.0,
     "w": 2.6427008451568565
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.12195121951219512,
     "source_value_text": "0.12195121951219512",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-13",
     "source_row_id": "UTVSgirxQpTgmTHbgE9EUk",
     "source_model_name": "kimi-k2.7-code",
     "p": 0.12195121951219512,
     "p_star": 0.13095238095238096,
     "y": -1.8925641683500207,
     "v": 0.20423412204234123,
     "family_factor": 1.0,
     "w": 1.643471142038477
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5403508771929825,
     "source_value_text": "0.5403508771929825",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-13",
     "source_row_id": "X3RxRkt2pBUXYJjAQHsUo6",
     "source_model_name": "kimi-k2.7-code",
     "p": 0.5403508771929825,
     "p_star": 0.5402097902097902,
     "y": 0.16118724471998086,
     "v": 0.014027834176233895,
     "family_factor": 1.0,
     "w": 4.38489429894137
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9555555555555556,
     "source_value_text": "0.9555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "ENc5ZM5TpBYNKkTWN4xyQM",
     "source_model_name": "kimi-k2.7-code",
     "p": 0.9555110666221778,
     "p_star": 0.9456086521303912,
     "y": 2.8556237017959454,
     "v": 0.4139187345337018,
     "family_factor": 1.0,
     "w": 0.9729164679191334
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8787878787878788,
     "source_value_text": "0.8787878787878788",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "XneEig6pACkAWeekvgCwNk",
     "source_model_name": "kimi-k2.7-code",
     "p": 0.8383838383838383,
     "p_star": 0.8366834170854272,
     "y": 1.633755220084807,
     "v": 0.05116800792476471,
     "family_factor": 0.5,
     "w": 1.9096311353026798
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8847767229341582,
     "source_value_text": "0.884777",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "moonshotai/kimi-k2.7-code-20260612",
     "source_model_name": "moonshotai/kimi-k2.7-code-20260612",
     "p": 0.846368963912211,
     "p_star": 0.8446284163548632,
     "y": 1.6930772248963832,
     "v": 0.05313580401018531,
     "family_factor": 0.5,
     "w": 1.3892959891055257
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.365,
     "source_value_text": "0.365",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "5AijYw5bFJtSuahnbzNo6Z",
     "source_model_name": "kimi-k2.7-code",
     "p": 0.365,
     "p_star": 0.36513486513486515,
     "y": -0.5531458114396754,
     "v": 0.004305236997915189,
     "family_factor": 1.0,
     "w": 1.6898828856584482
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7383231627502177,
     "source_value_text": "0.738323",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "moonshotai/kimi-k2.7-code-20260612",
     "source_model_name": "moonshotai/kimi-k2.7-code-20260612",
     "p": 0.7383231627502177,
     "p_star": 0.7336501595590369,
     "y": 1.0132216588349832,
     "v": 0.09837578137046903,
     "family_factor": 1.0,
     "w": 3.56448139133485
    }
   ]
  },
  {
   "slug": "inkling-small",
   "name": "Inkling-Small",
   "tier": "main",
   "rank": 43,
   "theta": 1.2076673492799355,
   "se": 0.13727487323857465,
   "si_iq": 118.11501023919902,
   "si_iq_low": 114.72805337400959,
   "si_iq_high": 121.50196710438847,
   "si_iq_display": 118,
   "domains": {
    "math": {
     "si_iq": 118.97661828902864,
     "n": 3
    },
    "knowledge": {
     "si_iq": 115.28349376924741,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.06,
     "source_value_text": "0.06",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-15",
     "source_row_id": "nPFA9ufjfVqg3YNmDRqWeC",
     "source_model_name": "inkling-small_xhigh",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.17073170731707318,
     "source_value_text": "0.17073170731707318",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "DVD8G8DHNyzkowBzK7JvMt",
     "source_model_name": "inkling-small_xhigh",
     "p": 0.17073170731707318,
     "p_star": 0.1785714285714286,
     "y": -1.5260563034950492,
     "v": 0.1584541062801932,
     "family_factor": 1.0,
     "w": 1.9345794392523366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.4631578947368421,
     "source_value_text": "0.4631578947368421",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "B6bZbqickq8o2fQcgDmzMo",
     "source_model_name": "inkling-small_xhigh",
     "p": 0.4631578947368421,
     "p_star": 0.4632867132867133,
     "y": -0.1471179216009749,
     "v": 0.014012660561735602,
     "family_factor": 1.0,
     "w": 4.38547787181284
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9,
     "source_value_text": "0.9",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "53BDFebxiT9KGeP5FRt6bJ",
     "source_model_name": "inkling-small_xhigh",
     "p": 0.8998998998998999,
     "p_star": 0.8912064238151195,
     "y": 2.103123786937726,
     "v": 0.2195850729832484,
     "family_factor": 1.0,
     "w": 1.564528641255433
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.88510101010101,
     "source_value_text": "0.88510101010101",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-14",
     "source_row_id": "jTHw5SET8usd7emYPjEDjS",
     "source_model_name": "inkling-small_xhigh",
     "p": 0.8468013468013468,
     "p_star": 0.8450586264656615,
     "y": 1.6963591952752834,
     "v": 0.05324854282687694,
     "family_factor": 0.5,
     "w": 1.8837055757256094
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8703701666666666,
     "source_value_text": "0.87037",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-09-19",
     "source_row_id": "thinkingmachines/inkling-small-20260730",
     "source_model_name": "thinkingmachines/inkling-small-20260730",
     "p": 0.8271602222222221,
     "p_star": 0.825516201005025,
     "y": 1.554176993958411,
     "v": 0.04872813367417466,
     "family_factor": 0.5,
     "w": 1.4194053082312732
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.191,
     "source_value_text": "0.191",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "eJfbDKqeg9kNXFoxpeV7HG",
     "source_model_name": "inkling-small_xhigh",
     "p": 0.191,
     "p_star": 0.1913086913086913,
     "y": -1.441528964496989,
     "v": 0.006450811754024096,
     "family_factor": 1.0,
     "w": 1.6793366215129268
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6076188571428572,
     "source_value_text": "0.6076188571428572",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-08",
     "source_row_id": "thinkingmachines/inkling-small-20260730",
     "source_model_name": "thinkingmachines/inkling-small-20260730",
     "p": 0.6076188571428572,
     "p_star": 0.6055086834733895,
     "y": 0.4284717751825447,
     "v": 0.08047700925647226,
     "family_factor": 1.0,
     "w": 3.917988136548142
    }
   ]
  },
  {
   "slug": "gpt-5-4-nano",
   "name": "GPT-5.4 Nano",
   "tier": "main",
   "rank": 44,
   "theta": 1.2032295137975064,
   "se": 0.13148853820688375,
   "si_iq": 118.04844270696259,
   "si_iq_low": 114.8042509866064,
   "si_iq_high": 121.29263442731877,
   "si_iq_display": 118,
   "domains": {
    "reasoning": {
     "si_iq": 128.52173979929478,
     "n": 2
    },
    "math": {
     "si_iq": 117.3301560393303,
     "n": 3
    },
    "knowledge": {
     "si_iq": 104.60466785444316,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.45,
     "source_value_text": "0.45",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "MeFyTsrHFWVrQJ8QHRjnRw",
     "source_model_name": "gpt-5.4-nano-2026-03-17_xhigh",
     "p": 0.42129629629629634,
     "p_star": 0.4220755408874221,
     "y": -0.3142588616959415,
     "v": 0.04515710075908147,
     "family_factor": 1.0,
     "w": 4.871320641489932
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.09,
     "source_value_text": "0.09",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "fxNDgLaScEoHo2canW89yv",
     "source_model_name": "gpt-5.4-nano-2026-03-17_none",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.12195121951219512,
     "source_value_text": "0.12195121951219512",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "SF6FYnnKztPCDWQc4v4EJa",
     "source_model_name": "gpt-5.4-nano-2026-03-17_high",
     "p": 0.12195121951219512,
     "p_star": 0.13095238095238096,
     "y": -1.8925641683500207,
     "v": 0.20423412204234123,
     "family_factor": 1.0,
     "w": 1.643471142038477
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.44912280701754387,
     "source_value_text": "0.44912280701754387",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "iKtopjTjyCWZqJaEjcc7ZL",
     "source_model_name": "gpt-5.4-nano-2026-03-17_high",
     "p": 0.44912280701754387,
     "p_star": 0.4493006993006993,
     "y": -0.203496553930413,
     "v": 0.014081897350379843,
     "family_factor": 1.0,
     "w": 4.382816306642845
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8778,
     "source_value_text": "0.8778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-14",
     "source_row_id": "jVv9m8DjkdpZaLPdUzAnG9",
     "source_model_name": "gpt-5.4-nano-2026-03-17_high",
     "p": 0.8776776776776777,
     "p_star": 0.8694672933803369,
     "y": 1.8962568968536184,
     "v": 0.18759616874026874,
     "family_factor": 1.0,
     "w": 1.7385488902376705
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7847,
     "source_value_text": "0.7847",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-14",
     "source_row_id": "fZB3qGSohAVYzN97mniuUp",
     "source_model_name": "gpt-5.4-nano-2026-03-17_high",
     "p": 0.7129333333333333,
     "p_star": 0.7118633165829146,
     "y": 0.9044509591422769,
     "v": 0.035790294027296686,
     "family_factor": 0.5,
     "w": 2.125889310886853
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.77567325,
     "source_value_text": "0.775673",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.4-nano-20260317",
     "source_model_name": "openai/gpt-5.4-nano-20260317",
     "p": 0.7008976666666666,
     "p_star": 0.6998881306532664,
     "y": 0.8467652059498807,
     "v": 0.03514083106770129,
     "family_factor": 0.5,
     "w": 1.5210221854592894
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.117,
     "source_value_text": "0.117",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "3QBsxKkbF2R2LEXTd6HDrJ",
     "source_model_name": "gpt-5.4-nano-2026-03-17_high",
     "p": 0.117,
     "p_star": 0.11738261738261738,
     "y": -2.0174529581755376,
     "v": 0.009632867343375595,
     "family_factor": 1.0,
     "w": 1.6639358412274217
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.65166675,
     "source_value_text": "0.651667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.4-nano-20260317",
     "source_model_name": "openai/gpt-5.4-nano-20260317",
     "p": 0.65166675,
     "p_star": 0.6486928921568628,
     "y": 0.6132986110622707,
     "v": 0.08435359109153404,
     "family_factor": 1.0,
     "w": 3.8356007984431364
    }
   ]
  },
  {
   "slug": "gpt-5-4-mini",
   "name": "GPT-5.4 Mini",
   "tier": "main",
   "rank": 45,
   "theta": 1.1092573345949561,
   "se": 0.1355773588299311,
   "si_iq": 116.63886001892433,
   "si_iq_low": 113.29378560421162,
   "si_iq_high": 119.98393443363706,
   "si_iq_display": 117,
   "domains": {
    "reasoning": {
     "si_iq": 113.57824960519972,
     "n": 2
    },
    "math": {
     "si_iq": 118.01782836130818,
     "n": 3
    },
    "knowledge": {
     "si_iq": 115.45624703311253,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.23,
     "source_value_text": "0.23",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "fzgzPmgay5wxMGHjevRjrm",
     "source_model_name": "gpt-5.4-mini-2026-03-17_high",
     "p": 0.18981481481481483,
     "p_star": 0.19288595526219288,
     "y": -1.4313658687887518,
     "v": 0.08000539502370328,
     "family_factor": 1.0,
     "w": 3.9282532675947572
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.11,
     "source_value_text": "0.11",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "NEysw7ag6KJxUahem2PHQv",
     "source_model_name": "gpt-5.4-mini-2026-03-17_none",
     "p": 0.019607843137254898,
     "p_star": 0.02436420112599495,
     "y": -3.689974471892956,
     "v": 2.131517661466075,
     "family_factor": 1.0,
     "w": 0.31687259007485896
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.0975609756097561,
     "source_value_text": "0.0975609756097561",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "jtQ6rDiNxjNKkVMEPBE3Ub",
     "source_model_name": "gpt-5.4-mini-2026-03-17_xhigh",
     "p": 0.0975609756097561,
     "p_star": 0.10714285714285714,
     "y": -2.120263536200091,
     "v": 0.24296296296296296,
     "family_factor": 1.0,
     "w": 1.4578833693304536
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.512280701754386,
     "source_value_text": "0.512280701754386",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "jjFRrQvsud3XsgYufr9f8f",
     "source_model_name": "gpt-5.4-mini-2026-03-17_xhigh",
     "p": 0.512280701754386,
     "p_star": 0.5122377622377622,
     "y": 0.048960827195701495,
     "v": 0.013945465888656465,
     "family_factor": 1.0,
     "w": 4.3880640278269825
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8888888888888888,
     "source_value_text": "0.8888888888888888",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "QGMk6JNCYuUkFMF4zdVCsM",
     "source_model_name": "gpt-5.4-mini-2026-03-17_xhigh",
     "p": 0.8887776665554443,
     "p_star": 0.8803259781520651,
     "y": 1.995520706756699,
     "v": 0.2020910093434368,
     "family_factor": 1.0,
     "w": 1.6551303565329458
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8686868686868687,
     "source_value_text": "0.8686868686868687",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "gKB2rCD7mHzFN2MCt2YCni",
     "source_model_name": "gpt-5.4-mini-2026-03-17_xhigh",
     "p": 0.8249158249158249,
     "p_star": 0.8232830820770519,
     "y": 1.5387509866711,
     "v": 0.048280513293592904,
     "family_factor": 0.5,
     "w": 1.9468177455202158
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.84048825,
     "source_value_text": "0.840488",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.4-mini-20260317",
     "source_model_name": "openai/gpt-5.4-mini-20260317",
     "p": 0.7873176666666667,
     "p_star": 0.7858738592964825,
     "y": 1.3002310112859594,
     "v": 0.04231498141034806,
     "family_factor": 0.5,
     "w": 1.4656210901436102
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.294,
     "source_value_text": "0.294",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "Z3pjKgAULY9j9wmzQpdqZG",
     "source_model_name": "gpt-5.4-mini-2026-03-17_high",
     "p": 0.294,
     "p_star": 0.2942057942057942,
     "y": -0.875044199032941,
     "v": 0.004806207697862559,
     "family_factor": 1.0,
     "w": 1.6874086001049606
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6216667499999999,
     "source_value_text": "0.621667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.4-mini-20260317",
     "source_model_name": "openai/gpt-5.4-mini-20260317",
     "p": 0.6216667499999999,
     "p_star": 0.6192811274509803,
     "y": 0.4864980980351358,
     "v": 0.08153374698717605,
     "family_factor": 1.0,
     "w": 3.895180884667681
    }
   ]
  },
  {
   "slug": "deepseek-v4-pro",
   "name": "DeepSeek-V4-Pro",
   "tier": "main",
   "rank": 46,
   "theta": 1.1037614651142722,
   "se": 0.14716450139177356,
   "si_iq": 116.55642197671409,
   "si_iq_low": 112.92546019513011,
   "si_iq_high": 120.18738375829804,
   "si_iq_display": 117,
   "domains": {
    "reasoning": {
     "si_iq": 111.05022835085083,
     "n": 2
    },
    "math": {
     "si_iq": 116.66693207557182,
     "n": 3
    },
    "knowledge": {
     "si_iq": 122.00700262736905,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.19,
     "source_value_text": "0.19",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "DSyqeLiA9LLZF4iaxsTVHL",
     "source_model_name": "deepseek-v4-pro_max",
     "p": 0.1477272727272727,
     "p_star": 0.1512151215121512,
     "y": -1.7251023032301986,
     "v": 0.10273725684322144,
     "family_factor": 1.0,
     "w": 3.48779889891358
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.17,
     "source_value_text": "0.17",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "BmvJaHMCnZzb24ErpAsozU",
     "source_model_name": "deepseek-v4-pro_none",
     "p": 0.08570169640890066,
     "p_star": 0.08980365981079273,
     "y": -2.316034605079059,
     "v": 0.25556603990154425,
     "family_factor": 1.0,
     "w": 1.9886791814604803
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.024390243902439025,
     "source_value_text": "0.024390243902439025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-17",
     "source_row_id": "RAZ6VMfGtQSE8EvUZRRz4Q",
     "source_model_name": "deepseek-v4-pro_max",
     "p": 0.024390243902439025,
     "p_star": 0.03571428571428571,
     "y": -3.295836866004329,
     "v": 0.6748971193415636,
     "family_factor": 1.0,
     "w": 0.6452469463621882
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.45263157894736844,
     "source_value_text": "0.45263157894736844",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-17",
     "source_row_id": "KUar3FaFjzq5SMKrEhtn8e",
     "source_model_name": "deepseek-v4-pro_max",
     "p": 0.45263157894736844,
     "p_star": 0.4527972027972028,
     "y": -0.18937512884061536,
     "v": 0.014062442177458154,
     "family_factor": 1.0,
     "w": 4.38356386602788
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9666666666666667,
     "source_value_text": "0.9666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-17",
     "source_row_id": "HjTDENSpy9sancDzr7pccY",
     "source_model_name": "deepseek-v4-pro_max",
     "p": 0.9666332999666333,
     "p_star": 0.9564890977934456,
     "y": 3.090257858663544,
     "v": 0.5115322331585972,
     "family_factor": 1.0,
     "w": 0.8176183901500546
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7763975155279503,
     "source_value_text": "0.7763975155279503",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-18",
     "source_row_id": "WUk3f44JhxtAJaSxi6gFZR",
     "source_model_name": "deepseek-v4-pro_max",
     "p": 0.7763975155279503,
     "p_star": 0.7758264462809917,
     "y": 1.2415082982236751,
     "v": 0.011855160860787767,
     "family_factor": 1.0,
     "w": 6.321628575248266
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9090909090909091,
     "source_value_text": "0.9090909090909091",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "TPdRwHTJtaJYSu2Cxc5Czn",
     "source_model_name": "deepseek-v4-pro_high",
     "p": 0.8787878787878788,
     "p_star": 0.8768844221105527,
     "y": 1.9632516240918003,
     "v": 0.06391824469790049,
     "family_factor": 0.5,
     "w": 1.7610921537552942
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.853535,
     "source_value_text": "0.853535",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-08",
     "source_row_id": "deepseek/deepseek-v4-pro-20260423",
     "source_model_name": "deepseek/deepseek-v4-pro-20260423",
     "p": 0.8047133333333334,
     "p_star": 0.8031821105527639,
     "y": 1.4063025938216192,
     "v": 0.04475501995922527,
     "family_factor": 0.5,
     "w": 1.4476868228671191
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.46993987975951906,
     "source_value_text": "0.46993987975951906",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "Sq9xqkVTmFvELpQy9KH5TM",
     "source_model_name": "deepseek-v4-pro_max",
     "p": 0.46993987975951906,
     "p_star": 0.46996990984966935,
     "y": -0.12026510774495462,
     "v": 0.004006464202886893,
     "family_factor": 1.0,
     "w": 1.691361976499996
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.788889,
     "source_value_text": "0.788889",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-08",
     "source_row_id": "deepseek/deepseek-v4-pro-20260423",
     "source_model_name": "deepseek/deepseek-v4-pro-20260423",
     "p": 0.788889,
     "p_star": 0.7832245098039214,
     "y": 1.2845571745912914,
     "v": 0.11322262136536254,
     "family_factor": 1.0,
     "w": 3.3162840633822874
    }
   ]
  },
  {
   "slug": "o3",
   "name": "o3",
   "tier": "main",
   "rank": 47,
   "theta": 1.0608382352456531,
   "se": 0.1262032223300013,
   "si_iq": 115.9125735286848,
   "si_iq_low": 112.79878540274892,
   "si_iq_high": 119.02636165462067,
   "si_iq_display": 116,
   "domains": {
    "reasoning": {
     "si_iq": 123.64450587467311,
     "n": 2
    },
    "math": {
     "si_iq": 112.8931550978743,
     "n": 3
    },
    "coding": {
     "si_iq": 111.35675159183283,
     "n": 2
    },
    "knowledge": {
     "si_iq": 114.27302246327949,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.37,
     "source_value_text": "0.37",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "MiKNm9AZG7MxP6hibnYN8a",
     "source_model_name": "o3-2025-04-16_medium",
     "p": 0.33712121212121215,
     "p_star": 0.3387338733873388,
     "y": -0.6689416061231427,
     "v": 0.050507317607186304,
     "family_factor": 1.0,
     "w": 4.698155494552413
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.29,
     "source_value_text": "0.29",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "FmLdgAHVM7MPn3JebBvxTb",
     "source_model_name": "o3-2025-04-16_high",
     "p": 0.2178894029521921,
     "p_star": 0.22068257718038825,
     "y": -1.2616930709162055,
     "v": 0.08323296845406493,
     "family_factor": 1.0,
     "w": 3.8590587008025987
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.3333333333333333,
     "source_value_text": "0.3333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "N4HerYebFnJDEU4PEvNNGM",
     "source_model_name": "o3-2025-04-16_high",
     "p": 0.3333333333333333,
     "p_star": 0.3339160839160839,
     "y": -0.690525947080071,
     "v": 0.015665581069382036,
     "family_factor": 1.0,
     "w": 4.322807142602558
    },
    {
     "benchmark": "math_level_5",
     "score": 0.9777190332326284,
     "source_value_text": "0.9777190332326284",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-16",
     "source_row_id": "6oW3GceNQznewQJRwLigth",
     "source_model_name": "o3-2025-04-16_high",
     "p": 0.9777190332326284,
     "p_star": 0.9773584905660377,
     "y": 3.765068592471483,
     "v": 0.03407979407979409,
     "family_factor": 1.0,
     "w": 3.7291226722979456
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8444444444444444,
     "source_value_text": "0.8444444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "8GjRH3T4wVQMnBKX4fv4ub",
     "source_model_name": "o3-2025-04-16_medium",
     "p": 0.8442887331776221,
     "p_star": 0.8368041954998477,
     "y": 1.6346393725608352,
     "v": 0.15591331757211294,
     "family_factor": 1.0,
     "w": 1.9537865584471066
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.813,
     "source_value_text": "81.3",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-06-25",
     "source_row_id": "2025-06-25-21-04-24--o3-price-reduction-high",
     "source_model_name": "o3 (high)",
     "p": 0.813,
     "p_star": 0.8116150442477875,
     "y": 1.4605386380513055,
     "v": 0.028811729831448973,
     "family_factor": 1.0,
     "w": 1.4005251635780447
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.6231884057971014,
     "source_value_text": "0.6231884057971014",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-12",
     "source_row_id": "AKt7PcE8LQtoMWVuxwMidk",
     "source_model_name": "o3-2025-04-16_medium",
     "p": 0.6231884057971014,
     "p_star": 0.6229338842975206,
     "y": 0.5020198431446938,
     "v": 0.008778027669869825,
     "family_factor": 1.0,
     "w": 6.50045598668643
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8181818181818182,
     "source_value_text": "0.8181818181818182",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-16",
     "source_row_id": "evANZQ9oQTdGYbDERw7VrD",
     "source_model_name": "o3-2025-04-16_high",
     "p": 0.7575757575757577,
     "p_star": 0.756281407035176,
     "y": 1.1323992862454935,
     "v": 0.039081974585064655,
     "family_factor": 1.0,
     "w": 4.151150937510667
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.494,
     "source_value_text": "0.494",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "CxHSa2gY7ySiPPGTZEZaRt",
     "source_model_name": "o3-2025-04-16_high",
     "p": 0.494,
     "p_star": 0.494005994005994,
     "y": -0.023977172625971384,
     "v": 0.003992585768228399,
     "family_factor": 1.0,
     "w": 1.6914307453712316
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.6305,
     "source_value_text": "63.05%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "8",
     "source_model_name": "o3-2025-04-16 (Prompt)",
     "p": 0.6305,
     "p_star": 0.6292079207920792,
     "y": 0.5288202876722345,
     "v": 0.04201773358445932,
     "family_factor": 1.0,
     "w": 4.979003419780842
    }
   ]
  },
  {
   "slug": "glm-5-1",
   "name": "GLM-5.1",
   "tier": "main",
   "rank": 48,
   "theta": 1.0357352769889034,
   "se": 0.16270904519216475,
   "si_iq": 115.53602915483356,
   "si_iq_low": 111.52153979752586,
   "si_iq_high": 119.55051851214125,
   "si_iq_display": 116,
   "domains": {
    "math": {
     "si_iq": 115.41512736235663,
     "n": 2
    },
    "knowledge": {
     "si_iq": 116.98754526781102,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.2,
     "source_value_text": "0.2",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "R7XgJMi2R9sv7tZdx5SZTv",
     "source_model_name": "glm-5.1",
     "p": 0.15824915824915825,
     "p_star": 0.16163282994966166,
     "y": -1.6461288738575033,
     "v": 0.09570066772788312,
     "family_factor": 1.0,
     "w": 3.61320576672616
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.3684210526315789,
     "source_value_text": "0.3684210526315789",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-29",
     "source_row_id": "Mhwme9odWJMzMjoYkW8r6B",
     "source_model_name": "glm-5.1",
     "p": 0.3684210526315789,
     "p_star": 0.3688811188811189,
     "y": -0.5370198248568143,
     "v": 0.014966325767024197,
     "family_factor": 1.0,
     "w": 4.349099587763072
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9333333333333333,
     "source_value_text": "0.9333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "b7Lw9ExxAhVY3hdExoh4MP",
     "source_model_name": "glm-5.1",
     "p": 0.9332665999332667,
     "p_star": 0.9238477608042825,
     "y": 2.4958128130586847,
     "v": 0.3026105541876743,
     "family_factor": 1.0,
     "w": 1.2418949150720182
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7417,
     "source_value_text": "0.7417",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-05-15",
     "source_row_id": "glm-5.1-swe-bench-frankenstein",
     "source_model_name": "glm-5.1",
     "p": 0.7417,
     "p_star": 0.7412006198347107,
     "y": 1.052218163079015,
     "v": 0.010748736135876688,
     "family_factor": 1.0,
     "w": 6.384784204841887
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.898989898989899,
     "source_value_text": "0.898989898989899",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "CBbeMKRRSeRsXnvSfn7Png",
     "source_model_name": "glm-5.1",
     "p": 0.8653198653198654,
     "p_star": 0.8634840871021776,
     "y": 1.844534283210198,
     "v": 0.058788852713045625,
     "family_factor": 0.5,
     "w": 1.8179811092689897
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8115756996197718,
     "source_value_text": "0.811576",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5.1-20260406",
     "source_model_name": "z-ai/glm-5.1-20260406",
     "p": 0.7487675994930291,
     "p_star": 0.7475175110533655,
     "y": 1.0854158355446568,
     "v": 0.03830458834411772,
     "family_factor": 0.5,
     "w": 1.4960828445618517
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.34,
     "source_value_text": "0.34",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "R2fMFAtRXah864hMifdQGV",
     "source_model_name": "glm-5.1",
     "p": 0.34,
     "p_star": 0.34015984015984013,
     "y": -0.6625819983728132,
     "v": 0.004446415688733116,
     "family_factor": 1.0,
     "w": 1.689184872565859
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7433332500000001,
     "source_value_text": "0.743333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5.1-20260406",
     "source_model_name": "z-ai/glm-5.1-20260406",
     "p": 0.7433332500000001,
     "p_star": 0.7385620098039216,
     "y": 1.0385079414789782,
     "v": 0.09955750202517588,
     "family_factor": 1.0,
     "w": 3.543373584107802
    }
   ]
  },
  {
   "slug": "gpt-5-mini",
   "name": "GPT-5 mini",
   "tier": "main",
   "rank": 49,
   "theta": 0.9921589749844548,
   "se": 0.11785738246798295,
   "si_iq": 114.88238462476681,
   "si_iq_low": 111.97451182003695,
   "si_iq_high": 117.7902574294967,
   "si_iq_display": 115,
   "domains": {
    "reasoning": {
     "si_iq": 114.89195034458218,
     "n": 2
    },
    "math": {
     "si_iq": 116.7194055307494,
     "n": 4
    },
    "knowledge": {
     "si_iq": 106.15349505682958,
     "n": 2
    },
    "agentic": {
     "si_iq": 112.16995396486777,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.24,
     "source_value_text": "0.24",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "5tdGvpe8Ahh8xsUnSwhdAF",
     "source_model_name": "gpt-5-mini-2025-08-07_high",
     "p": 0.2003367003367003,
     "p_star": 0.2033036636997033,
     "y": -1.3657728561604472,
     "v": 0.07605918986764465,
     "family_factor": 1.0,
     "w": 4.016301459288359
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.1,
     "source_value_text": "0.1",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "kW6hSbkCwQczqbazduGXPR",
     "source_model_name": "gpt-5-mini-2025-08-07_minimal",
     "p": 0.008592200925313948,
     "p_star": 0.013457624678528662,
     "y": -4.29466044373402,
     "v": 6.310808718362292,
     "family_factor": 1.0,
     "w": 0.11029915448283494
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.12195121951219512,
     "source_value_text": "0.12195121951219512",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "2WxRbjq5ZWTgiXZPqYUG4R",
     "source_model_name": "gpt-5-mini-2025-08-07_high",
     "p": 0.12195121951219512,
     "p_star": 0.13095238095238096,
     "y": -1.8925641683500207,
     "v": 0.20423412204234123,
     "family_factor": 1.0,
     "w": 1.643471142038477
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.4666666666666667,
     "source_value_text": "0.4666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "YSR9WCR2SnJYvP7DJwX7YN",
     "source_model_name": "gpt-5-mini-2025-08-07_high",
     "p": 0.4666666666666667,
     "p_star": 0.46678321678321677,
     "y": -0.1330631182071621,
     "v": 0.013998894824092833,
     "family_factor": 1.0,
     "w": 4.386007432541606
    },
    {
     "benchmark": "math_level_5",
     "score": 0.9784743202416919,
     "source_value_text": "0.9784743202416919",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-30",
     "source_row_id": "5duoiNDccsgaW7UVt6feYX",
     "source_model_name": "gpt-5-mini-2025-08-07_high",
     "p": 0.9784743202416919,
     "p_star": 0.9781132075471698,
     "y": 3.7997420469257452,
     "v": 0.03522775649212428,
     "family_factor": 1.0,
     "w": 3.6974657642058877
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8666666666666667,
     "source_value_text": "0.8666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-30",
     "source_row_id": "R82gycJfm5jaCdh32tFkH4",
     "source_model_name": "gpt-5-mini-2025-08-07_high",
     "p": 0.8665331998665332,
     "p_star": 0.8585650868259564,
     "y": 1.8034228583617016,
     "v": 0.17533678826674742,
     "family_factor": 1.0,
     "w": 1.8159578425662388
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.6466942148760331,
     "source_value_text": "0.6466942148760331",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-01",
     "source_row_id": "7nvdQy3AwKtoay2FBvfST5",
     "source_model_name": "gpt-5-mini-2025-08-07_medium",
     "p": 0.6466942148760331,
     "p_star": 0.6463911276552148,
     "y": 0.6032133594102569,
     "v": 0.009020650724809239,
     "family_factor": 1.0,
     "w": 6.485989365183958
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.75,
     "source_value_text": "0.75",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-30",
     "source_row_id": "jP8EyLtPFsakgnsHe2oJM6",
     "source_model_name": "gpt-5-mini-2025-08-07_high",
     "p": 0.6666666666666666,
     "p_star": 0.6658291457286433,
     "y": 0.6893806977644686,
     "v": 0.03372104165718676,
     "family_factor": 0.5,
     "w": 2.1587861642214348
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8007853333333332,
     "source_value_text": "0.800785",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "openai/gpt-5-mini-2025-08-07",
     "source_model_name": "openai/gpt-5-mini-2025-08-07",
     "p": 0.7343804444444443,
     "p_star": 0.7332026532663315,
     "y": 1.0109327654917444,
     "v": 0.037179623640655024,
     "family_factor": 0.5,
     "w": 1.5048564934198805
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.216,
     "source_value_text": "0.216",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "8d5RuFTTJKuJ5iJYmPZVJe",
     "source_model_name": "gpt-5-mini-2025-08-07_high",
     "p": 0.216,
     "p_star": 0.2162837162837163,
     "y": -1.2874560247305427,
     "v": 0.005887747156586107,
     "family_factor": 1.0,
     "w": 1.6820915239968932
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5546,
     "source_value_text": "55.46%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "17",
     "source_model_name": "GPT-5-mini-2025-08-07 (FC)",
     "p": 0.5546,
     "p_star": 0.5540594059405941,
     "y": 0.2170861659658457,
     "v": 0.03967563738117941,
     "family_factor": 1.0,
     "w": 5.062491887950579
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.712121101010101,
     "source_value_text": "0.712121",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5-mini-2025-08-07",
     "source_model_name": "openai/gpt-5-mini-2025-08-07",
     "p": 0.712121101010101,
     "p_star": 0.7079618637353932,
     "y": 0.8855058300761602,
     "v": 0.0929780042814731,
     "family_factor": 1.0,
     "w": 3.664183303270037
    }
   ]
  },
  {
   "slug": "qwen3-6-27b",
   "name": "Qwen3.6 27B",
   "tier": "main",
   "rank": 50,
   "theta": 0.9848866741840646,
   "se": 0.17964194592375757,
   "si_iq": 114.77330011276096,
   "si_iq_low": 110.34102851295383,
   "si_iq_high": 119.20557171256812,
   "si_iq_display": 115,
   "domains": {
    "math": {
     "si_iq": 114.34587133355444,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.07,
     "source_value_text": "0.07",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "dKZDn279PKuc2Kxm68D4r2",
     "source_model_name": "qwen3.6-27b_none",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.3508771929824561,
     "source_value_text": "0.3508771929824561",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "VonoEhAsGSJ2FHU33qnhui",
     "source_model_name": "qwen3.6-27b",
     "p": 0.3508771929824561,
     "p_star": 0.3513986013986014,
     "y": -0.6128971545483591,
     "v": 0.015287444180713683,
     "family_factor": 1.0,
     "w": 4.336985727745403
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9111111111111111,
     "source_value_text": "0.9111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "452pB5w5ea6uy92e2q2NMv",
     "source_model_name": "qwen3.6-27b",
     "p": 0.9110221332443554,
     "p_star": 0.9020868694781738,
     "y": 2.2206301607323202,
     "v": 0.24104004547939525,
     "family_factor": 1.0,
     "w": 1.4661034873401948
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8585858585858586,
     "source_value_text": "0.8585858585858586",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "buLf8Ne29xmzMZBRQkvrQG",
     "source_model_name": "qwen3.6-27b",
     "p": 0.8114478114478114,
     "p_star": 0.8098827470686767,
     "y": 1.4492484779718915,
     "v": 0.045837564812730984,
     "family_factor": 0.5,
     "w": 1.979429202383478
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.801499818181818,
     "source_value_text": "0.8015",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.6-27b-20260422",
     "source_model_name": "qwen/qwen3.6-27b-20260422",
     "p": 0.7353330909090907,
     "p_star": 0.7341505125628138,
     "y": 1.0157837536470942,
     "v": 0.03724897350137879,
     "family_factor": 0.5,
     "w": 1.504312655592804
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7627176144578314,
     "source_value_text": "0.762718",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.6-27b-20260422",
     "source_model_name": "qwen/qwen3.6-27b-20260422",
     "p": 0.7627176144578314,
     "p_star": 0.7575662886841484,
     "y": 1.1393827257582305,
     "v": 0.10466850030732612,
     "family_factor": 1.0,
     "w": 3.4548881734354335
    }
   ]
  },
  {
   "slug": "qwen3-7-plus",
   "name": "Qwen3.7-Plus",
   "tier": "main",
   "rank": 51,
   "theta": 0.9773682826956982,
   "se": 0.17420945712991234,
   "si_iq": 114.66052424043548,
   "si_iq_low": 110.362287404466,
   "si_iq_high": 118.95876107640494,
   "si_iq_display": 115,
   "domains": {
    "math": {
     "si_iq": 114.55317958274486,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.17,
     "source_value_text": "0.17",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "a5qR5FNnftfR8pk9HJ3JUz",
     "source_model_name": "qwen3.7-plus_none",
     "p": 0.08570169640890066,
     "p_star": 0.08980365981079273,
     "y": -2.316034605079059,
     "v": 0.25556603990154425,
     "family_factor": 1.0,
     "w": 1.9886791814604803
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.34385964912280703,
     "source_value_text": "0.34385964912280703",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-29",
     "source_row_id": "Tt8tBXHoCEYqGLePWXkM8u",
     "source_model_name": "qwen3.7-plus_none",
     "p": 0.34385964912280703,
     "p_star": 0.34440559440559443,
     "y": -0.6437222972324224,
     "v": 0.01543147208121827,
     "family_factor": 1.0,
     "w": 4.331574318381707
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9333333333333333,
     "source_value_text": "0.9333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "Jvdw6GAXiS6T79bkpbk6Ra",
     "source_model_name": "qwen3.7-plus",
     "p": 0.9332665999332667,
     "p_star": 0.9238477608042825,
     "y": 2.4958128130586847,
     "v": 0.3026105541876743,
     "family_factor": 1.0,
     "w": 1.2418949150720182
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8787878787878788,
     "source_value_text": "0.8787878787878788",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "URoWjw9Htc6QPwABVcrybw",
     "source_model_name": "qwen3.7-plus",
     "p": 0.8383838383838383,
     "p_star": 0.8366834170854272,
     "y": 1.633755220084807,
     "v": 0.05116800792476471,
     "family_factor": 0.5,
     "w": 1.9096311353026798
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.873737,
     "source_value_text": "0.873737",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "qwen/qwen3.7-plus-20260602",
     "source_model_name": "qwen/qwen3.7-plus-20260602",
     "p": 0.8316493333333334,
     "p_star": 0.8299827537688442,
     "y": 1.5855050416597294,
     "v": 0.049662165988027376,
     "family_factor": 0.5,
     "w": 1.412916343730687
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.726667,
     "source_value_text": "0.726667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "qwen/qwen3.7-plus-20260602",
     "source_model_name": "qwen/qwen3.7-plus-20260602",
     "p": 0.726667,
     "p_star": 0.7222225490196078,
     "y": 0.9555130739873019,
     "v": 0.09582120325628546,
     "family_factor": 1.0,
     "w": 3.6109816987545793
    }
   ]
  },
  {
   "slug": "claude-opus-4-5",
   "name": "Claude Opus 4.5",
   "tier": "main",
   "rank": 52,
   "theta": 0.9717902221491312,
   "se": 0.1344462138135681,
   "si_iq": 114.57685333223696,
   "si_iq_low": 111.25968744359542,
   "si_iq_high": 117.8940192208785,
   "si_iq_display": 115,
   "domains": {
    "reasoning": {
     "si_iq": 111.44243589331006,
     "n": 2
    },
    "math": {
     "si_iq": 112.9305065455395,
     "n": 3
    },
    "knowledge": {
     "si_iq": 118.37759409634238,
     "n": 2
    },
    "agentic": {
     "si_iq": 127.19591436838121,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.14,
     "source_value_text": "0.14",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "DPuTDKvupUqKgkdVj7Awsp",
     "source_model_name": "claude-opus-4-5-20251101_59K",
     "p": 0.09511784511784513,
     "p_star": 0.09912657932459913,
     "y": -2.206967147657535,
     "v": 0.167569741192018,
     "family_factor": 1.0,
     "w": 2.6427008451568565
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.22,
     "source_value_text": "0.22",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-25",
     "source_row_id": "k4zGHaXESxFRTRMkyDLZrz",
     "source_model_name": "claude-opus-4-5-20251101_48K",
     "p": 0.14077990746860541,
     "p_star": 0.14433654204812418,
     "y": -1.7797294718695729,
     "v": 0.13522642008792735,
     "family_factor": 1.0,
     "w": 3.0060687099783765
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.04878048780487805,
     "source_value_text": "0.04878048780487805",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "azk4theXxAsizmoi2HDD49",
     "source_model_name": "claude-opus-4-5-20251101_32K",
     "p": 0.04878048780487805,
     "p_star": 0.05952380952380952,
     "y": -2.7600099400329214,
     "v": 0.4151898734177215,
     "family_factor": 1.0,
     "w": 0.9705159705159706
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.34385964912280703,
     "source_value_text": "0.34385964912280703",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "mS5EwCRZVpvUvJEehPUDZu",
     "source_model_name": "claude-opus-4-5-20251101_32K",
     "p": 0.34385964912280703,
     "p_star": 0.34440559440559443,
     "y": -0.6437222972324224,
     "v": 0.01543147208121827,
     "family_factor": 1.0,
     "w": 4.331574318381707
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8611111111111112,
     "source_value_text": "0.8611111111111112",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-11-24",
     "source_row_id": "ikUWdu6HJ2qRgZynfzDCFe",
     "source_model_name": "claude-opus-4-5-20251101_32K",
     "p": 0.8609720831943055,
     "p_star": 0.8531248639944293,
     "y": 1.7593231080594933,
     "v": 0.16992029102448974,
     "family_factor": 1.0,
     "w": 1.8523987140879126
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7665289256198347,
     "source_value_text": "0.7665289256198347",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-05",
     "source_row_id": "mKQKxkpGDrFHBPBYR3mBrB",
     "source_model_name": "claude-opus-4-5-20251101",
     "p": 0.7665289256198347,
     "p_star": 0.7659782460214466,
     "y": 1.1857396931305404,
     "v": 0.011502274869220038,
     "family_factor": 1.0,
     "w": 6.341635469015374
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.860479797979798,
     "source_value_text": "0.860479797979798",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-11-24",
     "source_row_id": "Kwwo3UFcPDk6iLAeSeeRaa",
     "source_model_name": "claude-opus-4-5-20251101_32K",
     "p": 0.813973063973064,
     "p_star": 0.8123953098827472,
     "y": 1.4656500196423896,
     "v": 0.04626603707696283,
     "family_factor": 0.5,
     "w": 1.9736306552348628
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8610461538461541,
     "source_value_text": "0.861046",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.5-opus-20251124",
     "source_model_name": "anthropic/claude-4.5-opus-20251124",
     "p": 0.8147282051282055,
     "p_star": 0.813146656358717,
     "y": 1.4705874318446015,
     "v": 0.04639667752394908,
     "family_factor": 0.5,
     "w": 1.43586562153386
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.457,
     "source_value_text": "0.457",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "CA5LW4phRnHSsZUGXEm8H6",
     "source_model_name": "claude-opus-4-5-20251101_32K",
     "p": 0.457,
     "p_star": 0.45704295704295705,
     "y": -0.1722528218456881,
     "v": 0.004021697055615044,
     "family_factor": 1.0,
     "w": 1.691286502804259
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.7746999999999999,
     "source_value_text": "77.47%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "1",
     "source_model_name": "Claude-Opus-4-5-20251101 (FC)",
     "p": 0.7746999999999999,
     "p_star": 0.771980198019802,
     "y": 1.219526423488915,
     "v": 0.055690167973241535,
     "family_factor": 1.0,
     "w": 4.541756171193019
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7700000714285714,
     "source_value_text": "0.77",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.5-opus-20251124",
     "source_model_name": "anthropic/claude-4.5-opus-20251124",
     "p": 0.7700000714285714,
     "p_star": 0.7647059523809524,
     "y": 1.1786553855358255,
     "v": 0.10683762885085746,
     "family_factor": 1.0,
     "w": 3.4186563881778715
    }
   ]
  },
  {
   "slug": "inkling",
   "name": "Inkling",
   "tier": "main",
   "rank": 53,
   "theta": 0.9034457392085828,
   "se": 0.14425236006391906,
   "si_iq": 113.55168608812875,
   "si_iq_low": 109.99257501622009,
   "si_iq_high": 117.11079716003741,
   "si_iq_display": 114,
   "domains": {
    "math": {
     "si_iq": 113.07534726795943,
     "n": 3
    },
    "knowledge": {
     "si_iq": 116.87479816387184,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.21,
     "source_value_text": "0.21",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "UZ9LtVBCjHPMN9SKFUo7Wa",
     "source_model_name": "Inkling_xhigh",
     "p": 0.16877104377104377,
     "p_star": 0.17205053838717205,
     "y": -1.5711638543360564,
     "v": 0.08969178678512194,
     "family_factor": 1.0,
     "w": 3.7276615565203155
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.04878048780487805,
     "source_value_text": "0.04878048780487805",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "jvJPoRYkPH9Sb5MX252oHp",
     "source_model_name": "Inkling_xhigh",
     "p": 0.04878048780487805,
     "p_star": 0.05952380952380952,
     "y": -2.7600099400329214,
     "v": 0.4151898734177215,
     "family_factor": 1.0,
     "w": 0.9705159705159706
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.3333333333333333,
     "source_value_text": "0.3333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "6KvQvuMMX5zAuteUc6pFcW",
     "source_model_name": "Inkling_xhigh",
     "p": 0.3333333333333333,
     "p_star": 0.3339160839160839,
     "y": -0.690525947080071,
     "v": 0.015665581069382036,
     "family_factor": 1.0,
     "w": 4.322807142602558
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8888888888888888,
     "source_value_text": "0.8888888888888888",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-05",
     "source_row_id": "j2fELMf364qfh2cpaVDL6W",
     "source_model_name": "Inkling_xhigh",
     "p": 0.8887776665554443,
     "p_star": 0.8803259781520651,
     "y": 1.995520706756699,
     "v": 0.2020910093434368,
     "family_factor": 1.0,
     "w": 1.6551303565329458
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8825757575757576,
     "source_value_text": "0.8825757575757576",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-05",
     "source_row_id": "dfmiZmjAcNkLuAJL4z65eb",
     "source_model_name": "Inkling_xhigh",
     "p": 0.8434343434343434,
     "p_star": 0.8417085427135679,
     "y": 1.670995805433534,
     "v": 0.05238795362208151,
     "family_factor": 0.5,
     "w": 1.8943435339431118
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.818035862576065,
     "source_value_text": "0.818035862576065",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-09-19",
     "source_row_id": "thinkingmachines/inkling-20260715",
     "source_model_name": "thinkingmachines/inkling-20260715",
     "p": 0.7573811501014199,
     "p_star": 0.756087777487845,
     "y": 1.1313490604604663,
     "v": 0.03906401028807767,
     "family_factor": 0.5,
     "w": 1.490217694556427
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.403,
     "source_value_text": "0.403",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "bpnzC6CCi3hWuKCfqX4KEY",
     "source_model_name": "Inkling_xhigh",
     "p": 0.403,
     "p_star": 0.4030969030969031,
     "y": -0.3925777960956621,
     "v": 0.004147807106230525,
     "family_factor": 1.0,
     "w": 1.6906619282548254
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6755556666666667,
     "source_value_text": "0.675556",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-08",
     "source_row_id": "thinkingmachines/inkling-20260715",
     "source_model_name": "thinkingmachines/inkling-20260715",
     "p": 0.6755556666666667,
     "p_star": 0.6721133986928104,
     "y": 0.7177592534570219,
     "v": 0.08722950918038393,
     "family_factor": 1.0,
     "w": 3.776684478221295
    }
   ]
  },
  {
   "slug": "qwen3-5-397b-a17b",
   "name": "Qwen3.5 397B-A17B",
   "tier": "main",
   "rank": 54,
   "theta": 0.9004809414074432,
   "se": 0.1695383307108081,
   "si_iq": 113.50721412111164,
   "si_iq_low": 109.32422709976672,
   "si_iq_high": 117.69020114245657,
   "si_iq_display": 114,
   "domains": {
    "math": {
     "si_iq": 112.55275226139509,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.18,
     "source_value_text": "0.18",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "D7WDyCr24AVdzr4eKAreJu",
     "source_model_name": "qwen3.5-397b-a17b_none",
     "p": 0.09671733862084159,
     "p_star": 0.10071023625825899,
     "y": -2.189357854798553,
     "v": 0.217395934326983,
     "family_factor": 1.0,
     "w": 2.227838181626115
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.312280701754386,
     "source_value_text": "0.312280701754386",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "A4yUA9PfzRr92JAqDDo9ro",
     "source_model_name": "qwen3.5-397b-a17b_none",
     "p": 0.312280701754386,
     "p_star": 0.31293706293706297,
     "y": -0.7864238060285061,
     "v": 0.01620538189261802,
     "family_factor": 1.0,
     "w": 4.302726705567176
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8888888888888888,
     "source_value_text": "0.8888888888888888",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "JYuFdyZZSiMvmSZNzMTywb",
     "source_model_name": "qwen3.5-397b-a17b",
     "p": 0.8887776665554443,
     "p_star": 0.8803259781520651,
     "y": 1.995520706756699,
     "v": 0.2020910093434368,
     "family_factor": 1.0,
     "w": 1.6551303565329458
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8636363636363636,
     "source_value_text": "0.8636363636363636",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "bXrmQqzF9sXbuZfRrSc7NP",
     "source_model_name": "qwen3.5-397b-a17b_none",
     "p": 0.8181818181818182,
     "p_star": 0.8165829145728644,
     "y": 1.4933657411813466,
     "v": 0.04700941882143149,
     "family_factor": 0.5,
     "w": 1.9636506076216729
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8728152090966519,
     "source_value_text": "0.872815",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.5-397b-a17b-20260216",
     "source_model_name": "qwen/qwen3.5-397b-a17b-20260216",
     "p": 0.8304202787955358,
     "p_star": 0.8287598753845029,
     "y": 1.5768636484277674,
     "v": 0.04940114700119829,
     "family_factor": 0.5,
     "w": 1.4147237292959862
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7811111111111111,
     "source_value_text": "0.781111",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.5-397b-a17b-20260216",
     "source_model_name": "qwen/qwen3.5-397b-a17b-20260216",
     "p": 0.7811111111111111,
     "p_star": 0.775599128540305,
     "y": 1.2402017426223946,
     "v": 0.1104505290716701,
     "family_factor": 1.0,
     "w": 3.359966754684367
    }
   ]
  },
  {
   "slug": "claude-sonnet-4-6",
   "name": "Claude Sonnet 4.6",
   "tier": "main",
   "rank": 55,
   "theta": 0.8853358906701922,
   "se": 0.20088785048549607,
   "si_iq": 113.28003836005288,
   "si_iq_low": 108.32357059371583,
   "si_iq_high": 118.23650612638994,
   "si_iq_display": 113,
   "domains": {
    "reasoning": {
     "si_iq": 112.54033092847786,
     "n": 2
    },
    "knowledge": {
     "si_iq": 110.6777400709721,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.23,
     "source_value_text": "0.23",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "6P9AJQmBzaPmE7ossbqLjz",
     "source_model_name": "claude-sonnet-4-6_max",
     "p": 0.18981481481481483,
     "p_star": 0.19288595526219288,
     "y": -1.4313658687887518,
     "v": 0.08000539502370328,
     "family_factor": 1.0,
     "w": 3.9282532675947572
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.16,
     "source_value_text": "0.16",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "YdyvoMQ4mA5V8Ymg6Tksxu",
     "source_model_name": "claude-sonnet-4-6_low",
     "p": 0.07468605419695969,
     "p_star": 0.07889708336332642,
     "y": -2.4574275135361505,
     "v": 0.3085398685516122,
     "family_factor": 1.0,
     "w": 1.7308146294104374
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.857936507936508,
     "source_value_text": "0.857936507936508",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-20",
     "source_row_id": "9LWdzVN5w4ihNvncsaCWMu",
     "source_model_name": "claude-sonnet-4-6_32K",
     "p": 0.8577943022387468,
     "p_star": 0.8500161652335566,
     "y": 1.7347278471602223,
     "v": 0.16700764326630171,
     "family_factor": 1.0,
     "w": 1.8726055699511266
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7520661157024794,
     "source_value_text": "0.7520661157024794",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-21",
     "source_row_id": "KEdgiMmtJKHxgGiS82agYj",
     "source_model_name": "claude-sonnet-4-6",
     "p": 0.7520661157024794,
     "p_star": 0.7515453179427635,
     "y": 1.1068710477527743,
     "v": 0.011042160327391293,
     "family_factor": 1.0,
     "w": 6.3679126838108004
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8737373737373737,
     "source_value_text": "0.8737373737373737",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-20",
     "source_row_id": "58eQmyCfPa3FufhXJFvAL2",
     "source_model_name": "claude-sonnet-4-6_32K",
     "p": 0.8316498316498316,
     "p_star": 0.8299832495812395,
     "y": 1.5855085552882002,
     "v": 0.04966227264781261,
     "family_factor": 0.5,
     "w": 1.9288437191791636
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.6459467692307692,
     "source_value_text": "0.645947",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.6-sonnet-20260217",
     "source_model_name": "anthropic/claude-4.6-sonnet-20260217",
     "p": 0.5279290256410256,
     "p_star": 0.5277886787785079,
     "y": 0.11126937416320655,
     "v": 0.03273159680404923,
     "family_factor": 0.5,
     "w": 1.540578592201443
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.355,
     "source_value_text": "0.355",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "LJyKf8Xy4dymxNHbGLwNdA",
     "source_model_name": "claude-sonnet-4-6_high",
     "p": 0.355,
     "p_star": 0.35514485514485516,
     "y": -0.5964999610434015,
     "v": 0.0043577684303644955,
     "family_factor": 1.0,
     "w": 1.6896230933342997
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7490475714285715,
     "source_value_text": "0.749048",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.6-sonnet-20260217",
     "source_model_name": "anthropic/claude-4.6-sonnet-20260217",
     "p": 0.7490475714285715,
     "p_star": 0.7441642857142858,
     "y": 1.0677263271851511,
     "v": 0.10097169751344169,
     "family_factor": 1.0,
     "w": 3.518439610827558
    }
   ]
  },
  {
   "slug": "glm-4-7",
   "name": "GLM-4.7",
   "tier": "main",
   "rank": 56,
   "theta": 0.8194984399172153,
   "se": 0.22254059327968045,
   "si_iq": 112.29247659875823,
   "si_iq_low": 106.8017748234814,
   "si_iq_high": 117.78317837403506,
   "si_iq_display": 112,
   "domains": {
    "knowledge": {
     "si_iq": 112.76167520010321,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.21,
     "source_value_text": "0.21",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "9rDLegdh3zmBfFzTj3fkCc",
     "source_model_name": "glm-4.7",
     "p": 0.16877104377104377,
     "p_star": 0.17205053838717205,
     "y": -1.5711638543360564,
     "v": 0.08969178678512194,
     "family_factor": 1.0,
     "w": 3.7276615565203155
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8333333333333334,
     "source_value_text": "0.8333333333333334",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-01-29",
     "source_row_id": "GYzmrzMfeSjNjm2J6L9PeT",
     "source_model_name": "glm-4.7",
     "p": 0.8331664998331665,
     "p_star": 0.8259237498367934,
     "y": 1.557009034160403,
     "v": 0.1480960275440811,
     "family_factor": 1.0,
     "w": 2.0153486734533113
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8333333333333334,
     "source_value_text": "0.8333333333333334",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-01-29",
     "source_row_id": "6phXzd4aCbnBUSQmBsaywa",
     "source_model_name": "glm-4.7",
     "p": 0.7777777777777778,
     "p_star": 0.7763819095477387,
     "y": 1.2447049071656053,
     "v": 0.04116355168726432,
     "family_factor": 0.5,
     "w": 2.044969336237358
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8364136921606119,
     "source_value_text": "0.836414",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-4.7-20251222",
     "source_model_name": "z-ai/glm-4.7-20251222",
     "p": 0.7818849228808159,
     "p_star": 0.7804684157306611,
     "y": 1.2683981583724588,
     "v": 0.04164465382392454,
     "family_factor": 0.5,
     "w": 1.4706260624605203
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.322,
     "source_value_text": "0.322",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "aYau6EG7CCaWVSyVq3vvQc",
     "source_model_name": "glm-4.7",
     "p": 0.322,
     "p_star": 0.3221778221778222,
     "y": -0.7437813430390965,
     "v": 0.004570044500808327,
     "family_factor": 1.0,
     "w": 1.6885741026583378
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7037037777777777,
     "source_value_text": "0.703704",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-4.7-20251222",
     "source_model_name": "z-ai/glm-4.7-20251222",
     "p": 0.7037037777777777,
     "p_star": 0.6997095860566449,
     "y": 0.8459153190169396,
     "v": 0.09148931158233956,
     "family_factor": 1.0,
     "w": 3.692669712703493
    }
   ]
  },
  {
   "slug": "o4-mini",
   "name": "o4-mini",
   "tier": "main",
   "rank": 57,
   "theta": 0.7808489559395323,
   "se": 0.12527173863532748,
   "si_iq": 111.71273433909299,
   "si_iq_low": 108.62192853337389,
   "si_iq_high": 114.80354014481208,
   "si_iq_display": 112,
   "domains": {
    "reasoning": {
     "si_iq": 113.41608740580651,
     "n": 2
    },
    "math": {
     "si_iq": 112.88528927810296,
     "n": 4
    },
    "knowledge": {
     "si_iq": 105.91719222283857,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.22,
     "source_value_text": "0.22",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "dfonReEmxqpRWn5kxGSSES",
     "source_model_name": "o4-mini-2025-04-16_medium",
     "p": 0.17929292929292928,
     "p_star": 0.18246824682468246,
     "y": -1.499713575938965,
     "v": 0.08451059630927527,
     "family_factor": 1.0,
     "w": 3.8323369786378034
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.05,
     "source_value_text": "0.05",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "eJbFTXaxZjnW7HNR93u3WH",
     "source_model_name": "o4-mini-2025-04-16_high",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.04878048780487805,
     "source_value_text": "0.04878048780487805",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "TomkQucNryhFGkaUnUGeLR",
     "source_model_name": "o4-mini-2025-04-16_high",
     "p": 0.04878048780487805,
     "p_star": 0.05952380952380952,
     "y": -2.7600099400329214,
     "v": 0.4151898734177215,
     "family_factor": 1.0,
     "w": 0.9705159705159706
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.36140350877192984,
     "source_value_text": "0.36140350877192984",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "dcmRi5JTa27EuwiQTdqr2B",
     "source_model_name": "o4-mini-2025-04-16_high",
     "p": 0.36140350877192984,
     "p_star": 0.3618881118881119,
     "y": -0.5671785603171224,
     "v": 0.015088346237839981,
     "family_factor": 1.0,
     "w": 4.344488528549249
    },
    {
     "benchmark": "math_level_5",
     "score": 0.978285498489426,
     "source_value_text": "0.978285498489426",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-16",
     "source_row_id": "727ixGKZ7A7G8LmavE2ScL",
     "source_model_name": "o4-mini-2025-04-16_high",
     "p": 0.978285498489426,
     "p_star": 0.9779245283018868,
     "y": 3.790965383391951,
     "v": 0.034933403252909355,
     "family_factor": 1.0,
     "w": 3.705531676710446
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8166666666666667,
     "source_value_text": "0.8166666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-16",
     "source_row_id": "TVsxkJ8ZyfMVmVx88Qq3KN",
     "source_model_name": "o4-mini-2025-04-16_high",
     "p": 0.8164831498164832,
     "p_star": 0.8096030813422118,
     "y": 1.4474331658253643,
     "v": 0.13813426353637134,
     "family_factor": 1.0,
     "w": 2.0996558520174173
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.72,
     "source_value_text": "72.0",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-16",
     "source_row_id": "2025-04-16-22-01-58--o4-mini-high-diff-exsys",
     "source_model_name": "o4-mini (high)",
     "p": 0.72,
     "p_star": 0.7190265486725663,
     "y": 0.939638095871146,
     "v": 0.021804966686856442,
     "family_factor": 1.0,
     "w": 1.4202350249545832
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7960858585858586,
     "source_value_text": "0.7960858585858586",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-16",
     "source_row_id": "9Sgsz5XCjscuZkexf7MX9c",
     "source_model_name": "o4-mini-2025-04-16_high",
     "p": 0.728114478114478,
     "p_star": 0.7269681742043551,
     "y": 0.9792943332936426,
     "v": 0.036740439426346694,
     "family_factor": 1.0,
     "w": 4.222234999475831
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.196,
     "source_value_text": "0.196",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "Dzky9brdTFbSoVd2zTKiUp",
     "source_model_name": "o4-mini-2025-04-16_low",
     "p": 0.196,
     "p_star": 0.1963036963036963,
     "y": -1.4095585351231221,
     "v": 0.006325740862862681,
     "family_factor": 1.0,
     "w": 1.6799477751651428
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5324,
     "source_value_text": "53.24%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "21",
     "source_model_name": "o4-mini-2025-04-16 (FC)",
     "p": 0.5324,
     "p_star": 0.532079207920792,
     "y": 0.12849333142858307,
     "v": 0.039373916921980265,
     "family_factor": 1.0,
     "w": 5.073451308557087
    }
   ]
  },
  {
   "slug": "qwen3-235b-a22b-thinking-jul-2025",
   "name": "Qwen3-235B-A22B-Thinking (Jul 2025)",
   "tier": "main",
   "rank": 58,
   "theta": 0.7590997769519297,
   "se": 0.26293666991828357,
   "si_iq": 111.38649665427894,
   "si_iq_low": 104.89911015535242,
   "si_iq_high": 117.87388315320547,
   "si_iq_display": 111,
   "domains": {
    "knowledge": {
     "si_iq": 111.25633053403126,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.09,
     "source_value_text": "0.09",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "BP3KYD8rYyFg3LviNGtjLL",
     "source_model_name": "Qwen3-235B-A22B-Thinking-2507",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8666666666666667,
     "source_value_text": "0.8666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-12-10",
     "source_row_id": "XWpHpVPCaVjcwPpdpXuuGH",
     "source_model_name": "Qwen3-235B-A22B-Thinking-2507",
     "p": 0.8665331998665332,
     "p_star": 0.8585650868259564,
     "y": 1.8034228583617016,
     "v": 0.17533678826674742,
     "family_factor": 1.0,
     "w": 1.8159578425662388
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8005050505050505,
     "source_value_text": "0.8005050505050505",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-12-11",
     "source_row_id": "gu39ndv9QxWP3NRxSUJRaX",
     "source_model_name": "Qwen3-235B-A22B-Thinking-2507",
     "p": 0.734006734006734,
     "p_star": 0.7328308207705193,
     "y": 1.0090327835727702,
     "v": 0.037152608022519365,
     "family_factor": 0.5,
     "w": 2.1047732066999028
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7950335,
     "source_value_text": "0.795033",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-22",
     "source_row_id": "qwen/qwen3-235b-a22b-thinking-2507",
     "source_model_name": "qwen/qwen3-235b-a22b-thinking-2507",
     "p": 0.7267113333333333,
     "p_star": 0.7255720804020099,
     "y": 0.9722717816322589,
     "v": 0.036646017687205205,
     "family_factor": 0.5,
     "w": 1.5090541916283517
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.4044044044044044,
     "source_value_text": "0.4044044044044044",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "4ACEC4x26HWRGiAepHGw43",
     "source_model_name": "Qwen3-235B-A22B-Thinking-2507",
     "p": 0.4044044044044044,
     "p_star": 0.4044999044999045,
     "y": -0.3867500487606006,
     "v": 0.004143158864862641,
     "family_factor": 1.0,
     "w": 1.6906849410173657
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6266666666666667,
     "source_value_text": "0.626667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-22",
     "source_row_id": "qwen/qwen3-235b-a22b-thinking-2507",
     "source_model_name": "qwen/qwen3-235b-a22b-thinking-2507",
     "p": 0.6266666666666667,
     "p_star": 0.6241830065359477,
     "y": 0.5073412996833798,
     "v": 0.08194855451855224,
     "family_factor": 1.0,
     "w": 3.8863006252377117
    }
   ]
  },
  {
   "slug": "qwen-3-6-35b-a3b",
   "name": "Qwen 3.6 35B-A3B",
   "tier": "main",
   "rank": 59,
   "theta": 0.7186701100634317,
   "se": 0.1665946414077356,
   "si_iq": 110.78005165095148,
   "si_iq_low": 106.66969371648028,
   "si_iq_high": 114.89040958542267,
   "si_iq_display": 111,
   "domains": {
    "math": {
     "si_iq": 108.01401638416966,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.22,
     "source_value_text": "0.22",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "Ua5RK6JRxdyrHRa3hVFQwq",
     "source_model_name": "qwen3.6-35b-a3b_none",
     "p": 0.14077990746860541,
     "p_star": 0.14433654204812418,
     "y": -1.7797294718695729,
     "v": 0.13522642008792735,
     "family_factor": 1.0,
     "w": 3.0060687099783765
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.20350877192982456,
     "source_value_text": "0.20350877192982456",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "YRvn36dmMyDbS5e4XkF4Xi",
     "source_model_name": "qwen3.6-35b-a3b_none",
     "p": 0.20350877192982456,
     "p_star": 0.20454545454545456,
     "y": -1.3581234841531942,
     "v": 0.021414482952944493,
     "family_factor": 1.0,
     "w": 4.118124854954746
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8666666666666667,
     "source_value_text": "0.8666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "3n5KDcBaKqJh3WTg7qU2rs",
     "source_model_name": "qwen3.6-35b-a3b",
     "p": 0.8665331998665332,
     "p_star": 0.8585650868259564,
     "y": 1.8034228583617016,
     "v": 0.17533678826674742,
     "family_factor": 1.0,
     "w": 1.8159578425662388
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8484848484848485,
     "source_value_text": "0.8484848484848485",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "9kErpmgQ42wTvgJaFn478v",
     "source_model_name": "qwen3.6-35b-a3b_none",
     "p": 0.797979797979798,
     "p_star": 0.7964824120603015,
     "y": 1.3644526192048416,
     "v": 0.0437534530221292,
     "family_factor": 0.5,
     "w": 2.008126612098665
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8272847449686571,
     "source_value_text": "0.8272847449686571",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.6-35b-a3b-20260415",
     "source_model_name": "qwen/qwen3.6-35b-a3b-20260415",
     "p": 0.7697129932915429,
     "p_star": 0.768357651616711,
     "y": 1.1990607365765122,
     "v": 0.040278569018362284,
     "family_factor": 0.5,
     "w": 1.4809324338186098
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.744993393858478,
     "source_value_text": "0.744993393858478",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.6-35b-a3b-20260415",
     "source_model_name": "qwen/qwen3.6-35b-a3b-20260415",
     "p": 0.744993393858478,
     "p_star": 0.7401896018220372,
     "y": 1.0469542448429876,
     "v": 0.09996089681372086,
     "family_factor": 1.0,
     "w": 3.53622529431478
    }
   ]
  },
  {
   "slug": "claude-sonnet-4-5",
   "name": "Claude Sonnet 4.5",
   "tier": "main",
   "rank": 60,
   "theta": 0.6601929776231318,
   "se": 0.12730261286254274,
   "si_iq": 109.90289466434697,
   "si_iq_low": 106.7619814846859,
   "si_iq_high": 113.04380784400806,
   "si_iq_display": 110,
   "domains": {
    "reasoning": {
     "si_iq": 104.8822359215356,
     "n": 2
    },
    "math": {
     "si_iq": 109.38802766064876,
     "n": 4
    },
    "knowledge": {
     "si_iq": 110.46487341577611,
     "n": 2
    },
    "agentic": {
     "si_iq": 121.97130083192522,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.1,
     "source_value_text": "0.1",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "RuQX7KA7owzqzf8Le9veeM",
     "source_model_name": "claude-sonnet-4-5-20250929_59K",
     "p": 0.05303030303030304,
     "p_star": 0.05745574557455746,
     "y": -2.797567863222301,
     "v": 0.34544158934032293,
     "family_factor": 1.0,
     "w": 1.5874287406206002
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.17,
     "source_value_text": "0.17",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-25",
     "source_row_id": "4oSbA2RKFsfuAfVayAMAww",
     "source_model_name": "claude-sonnet-4-5-20250929_48K",
     "p": 0.08570169640890066,
     "p_star": 0.08980365981079273,
     "y": -2.316034605079059,
     "v": 0.25556603990154425,
     "family_factor": 1.0,
     "w": 1.9886791814604803
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.024390243902439025,
     "source_value_text": "0.024390243902439025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "d3m9Xip8cof4s77z6LKkEh",
     "source_model_name": "claude-sonnet-4-5-20250929_32K",
     "p": 0.024390243902439025,
     "p_star": 0.03571428571428571,
     "y": -3.295836866004329,
     "v": 0.6748971193415636,
     "family_factor": 1.0,
     "w": 0.6452469463621882
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.23859649122807017,
     "source_value_text": "0.23859649122807017",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "7oUkeLfwMK3MtkSNHX6QPu",
     "source_model_name": "claude-sonnet-4-5-20250929_32K",
     "p": 0.23859649122807017,
     "p_star": 0.2395104895104895,
     "y": -1.1553651052605591,
     "v": 0.019129121570601558,
     "family_factor": 1.0,
     "w": 4.197126558208324
    },
    {
     "benchmark": "math_level_5",
     "score": 0.9773413897280967,
     "source_value_text": "0.9773413897280967",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-21",
     "source_row_id": "FqjAH25VNjgwQTbDJFfqAg",
     "source_model_name": "claude-sonnet-4-5-20250929_32K",
     "p": 0.9773413897280967,
     "p_star": 0.9769811320754717,
     "y": 3.7481531155782246,
     "v": 0.03353405644308513,
     "family_factor": 1.0,
     "w": 3.7443631483861193
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7777777777777778,
     "source_value_text": "0.7777777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-28",
     "source_row_id": "k5PDL6MpCC6P5eLAhodJiS",
     "source_model_name": "claude-sonnet-4-5-20250929_59K",
     "p": 0.7775553331108886,
     "p_star": 0.7715215215215214,
     "y": 1.2169225472911813,
     "v": 0.12079991035982915,
     "family_factor": 1.0,
     "w": 2.2644936729601435
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7128099173553719,
     "source_value_text": "0.7128099173553719",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-05",
     "source_row_id": "Lti64yMEsBWSzgEMFCSVhp",
     "source_model_name": "claude-sonnet-4-5-20250929",
     "p": 0.7128099173553719,
     "p_star": 0.7123702274434807,
     "y": 0.9069236174323148,
     "v": 0.010062752919975191,
     "family_factor": 1.0,
     "w": 6.4245783648594825
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8232323232323232,
     "source_value_text": "0.8232323232323232",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-28",
     "source_row_id": "XaGuWDxPtqVvyxqdMncKFj",
     "source_model_name": "claude-sonnet-4-5-20250929_59K",
     "p": 0.7643097643097643,
     "p_star": 0.7629815745393634,
     "y": 1.1690959996167205,
     "v": 0.039726851603820106,
     "family_factor": 0.5,
     "w": 2.0659961294577727
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8111110666666667,
     "source_value_text": "0.811111",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.5-sonnet-20250929",
     "source_model_name": "anthropic/claude-4.5-sonnet-20250929",
     "p": 0.7481480888888888,
     "p_star": 0.7469011135678392,
     "y": 1.0821525304549886,
     "v": 0.03825256935996981,
     "family_factor": 0.5,
     "w": 1.4964862863445352
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.307,
     "source_value_text": "0.307",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "XQEGUQjpXupjdyKoGuSmum",
     "source_model_name": "claude-sonnet-4-5-20250929_59K",
     "p": 0.307,
     "p_star": 0.30719280719280717,
     "y": -0.8132761525083138,
     "v": 0.0046893042830933,
     "family_factor": 1.0,
     "w": 1.6879853356947587
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.7323999999999999,
     "source_value_text": "73.24%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "2",
     "source_model_name": "Claude-Sonnet-4-5-20250929 (FC)",
     "p": 0.7323999999999999,
     "p_star": 0.7300990099009901,
     "y": 0.9951249665376117,
     "v": 0.04974747188322636,
     "family_factor": 1.0,
     "w": 4.721994784245519
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7528572857142857,
     "source_value_text": "0.752857",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.5-sonnet-20250929",
     "source_model_name": "anthropic/claude-4.5-sonnet-20250929",
     "p": 0.7528572857142857,
     "p_star": 0.7478992997198879,
     "y": 1.0874397308915942,
     "v": 0.10195592602206409,
     "family_factor": 1.0,
     "w": 3.5012925597899747
    }
   ]
  },
  {
   "slug": "gemini-3-5-flash-lite",
   "name": "Gemini 3.5 Flash-Lite",
   "tier": "main",
   "rank": 61,
   "theta": 0.6225507346567122,
   "se": 0.14728647995912328,
   "si_iq": 109.33826101985068,
   "si_iq_low": 105.70428968425043,
   "si_iq_high": 112.97223235545094,
   "si_iq_display": 109,
   "domains": {
    "reasoning": {
     "si_iq": 112.36082250655285,
     "n": 2
    },
    "math": {
     "si_iq": 106.71473213587419,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.21,
     "source_value_text": "0.21",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "d5QCJNq9uLtxjhiMhqXLmg",
     "source_model_name": "gemini-3.5-flash-lite_low",
     "p": 0.16877104377104377,
     "p_star": 0.17205053838717205,
     "y": -1.5711638543360564,
     "v": 0.08969178678512194,
     "family_factor": 1.0,
     "w": 3.7276615565203155
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.19,
     "source_value_text": "0.19",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-05",
     "source_row_id": "Mg2yb9Tp3yc2H3ApJX6JBK",
     "source_model_name": "gemini-3.5-flash-lite_low",
     "p": 0.10773298083278256,
     "p_star": 0.11161681270572531,
     "y": -2.0743314770532617,
     "v": 0.18881924298033745,
     "family_factor": 1.0,
     "w": 2.4482675527083444
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.0,
     "source_value_text": "0.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "juNVfKBcYTwaKnk9GRA2zL",
     "source_model_name": "gemini-3.5-flash-lite_high",
     "p": 0.0,
     "p_star": 0.011904761904761904,
     "y": -4.418840607796598,
     "v": 1.9759036144578312,
     "family_factor": 1.0,
     "w": 0.24085896691816602
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.2596491228070175,
     "source_value_text": "0.2596491228070175",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "8o2J9uQLKDCTiCFwYdkJRK",
     "source_model_name": "gemini-3.5-flash-lite_high",
     "p": 0.2596491228070175,
     "p_star": 0.26048951048951047,
     "y": -1.043425873100819,
     "v": 0.018087486315388646,
     "family_factor": 1.0,
     "w": 4.234148897577492
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7111111111111111,
     "source_value_text": "0.7111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "mqsc4vFuKtAHXxbYyX9WwK",
     "source_model_name": "gemini-3.5-flash-lite_high",
     "p": 0.7108219330441553,
     "p_star": 0.7062388475431954,
     "y": 0.8771864606986053,
     "v": 0.10265166642248823,
     "family_factor": 1.0,
     "w": 2.4672878778978307
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8333333333333334,
     "source_value_text": "0.8333333333333334",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "chbh6XstiqtUa5W9zuyfjS",
     "source_model_name": "gemini-3.5-flash-lite_high",
     "p": 0.7777777777777778,
     "p_star": 0.7763819095477387,
     "y": 1.2447049071656053,
     "v": 0.04116355168726432,
     "family_factor": 0.5,
     "w": 2.044969336237358
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8402775531250001,
     "source_value_text": "0.8402775531250001",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.5-flash-lite-20260721",
     "source_model_name": "google/gemini-3.5-flash-lite-20260721",
     "p": 0.7870367375000001,
     "p_star": 0.7855943418341711,
     "y": 1.298570735117493,
     "v": 0.042279332027131473,
     "family_factor": 0.5,
     "w": 1.4658864068924542
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7349997500000001,
     "source_value_text": "0.7349997500000001",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-3.5-flash-lite-20260721",
     "source_model_name": "google/gemini-3.5-flash-lite-20260721",
     "p": 0.7349997500000001,
     "p_star": 0.730391911764706,
     "y": 0.9966118760519668,
     "v": 0.09762044431777375,
     "family_factor": 1.0,
     "w": 3.578105411247429
    }
   ]
  },
  {
   "slug": "gemini-2-5-pro-jun-2025",
   "name": "Gemini 2.5 Pro (Jun 2025)",
   "tier": "main",
   "rank": 62,
   "theta": 0.5644180883005688,
   "se": 0.1615667180411413,
   "si_iq": 108.46627132450854,
   "si_iq_low": 104.47996638795588,
   "si_iq_high": 112.45257626106118,
   "si_iq_display": 108,
   "domains": {
    "math": {
     "si_iq": 108.48927523191519,
     "n": 3
    },
    "coding": {
     "si_iq": 107.8653066658933,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "frontiermath_t4",
     "score": 0.0,
     "source_value_text": "0.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "2z7kL9DpfvY44T9Wo99FYx",
     "source_model_name": "gemini-2.5-pro",
     "p": 0.0,
     "p_star": 0.011904761904761904,
     "y": -4.418840607796598,
     "v": 1.9759036144578312,
     "family_factor": 1.0,
     "w": 0.24085896691816602
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.24561403508771928,
     "source_value_text": "0.24561403508771928",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "FkywQ2KS4AkLPzjSPmhHcS",
     "source_model_name": "gemini-2.5-pro",
     "p": 0.24561403508771928,
     "p_star": 0.2465034965034965,
     "y": -1.1173481997255794,
     "v": 0.01875894752431258,
     "family_factor": 1.0,
     "w": 4.210209086752297
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8472222222222222,
     "source_value_text": "0.8472222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-11-16",
     "source_row_id": "iJp7PgYZa3PiXAV8UWd7MC",
     "source_model_name": "gemini-2.5-pro",
     "p": 0.847069291513736,
     "p_star": 0.8395243069156113,
     "y": 1.6546929439932363,
     "v": 0.15804175183906524,
     "family_factor": 1.0,
     "w": 1.9376709250983484
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.831,
     "source_value_text": "83.1",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-06-06",
     "source_row_id": "2025-06-06-16-36-21--gemini0605-32k-think-diff-fenced",
     "source_model_name": "gemini-2.5-pro-preview-06-05 (32k think)",
     "p": 0.831,
     "p_star": 0.8295353982300885,
     "y": 1.5823381219812735,
     "v": 0.031152758503210334,
     "family_factor": 1.0,
     "w": 1.3940612653917368
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.5755693581780539,
     "source_value_text": "0.5755693581780539",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-13",
     "source_row_id": "KL724uHFGbiXj4o5PHyLn2",
     "source_model_name": "gemini-2.5-pro",
     "p": 0.5755693581780539,
     "p_star": 0.5754132231404959,
     "y": 0.30397202543104956,
     "v": 0.008439371502706104,
     "family_factor": 1.0,
     "w": 6.520756911329956
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8529040404040404,
     "source_value_text": "0.8529040404040404",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-11-16",
     "source_row_id": "cqUZ6gcq2HBnShFRWvKjGr",
     "source_model_name": "gemini-2.5-pro",
     "p": 0.803872053872054,
     "p_star": 0.8023450586264658,
     "y": 1.4010159729452512,
     "v": 0.04462562991157803,
     "family_factor": 0.5,
     "w": 1.9960164375519374
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.806210222222222,
     "source_value_text": "0.806210222222222",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-2.5-pro",
     "source_model_name": "google/gemini-2.5-pro",
     "p": 0.7416136296296294,
     "p_star": 0.7403994907872695,
     "y": 1.0480459465893044,
     "v": 0.03772397986561539,
     "family_factor": 0.5,
     "w": 1.5005982220869658
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.5622223333333333,
     "source_value_text": "0.5622223333333333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-2.5-pro",
     "source_model_name": "google/gemini-2.5-pro",
     "p": 0.5622223333333333,
     "p_star": 0.5610022875816993,
     "y": 0.24523078103078022,
     "v": 0.07805536570006928,
     "family_factor": 1.0,
     "w": 3.9712747684203724
    }
   ]
  },
  {
   "slug": "minimax-m3",
   "name": "MiniMax-M3",
   "tier": "main",
   "rank": 63,
   "theta": 0.5472610983983939,
   "se": 0.23467052768235716,
   "si_iq": 108.20891647597591,
   "si_iq_low": 102.41893513386937,
   "si_iq_high": 113.99889781808244,
   "si_iq_display": 108,
   "domains": {
    "reasoning": {
     "si_iq": 103.7337449725255,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.13,
     "source_value_text": "0.13",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "CtmxkTPbFRofQWTkEw5aSe",
     "source_model_name": "MiniMax-M3",
     "p": 0.0845959595959596,
     "p_star": 0.08870887088708872,
     "y": -2.3295025228174384,
     "v": 0.19260566518699013,
     "family_factor": 1.0,
     "w": 2.4165860928723633
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.08,
     "source_value_text": "0.08",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "jWHk7BTYHQRXk2rXCbnpcS",
     "source_model_name": "MiniMax-M3_none",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7111111111111111,
     "source_value_text": "0.7111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "79ZP6iwoBaF5t9a5VRqPnw",
     "source_model_name": "MiniMax-M3",
     "p": 0.7108219330441553,
     "p_star": 0.7062388475431954,
     "y": 0.8771864606986053,
     "v": 0.10265166642248823,
     "family_factor": 1.0,
     "w": 2.4672878778978307
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9090909090909091,
     "source_value_text": "0.9090909090909091",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "hDESmyGFrbZDomjff3rqzD",
     "source_model_name": "MiniMax-M3",
     "p": 0.8787878787878788,
     "p_star": 0.8768844221105527,
     "y": 1.9632516240918003,
     "v": 0.06391824469790049,
     "family_factor": 0.5,
     "w": 1.7610921537552942
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.9151233333333333,
     "source_value_text": "0.915123",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "minimax/minimax-m3-20260531",
     "source_model_name": "minimax/minimax-m3-20260531",
     "p": 0.886831111111111,
     "p_star": 0.8848872361809045,
     "y": 2.0395480172630496,
     "v": 0.06757493284991065,
     "family_factor": 0.5,
     "w": 1.2990258347928259
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7388889166666667,
     "source_value_text": "0.738889",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "minimax/minimax-m3-20260531",
     "source_model_name": "minimax/minimax-m3-20260531",
     "p": 0.7388889166666667,
     "p_star": 0.7342048202614379,
     "y": 1.016062025170114,
     "v": 0.09850659786779437,
     "family_factor": 1.0,
     "w": 3.5621323864382655
    }
   ]
  },
  {
   "slug": "gpt-oss-120b",
   "name": "gpt-oss-120b",
   "tier": "main",
   "rank": 64,
   "theta": 0.38690217525339793,
   "se": 0.26152195029480074,
   "si_iq": 105.80353262880097,
   "si_iq_low": 99.3510512383479,
   "si_iq_high": 112.25601401925402,
   "si_iq_display": 106,
   "domains": {},
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.02,
     "source_value_text": "0.02",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "58MQQiJ7vvgvP9e8LcG6eV",
     "source_model_name": "gpt-oss-120b_medium",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8888888888888888,
     "source_value_text": "0.8888888888888888",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-12-11",
     "source_row_id": "3QjP5HPi8tKUzHtNJktfv4",
     "source_model_name": "openai/gpt-oss-120b_high",
     "p": 0.8887776665554443,
     "p_star": 0.8803259781520651,
     "y": 1.995520706756699,
     "v": 0.2020910093434368,
     "family_factor": 1.0,
     "w": 1.6551303565329458
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.418,
     "source_value_text": "41.8",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-08-06",
     "source_row_id": "2025-08-06-04-54-48--gpt-oss-120b-high-polyglot",
     "source_model_name": "gpt-oss-120b (high)",
     "p": 0.418,
     "p_star": 0.41836283185840706,
     "y": -0.3294977560714239,
     "v": 0.018103410300317473,
     "family_factor": 1.0,
     "w": 1.4308730421411822
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7575757575757576,
     "source_value_text": "0.7575757575757576",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-12-11",
     "source_row_id": "LC5Rhog6wt2PT84CtJ483h",
     "source_model_name": "openai/gpt-oss-120b_high",
     "p": 0.6767676767676768,
     "p_star": 0.6758793969849246,
     "y": 0.7348989752401669,
     "v": 0.03407977379566213,
     "family_factor": 0.5,
     "w": 2.153010304408437
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7578456145038168,
     "source_value_text": "0.7578456145038168",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "openai/gpt-oss-120b",
     "source_model_name": "openai/gpt-oss-120b",
     "p": 0.6771274860050891,
     "p_star": 0.6762373981357168,
     "y": 0.7365336581340769,
     "v": 0.0340934332443439,
     "family_factor": 0.5,
     "w": 1.529462852560333
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.633333,
     "source_value_text": "0.633333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "openai/gpt-oss-120b",
     "source_model_name": "openai/gpt-oss-120b",
     "p": 0.633333,
     "p_star": 0.6307186274509805,
     "y": 0.5353009671023357,
     "v": 0.08253470309153106,
     "family_factor": 1.0,
     "w": 3.873821082843477
    }
   ]
  },
  {
   "slug": "gpt-5-nano",
   "name": "GPT-5 nano",
   "tier": "main",
   "rank": 65,
   "theta": 0.3639995990111502,
   "se": 0.12786442484327917,
   "si_iq": 105.45999398516726,
   "si_iq_low": 102.30521932524975,
   "si_iq_high": 108.61476864508477,
   "si_iq_display": 105,
   "domains": {
    "reasoning": {
     "si_iq": 112.27336434233408,
     "n": 2
    },
    "math": {
     "si_iq": 106.38184113726078,
     "n": 4
    },
    "knowledge": {
     "si_iq": 95.13847266306512,
     "n": 2
    },
    "agentic": {
     "si_iq": 97.4084400761873,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.22,
     "source_value_text": "0.22",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "gQHCk4faPpTNupNZ3xmr4c",
     "source_model_name": "gpt-5-nano-2025-08-07_high",
     "p": 0.17929292929292928,
     "p_star": 0.18246824682468246,
     "y": -1.499713575938965,
     "v": 0.08451059630927527,
     "family_factor": 1.0,
     "w": 3.8323369786378034
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.09,
     "source_value_text": "0.09",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "ZwQdGcba6Hez4ztMzmZP9j",
     "source_model_name": "gpt-5-nano-2025-08-07_medium",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.024390243902439025,
     "source_value_text": "0.024390243902439025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "P5v3FUnVVTbaqaCr43deKi",
     "source_model_name": "gpt-5-nano-2025-08-07_high",
     "p": 0.024390243902439025,
     "p_star": 0.03571428571428571,
     "y": -3.295836866004329,
     "v": 0.6748971193415636,
     "family_factor": 1.0,
     "w": 0.6452469463621882
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.2,
     "source_value_text": "0.2",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "JH3PjDrbrQndEcc8fh5Qre",
     "source_model_name": "gpt-5-nano-2025-08-07_high",
     "p": 0.2,
     "p_star": 0.20104895104895104,
     "y": -1.3797512625309547,
     "v": 0.021691561221577397,
     "family_factor": 1.0,
     "w": 4.108748338675631
    },
    {
     "benchmark": "math_level_5",
     "score": 0.952416918429003,
     "source_value_text": "0.952416918429003",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-08-20",
     "source_row_id": "SSLfQCm7RvLhSv5aPKaLNk",
     "source_model_name": "gpt-5-nano-2025-08-07_medium",
     "p": 0.952416918429003,
     "p_star": 0.9520754716981132,
     "y": 2.989016862182467,
     "v": 0.016528255014496566,
     "family_factor": 1.0,
     "w": 4.290804834739849
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8111111111111111,
     "source_value_text": "0.8111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-31",
     "source_row_id": "Y9YnaJQWpPFAPhe6jtKMhH",
     "source_model_name": "gpt-5-nano-2025-08-07_high",
     "p": 0.8109220331442554,
     "p_star": 0.8041628585106847,
     "y": 1.412518405939042,
     "v": 0.13520664631854779,
     "family_factor": 1.0,
     "w": 2.1257902692206843
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6944444444444444,
     "source_value_text": "0.6944444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-30",
     "source_row_id": "2pSDjMSGDh4HsAxkqUuNQP",
     "source_model_name": "gpt-5-nano-2025-08-07_high",
     "p": 0.5925925925925926,
     "p_star": 0.5921273031825796,
     "y": 0.37276654281398297,
     "v": 0.03235654785815131,
     "family_factor": 0.5,
     "w": 2.181041582500254
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.6843435000000001,
     "source_value_text": "0.684344",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "openai/gpt-5-nano-2025-08-07",
     "source_model_name": "openai/gpt-5-nano-2025-08-07",
     "p": 0.5791246666666668,
     "p_star": 0.578727055276382,
     "y": 0.3175500109338968,
     "v": 0.03232001037551953,
     "family_factor": 0.5,
     "w": 1.5439699559451225
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.117,
     "source_value_text": "0.117",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "KgUCEfVCyRnY8B5kVChyiD",
     "source_model_name": "gpt-5-nano-2025-08-07_high",
     "p": 0.117,
     "p_star": 0.11738261738261738,
     "y": -2.0174529581755376,
     "v": 0.009632867343375595,
     "family_factor": 1.0,
     "w": 1.6639358412274217
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5145000000000001,
     "source_value_text": "51.45%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "24",
     "source_model_name": "GPT-5-nano-2025-08-07 (FC)",
     "p": 0.5145000000000001,
     "p_star": 0.5143564356435645,
     "y": 0.05744153153386479,
     "v": 0.039244196028683585,
     "family_factor": 1.0,
     "w": 5.078177772241847
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.4511785656565656,
     "source_value_text": "0.451179",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5-nano-2025-08-07",
     "source_model_name": "openai/gpt-5-nano-2025-08-07",
     "p": 0.4511785656565656,
     "p_star": 0.45213584868290746,
     "y": -0.19204467230006902,
     "v": 0.07760466449907612,
     "family_factor": 1.0,
     "w": 3.981352534748465
    }
   ]
  },
  {
   "slug": "o3-mini",
   "name": "o3-mini",
   "tier": "main",
   "rank": 66,
   "theta": 0.32266915302019644,
   "se": 0.13615413786677577,
   "si_iq": 104.84003729530295,
   "si_iq_low": 101.48073212100218,
   "si_iq_high": 108.1993424696037,
   "si_iq_display": 105,
   "domains": {
    "reasoning": {
     "si_iq": 105.30350668252508,
     "n": 2
    },
    "math": {
     "si_iq": 105.93391627011296,
     "n": 4
    },
    "knowledge": {
     "si_iq": 101.09656033811858,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.15,
     "source_value_text": "0.15",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "65oGRSHSEY6edS9mqbsCfE",
     "source_model_name": "o3-mini-2025-01-31_high",
     "p": 0.10563973063973063,
     "p_star": 0.10954428776210953,
     "y": -2.095404445967328,
     "v": 0.14837600336739748,
     "family_factor": 1.0,
     "w": 2.8469206831571245
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.07,
     "source_value_text": "0.07",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "JSmdEXGULNBJ7PfSoVoa7W",
     "source_model_name": "o3-mini-2025-01-31_high",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.0,
     "source_value_text": "0.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "iR3Ut7aYEtz8dTYQFzq7rG",
     "source_model_name": "o3-mini-2025-01-31_high",
     "p": 0.0,
     "p_star": 0.011904761904761904,
     "y": -4.418840607796598,
     "v": 1.9759036144578312,
     "family_factor": 1.0,
     "w": 0.24085896691816602
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.18596491228070175,
     "source_value_text": "0.18596491228070175",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "mRJaJyBY2M2GGdbdMmT6iq",
     "source_model_name": "o3-mini-2025-01-31_high",
     "p": 0.18596491228070175,
     "p_star": 0.18706293706293706,
     "y": -1.4692085711254501,
     "v": 0.022912270123605666,
     "family_factor": 1.0,
     "w": 4.06794211429973
    },
    {
     "benchmark": "math_level_5",
     "score": 0.9648791540785498,
     "source_value_text": "0.9648791540785498",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-13",
     "source_row_id": "3VDhPT5WvzjJZkRc36Kuvi",
     "source_model_name": "o3-mini-2025-01-31_high",
     "p": 0.9648791540785498,
     "p_star": 0.9645283018867925,
     "y": 3.302904033227423,
     "v": 0.022042420004661573,
     "family_factor": 1.0,
     "w": 4.096936130739638
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7694444444444445,
     "source_value_text": "0.7694444444444445",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-27",
     "source_row_id": "Mjx6vYbgAb2DHXK8xcupX8",
     "source_model_name": "o3-mini-2025-01-31_high",
     "p": 0.769213658102547,
     "p_star": 0.7633611872742307,
     "y": 1.1711963153604372,
     "v": 0.117882657658621,
     "family_factor": 1.0,
     "w": 2.2948132052960406
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.5379999999999999,
     "source_value_text": "53.8",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-01-31",
     "source_row_id": "2025-01-31-20-27-46--o3-mini-diff2",
     "source_model_name": "o3-mini (medium)",
     "p": 0.5379999999999999,
     "p_star": 0.5378318584070796,
     "y": 0.1516172127595573,
     "v": 0.017722260281323163,
     "family_factor": 1.0,
     "w": 1.43197749768281
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7702020202020202,
     "source_value_text": "0.7702020202020202",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-13",
     "source_row_id": "MzsTvCEEfEpzn4WvxYdJkX",
     "source_model_name": "o3-mini-2025-01-31_high",
     "p": 0.6936026936026937,
     "p_star": 0.6926298157453937,
     "y": 0.8124428469691216,
     "v": 0.03478777851532408,
     "family_factor": 1.0,
     "w": 4.283402216054674
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.153,
     "source_value_text": "0.153",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "UCba4H3NNtUiWXMisWnh9g",
     "source_model_name": "o3-mini-2025-01-31_high",
     "p": 0.153,
     "p_star": 0.15334665334665334,
     "y": -1.7085902722273536,
     "v": 0.007686912071334542,
     "family_factor": 1.0,
     "w": 1.6733202979725479
    }
   ]
  },
  {
   "slug": "claude-haiku-4-5",
   "name": "Claude Haiku 4.5",
   "tier": "main",
   "rank": 67,
   "theta": 0.2462361506920369,
   "se": 0.17432646694347975,
   "si_iq": 103.69354226038055,
   "si_iq_low": 99.3924184635128,
   "si_iq_high": 107.99466605724831,
   "si_iq_display": 104,
   "domains": {
    "math": {
     "si_iq": 104.72976958463725,
     "n": 2
    },
    "knowledge": {
     "si_iq": 97.05679303521589,
     "n": 2
    },
    "agentic": {
     "si_iq": 113.55271468224578,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.08,
     "source_value_text": "0.08",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "6bmTzBjpMySeHn65gc5Hu5",
     "source_model_name": "claude-haiku-4-5-20251001_59K",
     "p": 0.03198653198653199,
     "p_star": 0.03662032869953662,
     "y": -3.2698440778146587,
     "v": 0.6738631312623583,
     "family_factor": 1.0,
     "w": 0.9137362314096615
    },
    {
     "benchmark": "math_level_5",
     "score": 0.9636087945413192,
     "source_value_text": "0.9636087945413192",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-22",
     "source_row_id": "Qwci6JAG4DUWqA9eSHThDJ",
     "source_model_name": "claude-haiku-4-5-20251001_32K",
     "p": 0.9636087945413192,
     "p_star": 0.9632589011114767,
     "y": 3.266426234964096,
     "v": 0.021308901223231744,
     "family_factor": 1.0,
     "w": 4.121709082830646
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6666666666666666,
     "source_value_text": "0.6666666666666666",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-22",
     "source_row_id": "neZvEzLi6yeL9z5KjGef7H",
     "source_model_name": "claude-haiku-4-5-20251001_32K",
     "p": 0.666332999666333,
     "p_star": 0.6627170648909779,
     "y": 0.6754260011478863,
     "v": 0.09528615734908652,
     "family_factor": 1.0,
     "w": 2.560345324969542
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7121212121212122,
     "source_value_text": "0.7121212121212122",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-22",
     "source_row_id": "GEaAdb9UmoUFbEtBx7WzAR",
     "source_model_name": "claude-haiku-4-5-20251001_32K",
     "p": 0.6161616161616162,
     "p_star": 0.6155778894472362,
     "y": 0.47082028915229174,
     "v": 0.03256943593764037,
     "family_factor": 0.5,
     "w": 2.177539133006521
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7310605833333333,
     "source_value_text": "0.731061",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.5-haiku-20251001",
     "source_model_name": "anthropic/claude-4.5-haiku-20251001",
     "p": 0.6414141111111111,
     "p_star": 0.640703487437186,
     "y": 0.578418783923614,
     "v": 0.03301925226480488,
     "family_factor": 0.5,
     "w": 1.5382172182239493
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.132,
     "source_value_text": "0.132",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "J2kUEjR9r6Spd594qDNTTf",
     "source_model_name": "claude-haiku-4-5-20251001",
     "p": 0.132,
     "p_star": 0.13236763236763235,
     "y": -1.880184940254883,
     "v": 0.008689890398757345,
     "family_factor": 1.0,
     "w": 1.6684702089287684
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.687,
     "source_value_text": "68.70%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "6",
     "source_model_name": "Claude-Haiku-4-5-20251001 (FC)",
     "p": 0.687,
     "p_star": 0.6851485148514852,
     "y": 0.7775345728374929,
     "v": 0.045442978151016104,
     "family_factor": 1.0,
     "w": 4.8617457520179865
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6657576363636364,
     "source_value_text": "0.665758",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "anthropic/claude-4.5-haiku-20251001",
     "source_model_name": "anthropic/claude-4.5-haiku-20251001",
     "p": 0.6657576363636364,
     "p_star": 0.662507486631016,
     "y": 0.6744885309155157,
     "v": 0.08597550164665697,
     "family_factor": 1.0,
     "w": 3.8021501484104645
    }
   ]
  },
  {
   "slug": "claude-3-7-sonnet",
   "name": "Claude 3.7 Sonnet",
   "tier": "main",
   "rank": 68,
   "theta": -0.06458283482775183,
   "se": 0.1747797750142745,
   "si_iq": 99.03125747758372,
   "si_iq_low": 94.71894929681378,
   "si_iq_high": 103.34356565835367,
   "si_iq_display": 99,
   "domains": {
    "math": {
     "si_iq": 96.8615937423144,
     "n": 2
    },
    "coding": {
     "si_iq": 101.7428495971097,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.9116314199395771,
     "source_value_text": "0.9116314199395771",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-13",
     "source_row_id": "epCyFNTf6vyUi5Dby7GeTq",
     "source_model_name": "claude-3-7-sonnet-20250219_64K",
     "p": 0.9116314199395771,
     "p_star": 0.9113207547169812,
     "y": 2.3298690519425143,
     "v": 0.009331747500110128,
     "family_factor": 1.0,
     "w": 4.57323706455434
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5777777777777777,
     "source_value_text": "0.5777777777777777",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-13",
     "source_row_id": "QW3FUBn5qtAFEX4oQuzEAV",
     "source_model_name": "claude-3-7-sonnet-20250219_64K",
     "p": 0.5773551329106884,
     "p_star": 0.575673499586543,
     "y": 0.3050374519432639,
     "v": 0.08721174326270069,
     "family_factor": 1.0,
     "w": 2.6707726304240764
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.649,
     "source_value_text": "64.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-02-24",
     "source_row_id": "2025-02-24-21-47-23--sonnet37-diff-think-32k-64k",
     "source_model_name": "claude-3-7-sonnet-20250219 (32k thinking tokens)",
     "p": 0.649,
     "p_star": 0.6483407079646017,
     "y": 0.6117535555656265,
     "v": 0.019321473848465647,
     "family_factor": 1.0,
     "w": 1.4273548625499481
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.609504132231405,
     "source_value_text": "0.609504132231405",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-04",
     "source_row_id": "cnM8U6moeqrp74wnXRj2Jj",
     "source_model_name": "claude-3-7-sonnet-20250219",
     "p": 0.609504132231405,
     "p_star": 0.6092778840243153,
     "y": 0.4442778527567834,
     "v": 0.008661098927228529,
     "family_factor": 1.0,
     "w": 6.507451039678002
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7973484848484849,
     "source_value_text": "0.7973484848484849",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-26",
     "source_row_id": "2t26VSNdsAE5pefQEMP25x",
     "source_model_name": "claude-3-7-sonnet-20250219_64K",
     "p": 0.7297979797979798,
     "p_star": 0.7286432160804021,
     "y": 0.9877496958563003,
     "v": 0.0368555951909103,
     "family_factor": 1.0,
     "w": 4.218682242287835
    }
   ]
  },
  {
   "slug": "claude-opus-4",
   "name": "Claude Opus 4",
   "tier": "main",
   "rank": 69,
   "theta": -0.14747512554673003,
   "se": 0.17415327641632236,
   "si_iq": 97.78787311679905,
   "si_iq_low": 93.49102241690164,
   "si_iq_high": 102.08472381669645,
   "si_iq_display": 98,
   "domains": {
    "math": {
     "si_iq": 93.90244941487346,
     "n": 2
    },
    "coding": {
     "si_iq": 108.20022748871997,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.850453172205438,
     "source_value_text": "0.850453172205438",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-22",
     "source_row_id": "YbrpPbWuYAXNqbSfU4so7f",
     "source_model_name": "claude-opus-4-20250514",
     "p": 0.850453172205438,
     "p_star": 0.8501886792452831,
     "y": 1.7360816597450544,
     "v": 0.005921016590250225,
     "family_factor": 1.0,
     "w": 4.7204985006348945
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6444444444444445,
     "source_value_text": "0.6444444444444445",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-28",
     "source_row_id": "VrRccga4uRVuCjNp637MeY",
     "source_model_name": "claude-opus-4-20250514_27K",
     "p": 0.6440885329774219,
     "p_star": 0.6409561735648692,
     "y": 0.5795166223658058,
     "v": 0.09255476315626501,
     "family_factor": 1.0,
     "w": 2.5966638882582833
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.72,
     "source_value_text": "72.0",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-05-25",
     "source_row_id": "2025-05-25-20-40-51--opus4-diff-exuser",
     "source_model_name": "claude-opus-4-20250514 (32k thinking)",
     "p": 0.72,
     "p_star": 0.7190265486725663,
     "y": 0.939638095871146,
     "v": 0.021804966686856442,
     "family_factor": 1.0,
     "w": 1.4202350249545832
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7066115702479339,
     "source_value_text": "0.7066115702479339",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-06",
     "source_row_id": "RbcvuVChvxK6SMQbPK8iRn",
     "source_model_name": "claude-opus-4-20250514",
     "p": 0.7066115702479339,
     "p_star": 0.7061846868383307,
     "y": 0.8769254159493165,
     "v": 0.009937192085292075,
     "family_factor": 1.0,
     "w": 6.431915967418523
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7626262626262627,
     "source_value_text": "0.7626262626262627",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-22",
     "source_row_id": "CtxFusPxCraL3EeRJu2c5k",
     "source_model_name": "claude-opus-4-20250514_16K",
     "p": 0.6835016835016835,
     "p_star": 0.6825795644891123,
     "y": 0.7656519081584366,
     "v": 0.03434583383277137,
     "family_factor": 1.0,
     "w": 4.297492915993879
    }
   ]
  },
  {
   "slug": "claude-sonnet-4",
   "name": "Claude Sonnet 4",
   "tier": "main",
   "rank": 70,
   "theta": -0.1934329755689458,
   "se": 0.1749522590903353,
   "si_iq": 97.09850536646582,
   "si_iq_low": 92.7819415188592,
   "si_iq_high": 101.41506921407243,
   "si_iq_display": 97,
   "domains": {
    "math": {
     "si_iq": 94.5350895186919,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8436555891238671,
     "source_value_text": "0.8436555891238671",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-22",
     "source_row_id": "dZLNhNKQVUgnB5ygAEUCcT",
     "source_model_name": "claude-sonnet-4-20250514",
     "p": 0.8436555891238671,
     "p_star": 0.8433962264150944,
     "y": 1.6837179868169712,
     "v": 0.005709819142341179,
     "family_factor": 1.0,
     "w": 4.729929575669184
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7111111111111111,
     "source_value_text": "0.7111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-22",
     "source_row_id": "FZHzYjwAQexVykNQTnRtwT",
     "source_model_name": "claude-sonnet-4-20250514_32K",
     "p": 0.7108219330441553,
     "p_star": 0.7062388475431954,
     "y": 0.8771864606986053,
     "v": 0.10265166642248823,
     "family_factor": 1.0,
     "w": 2.4672878778978307
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.613,
     "source_value_text": "61.3",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-05-24",
     "source_row_id": "2025-05-24-22-10-36--sonnet4-diff-exuser-think32k",
     "source_model_name": "claude-sonnet-4-20250514 (32k thinking)",
     "p": 0.613,
     "p_star": 0.6125,
     "y": 0.4578330936254806,
     "v": 0.018560421725777917,
     "family_factor": 1.0,
     "w": 1.4295510075669062
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7918781725888325,
     "source_value_text": "0.7918781725888325",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-26",
     "source_row_id": "J9wjcQqKJ7hCSYnnoa5E9i",
     "source_model_name": "claude-sonnet-4-20250514_59K",
     "p": 0.7225042301184433,
     "p_star": 0.7213861184093054,
     "y": 0.9513476393680855,
     "v": 0.03637120421058923,
     "family_factor": 0.5,
     "w": 2.116833507967199
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7672559999999999,
     "source_value_text": "0.7672559999999999",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-09-01",
     "source_row_id": "anthropic/claude-4-sonnet-20250522",
     "source_model_name": "anthropic/claude-4-sonnet-20250522",
     "p": 0.6896746666666665,
     "p_star": 0.6887215276381908,
     "y": 0.7941490993675676,
     "v": 0.03460962095181457,
     "family_factor": 0.5,
     "w": 1.5252913738778828
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.64,
     "source_value_text": "0.64",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-09-01",
     "source_row_id": "anthropic/claude-4-sonnet-20250522",
     "source_model_name": "anthropic/claude-4-sonnet-20250522",
     "p": 0.64,
     "p_star": 0.6372549019607843,
     "y": 0.5634693572514125,
     "v": 0.08316008316008315,
     "family_factor": 1.0,
     "w": 3.860594344503171
    }
   ]
  },
  {
   "slug": "qwen3-32b",
   "name": "Qwen3-32B",
   "tier": "main",
   "rank": 71,
   "theta": -0.3592145531091748,
   "se": 0.22742703334482423,
   "si_iq": 94.61178170336238,
   "si_iq_low": 89.00051772078187,
   "si_iq_high": 100.22304568594289,
   "si_iq_display": 95,
   "domains": {
    "agentic": {
     "si_iq": 92.11116481907796,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6694444444444444,
     "source_value_text": "0.6694444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "BAi4jidcT3F6reBkSXDJKv",
     "source_model_name": "Qwen3-32B",
     "p": 0.6691135580024469,
     "p_star": 0.6654371763067415,
     "y": 0.6876195569727444,
     "v": 0.09566760839433505,
     "family_factor": 1.0,
     "w": 2.5553539704555206
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.4,
     "source_value_text": "40.0",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-05-08",
     "source_row_id": "2025-05-08-03-20-24--qwen3-32b-default",
     "source_model_name": "Qwen3 32B",
     "p": 0.4,
     "p_star": 0.4004424778761062,
     "y": -0.40362178961387507,
     "v": 0.01834824978084035,
     "family_factor": 1.0,
     "w": 1.430164470880459
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6571969696969697,
     "source_value_text": "0.6571969696969697",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "Ffoxqm7YsZr3FimCGsGAJv",
     "source_model_name": "Qwen3-32B",
     "p": 0.5429292929292929,
     "p_star": 0.542713567839196,
     "y": 0.17127172060736964,
     "v": 0.032520463076018635,
     "family_factor": 0.5,
     "w": 2.178343841352397
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.5572391666666667,
     "source_value_text": "0.5572391666666667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-08",
     "source_row_id": "qwen/qwen3-32b-04-28",
     "source_model_name": "qwen/qwen3-32b-04-28",
     "p": 0.4096522222222223,
     "p_star": 0.410106231155779,
     "y": -0.3635262413643118,
     "v": 0.03746607192279553,
     "family_factor": 0.5,
     "w": 1.5026127200328405
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.48710000000000003,
     "source_value_text": "48.71%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "29",
     "source_model_name": "Qwen3-32B (FC)",
     "p": 0.48710000000000003,
     "p_star": 0.4872277227722772,
     "y": -0.05110022555791333,
     "v": 0.03923744536136686,
     "family_factor": 1.0,
     "w": 5.0784239782005
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.4516665,
     "source_value_text": "0.4516665",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-09",
     "source_row_id": "qwen/qwen3-32b-04-28",
     "source_model_name": "qwen/qwen3-32b-04-28",
     "p": 0.4516665,
     "p_star": 0.4526142156862745,
     "y": -0.19011368515604157,
     "v": 0.0775903922627841,
     "family_factor": 1.0,
     "w": 3.981672500279335
    }
   ]
  },
  {
   "slug": "gpt-4-1-mini",
   "name": "GPT-4.1 mini",
   "tier": "main",
   "rank": 72,
   "theta": -0.5760112728981273,
   "se": 0.14099121772252252,
   "si_iq": 91.35983090652809,
   "si_iq_low": 87.88118137999166,
   "si_iq_high": 94.83848043306452,
   "si_iq_display": 91,
   "domains": {
    "reasoning": {
     "si_iq": 89.89274062930836,
     "n": 2
    },
    "math": {
     "si_iq": 92.14723549517288,
     "n": 3
    },
    "knowledge": {
     "si_iq": 89.40879570096934,
     "n": 2
    },
    "agentic": {
     "si_iq": 91.54484738458359,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.01,
     "source_value_text": "0.01",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "ZyRri9YZ8CNz6CrUWXFjBA",
     "source_model_name": "gpt-4.1-mini-2025-04-14",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 22.969328441965256,
     "family_factor": 1.0,
     "w": 0.03065138124698309
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.07,
     "source_value_text": "0.07",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "giKk2ut3JVFVQUvbykxvSu",
     "source_model_name": "gpt-4.1-mini-2025-04-14",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.06666666666666667,
     "source_value_text": "0.06666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "6EQrp2MY4QMYLfTxpioYTe",
     "source_model_name": "gpt-4.1-mini-2025-04-14",
     "p": 0.06666666666666667,
     "p_star": 0.06818181818181818,
     "y": -2.6149597780361984,
     "v": 0.05484196853802857,
     "family_factor": 1.0,
     "w": 3.2290987044458945
    },
    {
     "benchmark": "math_level_5",
     "score": 0.8729229607250756,
     "source_value_text": "0.8729229607250756",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "6ybVweWdTfiCuirnS2BKXD",
     "source_model_name": "gpt-4.1-mini-2025-04-14",
     "p": 0.8729229607250756,
     "p_star": 0.8726415094339622,
     "y": 1.9245189590739955,
     "v": 0.006785665665665663,
     "family_factor": 1.0,
     "w": 4.682276379354564
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.44722222222222224,
     "source_value_text": "0.44722222222222224",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "cXbbdQDW2jeYassmRuZYpU",
     "source_model_name": "gpt-4.1-mini-2025-04-14",
     "p": 0.4466688911133356,
     "p_star": 0.4478282630456544,
     "y": -0.20944929805601276,
     "v": 0.08619475598217637,
     "family_factor": 1.0,
     "w": 2.6853602689426057
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.324,
     "source_value_text": "32.4",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-14",
     "source_row_id": "2025-04-14-21-27-53--gpt41mini-diff",
     "source_model_name": "gpt-4.1-mini",
     "p": 0.324,
     "p_star": 0.3247787610619469,
     "y": -0.7318961832298867,
     "v": 0.020087779130850903,
     "family_factor": 1.0,
     "w": 1.4251503657911868
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6584595959595959,
     "source_value_text": "0.6584595959595959",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "dXHddeGRX7JRVa5UNfad5C",
     "source_model_name": "gpt-4.1-mini-2025-04-14",
     "p": 0.5446127946127945,
     "p_star": 0.5443886097152428,
     "y": 0.17802311603373996,
     "v": 0.0325014966933519,
     "family_factor": 0.5,
     "w": 2.1786556514368556
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.6473065000000001,
     "source_value_text": "0.647307",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4.1-mini-2025-04-14",
     "source_model_name": "openai/gpt-4.1-mini-2025-04-14",
     "p": 0.5297420000000002,
     "p_star": 0.529592542713568,
     "y": 0.11850867401109187,
     "v": 0.03270202223173324,
     "family_factor": 0.5,
     "w": 1.5408217820060874
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.127,
     "source_value_text": "0.127",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "gYV4CJTjSd7VonfzMmnwcw",
     "source_model_name": "gpt-4.1-mini-2025-04-14",
     "p": 0.127,
     "p_star": 0.12737262737262736,
     "y": -1.9243917649756306,
     "v": 0.008978977967832813,
     "family_factor": 1.0,
     "w": 1.6670774874036531
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5045000000000001,
     "source_value_text": "50.45%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "27",
     "source_model_name": "GPT-4.1-mini-2025-04-14 (FC)",
     "p": 0.5045000000000001,
     "p_star": 0.5044554455445545,
     "y": 0.017822253907504283,
     "v": 0.039214955799842945,
     "family_factor": 1.0,
     "w": 5.079244375174705
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.44333325,
     "source_value_text": "0.443333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4.1-mini-2025-04-14",
     "source_model_name": "openai/gpt-4.1-mini-2025-04-14",
     "p": 0.44333325,
     "p_star": 0.4444443627450981,
     "y": -0.22314388219656878,
     "v": 0.07785467414258311,
     "family_factor": 1.0,
     "w": 3.9757559625319256
    }
   ]
  },
  {
   "slug": "gpt-4-1",
   "name": "GPT-4.1",
   "tier": "main",
   "rank": 73,
   "theta": -0.6072819047130231,
   "se": 0.13930784101069046,
   "si_iq": 90.89077142930465,
   "si_iq_low": 87.45365553653768,
   "si_iq_high": 94.32788732207163,
   "si_iq_display": 91,
   "domains": {
    "math": {
     "si_iq": 89.5405923411597,
     "n": 3
    },
    "coding": {
     "si_iq": 91.06541333684507,
     "n": 2
    },
    "knowledge": {
     "si_iq": 94.9829730834305,
     "n": 2
    },
    "agentic": {
     "si_iq": 95.41579157303616,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.03,
     "source_value_text": "0.03",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "TzdbTbqAFB73Tfet8GFzQQ",
     "source_model_name": "gpt-4.1-2025-04-14",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 22.969328441965256,
     "family_factor": 1.0,
     "w": 0.03065138124698309
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.05964912280701754,
     "source_value_text": "0.05964912280701754",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "kCG2nzspryMy7LBwWPqwXy",
     "source_model_name": "gpt-4.1-2025-04-14",
     "p": 0.05964912280701754,
     "p_star": 0.06118881118881119,
     "y": -2.730650033019451,
     "v": 0.06065442936951317,
     "family_factor": 1.0,
     "w": 3.1122702434177842
    },
    {
     "benchmark": "math_level_5",
     "score": 0.8300604229607251,
     "source_value_text": "0.8300604229607251",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "YyJXPVXJjN5EnLfYjfCTrQ",
     "source_model_name": "gpt-4.1-2025-04-14",
     "p": 0.8300604229607251,
     "p_star": 0.829811320754717,
     "y": 1.5842906510520829,
     "v": 0.005340060842007402,
     "family_factor": 1.0,
     "w": 4.746532287938555
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.38333333333333336,
     "source_value_text": "0.38333333333333336",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "VAQtARXUPTpdxGKMekUSbX",
     "source_model_name": "gpt-4.1-2025-04-14",
     "p": 0.3827160493827161,
     "p_star": 0.38526570048309183,
     "y": -0.46725691376567796,
     "v": 0.09002766438855224,
     "family_factor": 1.0,
     "w": 2.631195839873309
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.524,
     "source_value_text": "52.4",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-14",
     "source_row_id": "2025-04-14-21-05-54--gpt41-diff-exuser",
     "source_model_name": "gpt-4.1",
     "p": 0.524,
     "p_star": 0.5238938053097345,
     "y": 0.09564807472222125,
     "v": 0.01766113232191299,
     "family_factor": 1.0,
     "w": 1.4321547863799022
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.48541666666666666,
     "source_value_text": "0.48541666666666666",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-08",
     "source_row_id": "SheUt9cNpkSevy4r6Gsr3u",
     "source_model_name": "gpt-4.1-2025-04-14",
     "p": 0.48541666666666666,
     "p_star": 0.48544679752066117,
     "y": -0.058229257242453744,
     "v": 0.008254380442748377,
     "family_factor": 1.0,
     "w": 6.5318999406265075
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6691919191919192,
     "source_value_text": "0.6691919191919192",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "Gj8pd5gU9r4LqwDK8XZ4mL",
     "source_model_name": "gpt-4.1-2025-04-14",
     "p": 0.5589225589225589,
     "p_star": 0.5586264656616415,
     "y": 0.23558949737426138,
     "v": 0.03237837254614345,
     "family_factor": 0.5,
     "w": 2.180682002977403
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.6607744999999999,
     "source_value_text": "0.660774",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4.1-2025-04-14",
     "source_model_name": "openai/gpt-4.1-2025-04-14",
     "p": 0.5476993333333332,
     "p_star": 0.5474596381909547,
     "y": 0.19041178224383085,
     "v": 0.03246918188727771,
     "family_factor": 0.5,
     "w": 1.5427390982492717
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.311,
     "source_value_text": "0.311",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "avdYKfKUuY6EvfVdxftBE8",
     "source_model_name": "gpt-4.1-2025-04-14",
     "p": 0.311,
     "p_star": 0.3111888111888112,
     "y": -0.7945673590058485,
     "v": 0.004655943253363629,
     "family_factor": 1.0,
     "w": 1.68814999253427
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5396,
     "source_value_text": "53.96%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "20",
     "source_model_name": "GPT-4.1-2025-04-14 (FC)",
     "p": 0.5396,
     "p_star": 0.5392079207920791,
     "y": 0.15715432937146756,
     "v": 0.039454449128301296,
     "family_factor": 1.0,
     "w": 5.070521490038607
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.5083332500000001,
     "source_value_text": "0.508333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4.1-2025-04-14",
     "source_model_name": "openai/gpt-4.1-2025-04-14",
     "p": 0.5083332500000001,
     "p_star": 0.5081698529411766,
     "y": 0.03268232054569858,
     "v": 0.07691403746934843,
     "family_factor": 1.0,
     "w": 3.9968947139599287
    }
   ]
  },
  {
   "slug": "llama-4-maverick",
   "name": "Llama 4 Maverick",
   "tier": "main",
   "rank": 74,
   "theta": -1.2770882045116685,
   "se": 0.17331953600460323,
   "si_iq": 80.84367693232497,
   "si_iq_low": 76.56739695119524,
   "si_iq_high": 85.1199569134547,
   "si_iq_display": 81,
   "domains": {
    "math": {
     "si_iq": 80.24743598912693,
     "n": 2
    },
    "agentic": {
     "si_iq": 80.42578283585911,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.7301737160120846,
     "source_value_text": "0.7301737160120846",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-08",
     "source_row_id": "HkjCosgMFq5QXB2CyTyU7r",
     "source_model_name": "Llama-4-Maverick-17B-128E-Instruct-FP8",
     "p": 0.7301737160120846,
     "p_star": 0.73,
     "y": 0.9946225751440619,
     "v": 0.003826217064487399,
     "family_factor": 1.0,
     "w": 4.815739358869692
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.20555555555555555,
     "source_value_text": "0.20555555555555555",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-08",
     "source_row_id": "GJEpPThqUxXJBSbvkuXVnw",
     "source_model_name": "Llama-4-Maverick-17B-128E-Instruct-FP8",
     "p": 0.20476031587142698,
     "p_star": 0.21117856987422207,
     "y": -1.3178358926434648,
     "v": 0.1282690940963611,
     "family_factor": 1.0,
     "w": 2.1903972676604693
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.156,
     "source_value_text": "15.6",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-06",
     "source_row_id": "2025-04-06-08-39-52--llama-4-maverick-17b-128e-instruct-polyglot-whole",
     "source_model_name": "Llama 4 Maverick",
     "p": 0.156,
     "p_star": 0.15752212389380532,
     "y": -1.67678148449928,
     "v": 0.03319445755830422,
     "family_factor": 1.0,
     "w": 1.388472371962454
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6698232323232324,
     "source_value_text": "0.6698232323232324",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-08",
     "source_row_id": "LyHy99ubGCqBhoaksQjkiF",
     "source_model_name": "Llama-4-Maverick-17B-128E-Instruct-FP8",
     "p": 0.5597643097643098,
     "p_star": 0.559463986599665,
     "y": 0.23898696079893586,
     "v": 0.03237324444937679,
     "family_factor": 0.5,
     "w": 2.1807664818943855
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.6478116,
     "source_value_text": "0.6478116",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-29",
     "source_row_id": "meta-llama/llama-4-maverick-17b-128e-instruct",
     "source_model_name": "meta-llama/llama-4-maverick-17b-128e-instruct",
     "p": 0.5304154666666667,
     "p_star": 0.5302626251256283,
     "y": 0.12119864125498248,
     "v": 0.032691322294685,
     "family_factor": 0.5,
     "w": 1.5409097858147485
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.3729,
     "source_value_text": "37.29%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "50",
     "source_model_name": "Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)",
     "p": 0.3729,
     "p_star": 0.37415841584158416,
     "y": -0.5144179991228098,
     "v": 0.04186367187354459,
     "family_factor": 1.0,
     "w": 4.984410538991639
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.43089426016260163,
     "source_value_text": "0.43089426016260163",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-29",
     "source_row_id": "meta-llama/llama-4-maverick-17b-128e-instruct",
     "source_model_name": "meta-llama/llama-4-maverick-17b-128e-instruct",
     "p": 0.43089426016260163,
     "p_star": 0.43224927466921725,
     "y": -0.27268001201133407,
     "v": 0.07833172331672386,
     "family_factor": 1.0,
     "w": 3.9651205519429604
    }
   ]
  },
  {
   "slug": "gemma-3-27b",
   "name": "Gemma 3 27B",
   "tier": "main",
   "rank": 75,
   "theta": -1.5477733038183439,
   "se": 0.1798430950324008,
   "si_iq": 76.78340044272484,
   "si_iq_low": 72.34616592917847,
   "si_iq_high": 81.22063495627121,
   "si_iq_display": 77,
   "domains": {
    "math": {
     "si_iq": 80.68543055680237,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.740370090634441,
     "source_value_text": "0.740370090634441",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-13",
     "source_row_id": "amrtN7UjAtuyEmv5DaGshP",
     "source_model_name": "gemma-3-27b-it",
     "p": 0.740370090634441,
     "p_star": 0.740188679245283,
     "y": 1.0469494474808976,
     "v": 0.0039215316039275284,
     "family_factor": 1.0,
     "w": 4.811322468818419
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.225,
     "source_value_text": "0.225",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "DhJ248BX3ZPBHXvkRG4Qsz",
     "source_model_name": "gemma-3-27b-it",
     "p": 0.22422422422422422,
     "p_star": 0.23021934978456718,
     "y": -1.207073055253687,
     "v": 0.12052364844795078,
     "family_factor": 1.0,
     "w": 2.267330526766669
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.049,
     "source_value_text": "4.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-03-15",
     "source_row_id": "2025-03-15-01-21-24--gemma3-27b-or",
     "source_model_name": "gemma-3-27b-it",
     "p": 0.049,
     "p_star": 0.05099557522123894,
     "y": -2.9236745925763166,
     "v": 0.09102588447449872,
     "family_factor": 1.0,
     "w": 1.246879721800662
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4772727272727273,
     "source_value_text": "0.4772727272727273",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "jdFH2zZdssYKDVJQPKXvNB",
     "source_model_name": "gemma-3-27b-it",
     "p": 0.30303030303030304,
     "p_star": 0.30402010050251255,
     "y": -0.8282269605905975,
     "v": 0.04953795495908453,
     "family_factor": 1.0,
     "w": 3.860894509006734
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.29469999999999996,
     "source_value_text": "29.47%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "69",
     "source_model_name": "Gemma-3-27b-it (Prompt)",
     "p": 0.29469999999999996,
     "p_star": 0.29673267326732666,
     "y": -0.8629054416811471,
     "v": 0.04697550335543672,
     "family_factor": 1.0,
     "w": 4.811051944326552
    }
   ]
  },
  {
   "slug": "gpt-4-1-nano",
   "name": "GPT-4.1 nano",
   "tier": "main",
   "rank": 76,
   "theta": -1.595337039208958,
   "se": 0.1699171217498752,
   "si_iq": 76.06994441186563,
   "si_iq_low": 71.87761155118409,
   "si_iq_high": 80.26227727254717,
   "si_iq_display": 76,
   "domains": {
    "math": {
     "si_iq": 80.46572833111878,
     "n": 2
    },
    "knowledge": {
     "si_iq": 71.54593987324424,
     "n": 2
    },
    "agentic": {
     "si_iq": 65.5984351450394,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.0,
     "source_value_text": "0.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "FLJ6bNrtaJQGCU2dP3CvWH",
     "source_model_name": "gpt-4.1-nano-2025-04-14",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 22.969328441965256,
     "family_factor": 1.0,
     "w": 0.03065138124698309
    },
    {
     "benchmark": "math_level_5",
     "score": 0.6999622356495468,
     "source_value_text": "0.6999622356495468",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "K4TfMXsaPd4Z46zFmiV4Rf",
     "source_model_name": "gpt-4.1-nano-2025-04-14",
     "p": 0.6999622356495468,
     "p_star": 0.699811320754717,
     "y": 0.8463995491518039,
     "v": 0.0035898884582476354,
     "family_factor": 1.0,
     "w": 4.8267259231727735
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.28888888888888886,
     "source_value_text": "0.28888888888888886",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "3qLHwibDhgtWEbKGwxUYVa",
     "source_model_name": "gpt-4.1-nano-2025-04-14",
     "p": 0.2881770659548437,
     "p_star": 0.2927819123471297,
     "y": -0.8819110820203037,
     "v": 0.10305795914523645,
     "family_factor": 1.0,
     "w": 2.4623511538514817
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.08900000000000001,
     "source_value_text": "8.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-14",
     "source_row_id": "2025-04-14-22-46-01--gpt41nano-diff",
     "source_model_name": "gpt-4.1-nano",
     "p": 0.08900000000000001,
     "p_star": 0.09081858407079647,
     "y": -2.3036807166960718,
     "v": 0.05335072962309636,
     "family_factor": 1.0,
     "w": 1.335610530645752
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.48926767676767674,
     "source_value_text": "0.48926767676767674",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-14",
     "source_row_id": "azWfeFPP6zSocuQX3JYBU5",
     "source_model_name": "gpt-4.1-nano-2025-04-14",
     "p": 0.319023569023569,
     "p_star": 0.3199329983249581,
     "y": -0.7540797315551028,
     "v": 0.04692232666359965,
     "family_factor": 0.5,
     "w": 1.9648146142946483
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.4966332500000001,
     "source_value_text": "0.496633",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4.1-nano-2025-04-14",
     "source_model_name": "openai/gpt-4.1-nano-2025-04-14",
     "p": 0.32884433333333346,
     "p_star": 0.3297044120603016,
     "y": -0.7095222590915372,
     "v": 0.045496858643799036,
     "family_factor": 0.5,
     "w": 1.44232099611042
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.06,
     "source_value_text": "0.06",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "A4JEeJR5LQfLR3Hb8z7kL2",
     "source_model_name": "gpt-4.1-nano-2025-04-14",
     "p": 0.06,
     "p_star": 0.06043956043956044,
     "y": -2.743768283704289,
     "v": 0.0175746152257679,
     "family_factor": 1.0,
     "w": 1.626703386457608
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.33049999999999996,
     "source_value_text": "33.05%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "58",
     "source_model_name": "GPT-4.1-nano-2025-04-14 (FC)",
     "p": 0.33049999999999996,
     "p_star": 0.33217821782178214,
     "y": -0.6983497192360744,
     "v": 0.04419015465449375,
     "family_factor": 1.0,
     "w": 4.90398795174959
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.11833325,
     "source_value_text": "0.118333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4.1-nano-2025-04-14",
     "source_model_name": "openai/gpt-4.1-nano-2025-04-14",
     "p": 0.11833325,
     "p_star": 0.12581691176470589,
     "y": -1.9384620678511224,
     "v": 0.17477858969365556,
     "family_factor": 1.0,
     "w": 2.5733692787887326
    }
   ]
  },
  {
   "slug": "gpt-4o-aug-2024",
   "name": "GPT-4o (Aug 2024)",
   "tier": "main",
   "rank": 77,
   "theta": -1.8188680756463844,
   "se": 0.17587550937533702,
   "si_iq": 72.71697886530424,
   "si_iq_low": 68.37763583883333,
   "si_iq_high": 77.05632189177514,
   "si_iq_display": 73,
   "domains": {
    "math": {
     "si_iq": 69.47563886830959,
     "n": 3
    },
    "knowledge": {
     "si_iq": 79.2812710207624,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.06,
     "source_value_text": "0.06",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "Cjt9Xa7iPVBf9dN5cfJ88q",
     "source_model_name": "gpt-4o-2024-08-06",
     "p": 0.010942760942760942,
     "p_star": 0.015784911824515784,
     "y": -4.132789922745794,
     "v": 2.717204443192828,
     "family_factor": 1.0,
     "w": 0.25099590585096504
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.0035087719298245615,
     "source_value_text": "0.0035087719298245615",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "ikS95CXY2foitnUPDKwNJn",
     "source_model_name": "gpt-4o-2024-08-06",
     "p": 0.0035087719298245615,
     "p_star": 0.005244755244755245,
     "y": -5.245268145458221,
     "v": 0.6678383128295255,
     "family_factor": 1.0,
     "w": 0.6511787594415198
    },
    {
     "benchmark": "math_level_5",
     "score": 0.5327605740181269,
     "source_value_text": "0.5327605740181269",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "ZQgz8AGm4KHin9MFupLu58",
     "source_model_name": "gpt-4o-2024-08-06",
     "p": 0.5327605740181269,
     "p_star": 0.5327358490566038,
     "y": 0.1311309770845989,
     "v": 0.0030295759419578213,
     "family_factor": 1.0,
     "w": 4.852975424082859
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.06388888888888888,
     "source_value_text": "0.06388888888888888",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "mBUKqiVQsqXd3qmdtKP5UP",
     "source_model_name": "gpt-4o-2024-08-06",
     "p": 0.0629518407296185,
     "p_star": 0.07245288767027896,
     "y": -2.549607062761063,
     "v": 0.3208220920514874,
     "family_factor": 1.0,
     "w": 1.1881505497074172
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.231,
     "source_value_text": "23.1",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2024-12-30",
     "source_row_id": "2024-12-30-20-44-54--gpt4o-ex-as-sys-clean-prompt",
     "source_model_name": "gpt-4o-2024-08-06",
     "p": 0.231,
     "p_star": 0.23219026548672567,
     "y": -1.1959848155189508,
     "v": 0.024709731014672845,
     "family_factor": 1.0,
     "w": 1.4119970605374952
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.49210858585858586,
     "source_value_text": "0.49210858585858586",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "fairJpL9VekDBKxYHG9ZoG",
     "source_model_name": "gpt-4o-2024-08-06",
     "p": 0.3228114478114478,
     "p_star": 0.32370184254606366,
     "y": -0.736811187069335,
     "v": 0.046357404407906574,
     "family_factor": 0.5,
     "w": 1.972398566117356
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.5280586666666666,
     "source_value_text": "0.528059",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4o-2024-08-06",
     "source_model_name": "openai/gpt-4o-2024-08-06",
     "p": 0.37074488888888874,
     "p_star": 0.3713944120603014,
     "y": -0.5262394106289239,
     "v": 0.04063791709845629,
     "family_factor": 0.5,
     "w": 1.4782073707372039
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.26,
     "source_value_text": "0.26",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "bDFqfWxMG7gLDq4Mz8PRTP",
     "source_model_name": "gpt-4o-2024-08-06",
     "p": 0.26,
     "p_star": 0.26023976023976025,
     "y": -1.044722772514432,
     "v": 0.005184026459271048,
     "family_factor": 1.0,
     "w": 1.685547347314096
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.43,
     "source_value_text": "0.43",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4o-2024-08-06",
     "source_model_name": "openai/gpt-4o-2024-08-06",
     "p": 0.43,
     "p_star": 0.43137254901960786,
     "y": -0.2762533766281581,
     "v": 0.07836990595611286,
     "family_factor": 1.0,
     "w": 3.9642717609579727
    }
   ]
  },
  {
   "slug": "gpt-4o-nov-2024",
   "name": "GPT-4o (Nov 2024)",
   "tier": "main",
   "rank": 78,
   "theta": -2.089131385351066,
   "se": 0.1901627643275167,
   "si_iq": 68.66302921973401,
   "si_iq_low": 63.97117946640641,
   "si_iq_high": 73.3548789730616,
   "si_iq_display": 69,
   "domains": {
    "math": {
     "si_iq": 68.24607724827223,
     "n": 2
    },
    "coding": {
     "si_iq": 68.07930472606665,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.49773413897280966,
     "source_value_text": "0.49773413897280966",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-05",
     "source_row_id": "D3G2BKGnh6YSvw4bEYSdiY",
     "source_model_name": "gpt-4o-2024-11-20",
     "p": 0.49773413897280966,
     "p_star": 0.4977358490566038,
     "y": -0.009056665677797055,
     "v": 0.00301665139164121,
     "family_factor": 1.0,
     "w": 4.853584282206342
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.0625,
     "source_value_text": "0.0625",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "buNVL2TWcdVgxAcMfVE8xJ",
     "source_model_name": "gpt-4o-2024-11-20",
     "p": 0.06156156156156156,
     "p_star": 0.07109283196239717,
     "y": -2.570022291612731,
     "v": 0.32656604235377523,
     "family_factor": 1.0,
     "w": 1.1721514381243734
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.182,
     "source_value_text": "18.2",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2024-12-30",
     "source_row_id": "2024-12-30-20-57-12--gpt-4o-2024-11-20-ex-as-sys",
     "source_model_name": "gpt-4o-2024-11-20",
     "p": 0.182,
     "p_star": 0.18340707964601768,
     "y": -1.4934325478947037,
     "v": 0.029413312269044218,
     "family_factor": 1.0,
     "w": 1.3988583968696964
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.30991735537190085,
     "source_value_text": "0.30991735537190085",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-11",
     "source_row_id": "PncXWJm7ZCY3qv982pKoRy",
     "source_model_name": "gpt-4o-2024-11-20",
     "p": 0.30991735537190085,
     "p_star": 0.3103100881087358,
     "y": -0.7986700117733228,
     "v": 0.009633999939154711,
     "family_factor": 1.0,
     "w": 6.449703391092011
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4788510101010101,
     "source_value_text": "0.4788510101010101",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-05",
     "source_row_id": "gULKGqAe9nG9syxmYMtkhi",
     "source_model_name": "gpt-4o-2024-11-20",
     "p": 0.30513468013468015,
     "p_star": 0.30611390284757123,
     "y": -0.8183505576767842,
     "v": 0.049171047141436136,
     "family_factor": 1.0,
     "w": 3.870390938814103
    }
   ]
  },
  {
   "slug": "gpt-4o-mini",
   "name": "GPT-4o mini",
   "tier": "main",
   "rank": 79,
   "theta": -2.1110199671403955,
   "se": 0.1734437966912658,
   "si_iq": 68.33470049289407,
   "si_iq_low": 64.05535465145184,
   "si_iq_high": 72.6140463343363,
   "si_iq_display": 68,
   "domains": {
    "reasoning": {
     "si_iq": 80.15053805436133,
     "n": 2
    },
    "math": {
     "si_iq": 69.7929619964934,
     "n": 3
    },
    "knowledge": {
     "si_iq": 64.49935041926716,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.03,
     "source_value_text": "0.03",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "QGrgPmo24qW4h9SAvELP3Y",
     "source_model_name": "gpt-4o-mini-2024-07-18",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 22.969328441965256,
     "family_factor": 1.0,
     "w": 0.03065138124698309
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.12,
     "source_value_text": "0.12",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "mbviVfQ7Bh7wHSCDDmrt7u",
     "source_model_name": "gpt-4o-mini-2024-07-18",
     "p": 0.03062348534919585,
     "p_star": 0.03527077757346124,
     "y": -3.30879267312414,
     "v": 1.1176837657418708,
     "family_factor": 1.0,
     "w": 0.5806982084184594
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.007017543859649123,
     "source_value_text": "0.007017543859649123",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "6XhtKr59amKko65T7RUB2a",
     "source_model_name": "gpt-4o-mini-2024-07-18",
     "p": 0.007017543859649123,
     "p_star": 0.008741258741258742,
     "y": -4.730921391293651,
     "v": 0.4021164021164021,
     "family_factor": 1.0,
     "w": 0.9957850368809273
    },
    {
     "benchmark": "math_level_5",
     "score": 0.5263406344410876,
     "source_value_text": "0.5263406344410876",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "5iyKgWVhAmNwrA5rNL7MbW",
     "source_model_name": "gpt-4o-mini-2024-07-18",
     "p": 0.5263406344410876,
     "p_star": 0.5263207547169811,
     "y": 0.1053804318108228,
     "v": 0.003024972120142543,
     "family_factor": 1.0,
     "w": 4.853192286399506
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.06944444444444445,
     "source_value_text": "0.06944444444444445",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-07-30",
     "source_row_id": "MPJkYPEMsQrowqtecK3mmz",
     "source_model_name": "gpt-4o-mini-2024-07-18",
     "p": 0.06851295740184629,
     "p_star": 0.07789311050180615,
     "y": -2.471323640366869,
     "v": 0.2998900657463158,
     "family_factor": 1.0,
     "w": 1.250343638987002
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.036000000000000004,
     "source_value_text": "3.6",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2024-12-21",
     "source_row_id": "2024-12-21-18-41-18--polyglot-gpt-4o-mini",
     "source_model_name": "gpt-4o-mini-2024-07-18",
     "p": 0.036000000000000004,
     "p_star": 0.03805309734513275,
     "y": -3.229976771427647,
     "v": 0.12034402344836437,
     "family_factor": 1.0,
     "w": 1.185586935550015
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.37720959595959597,
     "source_value_text": "0.37720959595959597",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "L9yfwZC3snsKZshBXTaXjc",
     "source_model_name": "gpt-4o-mini-2024-07-18",
     "p": 0.16961279461279463,
     "p_star": 0.17127303182579565,
     "y": -1.576631789559764,
     "v": 0.10378206768658205,
     "family_factor": 0.5,
     "w": 1.4165875234851226
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.4305555,
     "source_value_text": "0.430555",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4o-mini",
     "source_model_name": "openai/gpt-4o-mini",
     "p": 0.24074066666666663,
     "p_star": 0.24204347738693463,
     "y": -1.1415086573233748,
     "v": 0.0647858751874786,
     "family_factor": 0.5,
     "w": 1.3155366630745218
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.083,
     "source_value_text": "0.083",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "DLr586bZUHpghAf8m3GRSm",
     "source_model_name": "gpt-4o-mini-2024-07-18",
     "p": 0.083,
     "p_star": 0.08341658341658342,
     "y": -2.3968059480719153,
     "v": 0.013052913247075332,
     "family_factor": 1.0,
     "w": 1.6476950947151576
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.28000025,
     "source_value_text": "0.28",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-4o-mini",
     "source_model_name": "openai/gpt-4o-mini",
     "p": 0.28000025,
     "p_star": 0.2843139705882353,
     "y": -0.9231624066275108,
     "v": 0.09447326220097808,
     "family_factor": 1.0,
     "w": 3.636010283284028
    }
   ]
  },
  {
   "slug": "llama-3-3-70b",
   "name": "Llama 3.3 70B",
   "tier": "main",
   "rank": 80,
   "theta": -2.2543116300409145,
   "se": 0.1938824532984411,
   "si_iq": 66.18532554938628,
   "si_iq_low": 61.40170061681997,
   "si_iq_high": 70.96895048195259,
   "si_iq_display": 66,
   "domains": {
    "math": {
     "si_iq": 64.900806157895,
     "n": 2
    },
    "agentic": {
     "si_iq": 67.75248016917593,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.41597432024169184,
     "source_value_text": "0.41597432024169184",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "DeaDxFfiQtCTdnZPH7Awaf",
     "source_model_name": "Llama-3.3-70B-Instruct",
     "p": 0.41597432024169184,
     "p_star": 0.4160377358490566,
     "y": -0.33906039723775017,
     "v": 0.0031041215624645116,
     "family_factor": 1.0,
     "w": 4.849466659750168
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.05138888888888889,
     "source_value_text": "0.05138888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "ZjsXQpZ7SsejXDo52aetZZ",
     "source_model_name": "Llama-3.3-70B-Instruct",
     "p": 0.05043932821710599,
     "p_star": 0.060212386299342814,
     "y": -2.747775823232058,
     "v": 0.3820690578372585,
     "family_factor": 1.0,
     "w": 1.0371957956463467
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4744318181818182,
     "source_value_text": "0.4744318181818182",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "TxXS78Wg2pSCDbpmeJuzQn",
     "source_model_name": "Llama-3.3-70B-Instruct",
     "p": 0.29924242424242425,
     "p_star": 0.30025125628140703,
     "y": -0.8461016879957733,
     "v": 0.05021712546521216,
     "family_factor": 0.5,
     "w": 1.9217192027926628
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.4753785,
     "source_value_text": "0.4753785",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "meta-llama/llama-3.3-70b-instruct",
     "source_model_name": "meta-llama/llama-3.3-70b-instruct",
     "p": 0.30050466666666664,
     "p_star": 0.3015071557788944,
     "y": -0.8401311843385006,
     "v": 0.049988078825227655,
     "family_factor": 0.5,
     "w": 1.410666083403201
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.319,
     "source_value_text": "31.90%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "62",
     "source_model_name": "Llama-3.3-70B-Instruct (FC)",
     "p": 0.319,
     "p_star": 0.32079207920792085,
     "y": -0.7501341119335556,
     "v": 0.04499154159018104,
     "family_factor": 1.0,
     "w": 4.876882978354603
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.313333,
     "source_value_text": "0.313333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-10-04",
     "source_row_id": "meta-llama/llama-3.3-70b-instruct",
     "source_model_name": "meta-llama/llama-3.3-70b-instruct",
     "p": 0.313333,
     "p_star": 0.3169931372549019,
     "y": -0.7676247828585798,
     "v": 0.08878809226199978,
     "family_factor": 1.0,
     "w": 3.7455051995823228
    }
   ]
  },
  {
   "slug": "gpt-5-5-pro",
   "name": "GPT-5.5 Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": 2.5948481854257577,
   "se": 0.14020112928999415,
   "si_iq": 138.92272278138637,
   "si_iq_low": 135.4635669566289,
   "si_iq_high": 142.38187860614383,
   "si_iq_display": 139,
   "domains": {
    "math": {
     "si_iq": 138.969682811899,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.62,
     "source_value_text": "0.62",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "5u4XrDnQSRnuXSK6oXKAth",
     "source_model_name": "gpt-5.5-pro_xhigh",
     "p": 0.6001683501683501,
     "p_star": 0.5991765843250991,
     "y": 0.402035382803592,
     "v": 0.04437302248025652,
     "family_factor": 1.0,
     "w": 4.897776392284414
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.7804878048780488,
     "source_value_text": "0.7804878048780488",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "SFKXCPUu73mwxMoUotiZM2",
     "source_model_name": "gpt-5.5-pro_xhigh",
     "p": 0.7804878048780488,
     "p_star": 0.7738095238095238,
     "y": 1.2299482907291968,
     "v": 0.1327935222672065,
     "family_factor": 1.0,
     "w": 2.1478260869565213
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8771929824561403,
     "source_value_text": "0.8771929824561403",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "LSKDetgzyVojru45w7RJhf",
     "source_model_name": "gpt-5.5-pro_xhigh",
     "p": 0.8771929824561403,
     "p_star": 0.8758741258741258,
     "y": 1.953926224043549,
     "v": 0.03204857889854094,
     "family_factor": 1.0,
     "w": 3.7864852781503484
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-24",
     "source_row_id": "YxbseUDNgFUjokfYXui62r",
     "source_model_name": "gpt-5.5-pro-pre-release_xhigh",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9392135642135643,
     "source_value_text": "0.9392135642135643",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-24",
     "source_row_id": "cBmhJzrC3SkfZ7uVgGVYZX",
     "source_model_name": "gpt-5.5-pro-pre-release_xhigh",
     "p": 0.9189514189514191,
     "p_star": 0.9168461354391003,
     "y": 2.4002469854056128,
     "v": 0.08942440198365463,
     "family_factor": 1.0,
     "w": 3.0479191864596475
    }
   ]
  },
  {
   "slug": "ai-co-mathematician",
   "name": "AI Co-Mathematician",
   "tier": "insufficient",
   "rank": null,
   "theta": 2.495691343391367,
   "se": 0.20340066190616438,
   "si_iq": 137.4353701508705,
   "si_iq_low": 132.41690426578546,
   "si_iq_high": 142.45383603595553,
   "si_iq_display": 137,
   "domains": {},
   "inputs": [
    {
     "benchmark": "frontiermath_t4",
     "score": 0.756,
     "source_value_text": "0.756",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "gdm-ai-co-mathematician-manual-run-v2",
     "source_model_name": "gdm-ai-co-mathematician",
     "p": 0.756,
     "p_star": 0.7499047619047619,
     "y": 1.098104416640941,
     "v": 0.12392922729485976,
     "family_factor": 1.0,
     "w": 2.232848324625454
    }
   ]
  },
  {
   "slug": "muse-wonder",
   "name": "Muse Wonder",
   "tier": "insufficient",
   "rank": null,
   "theta": 2.398000731905039,
   "se": 0.13778695454855178,
   "si_iq": 135.9700109785756,
   "si_iq_low": 132.57041962852054,
   "si_iq_high": 139.36960232863063,
   "si_iq_display": 136,
   "domains": {
    "math": {
     "si_iq": 135.72237374529195,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.51,
     "source_value_text": "0.51",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "gmscEuzbtZeUeFUFZMZiAV",
     "source_model_name": "muse-wonder-1.0_max",
     "p": 0.46023353161489317,
     "p_star": 0.46062725902464674,
     "y": -0.15781770641113804,
     "v": 0.048156315143120916,
     "family_factor": 1.0,
     "w": 4.77270766692242
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.7073170731707317,
     "source_value_text": "0.7073170731707317",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-12",
     "source_row_id": "76KF9F9owpePuyHpP68mdZ",
     "source_model_name": "muse-wonder-1.0_max",
     "p": 0.7073170731707317,
     "p_star": 0.7023809523809523,
     "y": 0.8586616190375185,
     "v": 0.11118644067796606,
     "family_factor": 1.0,
     "w": 2.367576243980739
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8210526315789474,
     "source_value_text": "0.8210526315789474",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-12",
     "source_row_id": "hwVgELmPofPY3Vqm7BRLxs",
     "source_model_name": "muse-wonder-1.0_max",
     "p": 0.8210526315789474,
     "p_star": 0.8199300699300699,
     "y": 1.5158737802166435,
     "v": 0.023599064317800726,
     "family_factor": 1.0,
     "w": 4.045338067563267
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9944444444444445,
     "source_value_text": "0.9944444444444445",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-12",
     "source_row_id": "AFigcTGzpgZgMi6j2fpboa",
     "source_model_name": "muse-wonder-1.0_max",
     "p": 0.9944388833277722,
     "p_star": 0.9836902119510814,
     "y": 4.099545600844267,
     "v": 1.3268807560842293,
     "family_factor": 1.0,
     "w": 0.35041470555124987
    }
   ]
  },
  {
   "slug": "gpt-5-4-pro",
   "name": "GPT-5.4 Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": 2.304923691146538,
   "se": 0.13313277613354157,
   "si_iq": 134.57385536719806,
   "si_iq_low": 131.28909567688265,
   "si_iq_high": 137.85861505751348,
   "si_iq_display": 135,
   "domains": {
    "math": {
     "si_iq": 133.7541625121255,
     "n": 2
    },
    "knowledge": {
     "si_iq": 134.17616307504346,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.59,
     "source_value_text": "0.59",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "5yc9mNtsSiFQ5PducfGZGT",
     "source_model_name": "gpt-5.4-pro-2026-03-05_xhigh",
     "p": 0.5686026936026936,
     "p_star": 0.5679234590125679,
     "y": 0.2733839036197291,
     "v": 0.043620143680307207,
     "family_factor": 1.0,
     "w": 4.923451286614358
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.5853658536585366,
     "source_value_text": "0.5853658536585366",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-13",
     "source_row_id": "W6b3C8AeNC7CAFs5DQma8N",
     "source_model_name": "gpt-5.4-pro-2026-03-05_xhigh",
     "p": 0.5853658536585366,
     "p_star": 0.5833333333333334,
     "y": 0.336472236621213,
     "v": 0.09562682215743441,
     "family_factor": 1.0,
     "w": 2.5558867362146045
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.8245614035087719,
     "source_value_text": "0.8245614035087719",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-13",
     "source_row_id": "ZFVa8dw7oiir6PhcF8XZMo",
     "source_model_name": "gpt-5.4-pro-2026-03-05_xhigh",
     "p": 0.8245614035087719,
     "p_star": 0.8234265734265734,
     "y": 1.5397375771751585,
     "v": 0.02396417985747619,
     "family_factor": 1.0,
     "w": 4.0334232080175
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.946,
     "source_value_text": "0.946",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-03-20",
     "source_row_id": "gpt-5-4-pro-gpqa-cloud-run",
     "source_model_name": "gpt-5.4-pro-2026-03-05_xhigh",
     "p": 0.9279999999999999,
     "p_star": 0.9258492462311558,
     "y": 2.5246111863543095,
     "v": 0.09904934759978593,
     "family_factor": 1.0,
     "w": 2.900538364739894
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.463,
     "source_value_text": "0.463",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "RfSJbuuuMkeVHQj7xrth4u",
     "source_model_name": "gpt-5.4-pro-2026-03-05_xhigh",
     "p": 0.463,
     "p_star": 0.463036963036963,
     "y": -0.14812237499590797,
     "v": 0.004013948470936504,
     "family_factor": 1.0,
     "w": 1.6913248936106877
    }
   ]
  },
  {
   "slug": "gpt-5-2-pro",
   "name": "GPT-5.2 Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": 2.105165077116014,
   "se": 0.13651536385232954,
   "si_iq": 131.5774761567402,
   "si_iq_low": 128.2092585223308,
   "si_iq_high": 134.9456937911496,
   "si_iq_display": 132,
   "domains": {
    "math": {
     "si_iq": 129.87285956785803,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.6,
     "source_value_text": "0.6",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "LgRDo2HcNECAGiD8UnHYjx",
     "source_model_name": "gpt-5.2-pro-2025-12-11_xhigh",
     "p": 0.5791245791245792,
     "p_star": 0.5783411674500784,
     "y": 0.31596741625636526,
     "v": 0.043826157726371696,
     "family_factor": 1.0,
     "w": 4.916399022018049
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.46,
     "source_value_text": "0.46",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-13",
     "source_row_id": "oALBfwNc7dcNSDJSSBJXYe",
     "source_model_name": "gpt-5.2-pro-2025-12-11_xhigh",
     "p": 0.46,
     "p_star": 0.46095238095238095,
     "y": -0.15650917148655114,
     "v": 0.09354101568203722,
     "family_factor": 1.0,
     "w": 2.5834317249912293
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.74,
     "source_value_text": "0.74",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-13",
     "source_row_id": "dMJenf5xYWu7Pwn2U6w4dW",
     "source_model_name": "gpt-5.2-pro-2025-12-11_xhigh",
     "p": 0.74,
     "p_star": 0.7391608391608392,
     "y": 1.0416115662264223,
     "v": 0.018071784934345525,
     "family_factor": 1.0,
     "w": 4.234711961693709
    }
   ]
  },
  {
   "slug": "mimo-v2-6-pro",
   "name": "MiMo-V2.6 Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": 2.042947244573124,
   "se": 0.5604943616626229,
   "si_iq": 130.64420866859686,
   "si_iq_low": 116.81523777722367,
   "si_iq_high": 144.47317955997005,
   "si_iq_display": 131,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8989897499999999,
     "source_value_text": "0.89899",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "xiaomi/mimo-v2.6-pro-20260921",
     "source_model_name": "xiaomi/mimo-v2.6-pro-20260921",
     "p": 0.8653196666666666,
     "p_star": 0.8634838894472362,
     "y": 1.8445326064544822,
     "v": 0.0587887848005446,
     "family_factor": 1.0,
     "w": 2.705000048371126
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7983335000000001,
     "source_value_text": "0.798334",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "xiaomi/mimo-v2.6-pro-20260921",
     "source_model_name": "xiaomi/mimo-v2.6-pro-20260921",
     "p": 0.7983335000000001,
     "p_star": 0.7924838235294118,
     "y": 1.339962798066323,
     "v": 0.11689267285914212,
     "family_factor": 1.0,
     "w": 3.2601690590339487
    }
   ]
  },
  {
   "slug": "qwen-3-8-max",
   "name": "Qwen 3.8 Max",
   "tier": "insufficient",
   "rank": null,
   "theta": 2.0092615095403867,
   "se": 0.1223447108728183,
   "si_iq": 130.1389226431058,
   "si_iq_low": 127.12033483723582,
   "si_iq_high": 133.15751044897578,
   "si_iq_display": 130,
   "domains": {
    "reasoning": {
     "si_iq": 130.36115974584777,
     "n": 2
    },
    "math": {
     "si_iq": 130.22271559011668,
     "n": 3
    },
    "knowledge": {
     "si_iq": 129.60560043961294,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.46,
     "source_value_text": "0.46",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "bq5y6Tp83KLtxC58UDfpyN",
     "source_model_name": "qwen3.8-max_xhigh",
     "p": 0.4318181818181819,
     "p_star": 0.43249324932493255,
     "y": -0.27168592699462696,
     "v": 0.044759401196877796,
     "family_factor": 1.0,
     "w": 4.8847036899859635
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.38,
     "source_value_text": "0.38",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-05",
     "source_row_id": "c2YLifDU4zYCX5Jbi9HLL7",
     "source_model_name": "qwen3.8-max_xhigh",
     "p": 0.3170301828596607,
     "p_star": 0.3188417652075849,
     "y": -0.7590996897949436,
     "v": 0.05951517609635058,
     "family_factor": 1.0,
     "w": 4.432849578897997
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.4634146341463415,
     "source_value_text": "0.4634146341463415",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-04",
     "source_row_id": "PBRdMZyz4L4CqPpXyLD2Lk",
     "source_model_name": "qwen3.8-max_xhigh",
     "p": 0.4634146341463415,
     "p_star": 0.4642857142857143,
     "y": -0.1431008436406733,
     "v": 0.09344729344729347,
     "family_factor": 1.0,
     "w": 2.584683357879234
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.7473684210526316,
     "source_value_text": "0.7473684210526316",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-04",
     "source_row_id": "ABT89ieSWGnGj4RYMduHiG",
     "source_model_name": "qwen3.8-max_xhigh",
     "p": 0.7473684210526316,
     "p_star": 0.7465034965034965,
     "y": 1.08005027080805,
     "v": 0.018412339497698455,
     "family_factor": 1.0,
     "w": 4.222532905953761
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9944444444444445,
     "source_value_text": "0.9944444444444445",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-04",
     "source_row_id": "aGRKHaq9uSawfYVpC565zU",
     "source_model_name": "qwen3.8-max_xhigh",
     "p": 0.9944388833277722,
     "p_star": 0.9836902119510814,
     "y": 4.099545600844267,
     "v": 1.3268807560842293,
     "family_factor": 1.0,
     "w": 0.35041470555124987
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9267676767676768,
     "source_value_text": "0.9267676767676768",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-04",
     "source_row_id": "TEVNDC9QXBh7PQvX9kHZip",
     "source_model_name": "qwen3.8-max_xhigh",
     "p": 0.9023569023569024,
     "p_star": 0.9003350083752093,
     "y": 2.200952447450233,
     "v": 0.0763495616526761,
     "family_factor": 1.0,
     "w": 3.2738968204907044
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.458,
     "source_value_text": "0.458",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "bfftd5EzUK9yAekafEofvK",
     "source_model_name": "qwen3.8-max_xhigh",
     "p": 0.458,
     "p_star": 0.458041958041958,
     "y": -0.16822779371809515,
     "v": 0.004020322731407263,
     "family_factor": 1.0,
     "w": 1.691293311845086
    }
   ]
  },
  {
   "slug": "deepseek-v4-flash",
   "name": "DeepSeek-V4-Flash",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.9537643861458511,
   "se": 0.5579868747380726,
   "si_iq": 129.30646579218777,
   "si_iq_low": 115.5393616492815,
   "si_iq_high": 143.07356993509404,
   "si_iq_display": 129,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8989900000000001,
     "source_value_text": "0.89899",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-08",
     "source_row_id": "deepseek/deepseek-v4-flash-20260423",
     "source_model_name": "deepseek/deepseek-v4-flash-20260423",
     "p": 0.8653200000000001,
     "p_star": 0.8634842211055278,
     "y": 1.8445354199948976,
     "v": 0.05878889875553653,
     "family_factor": 1.0,
     "w": 2.7049986041679204
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7755553333333334,
     "source_value_text": "0.775555",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-08",
     "source_row_id": "deepseek/deepseek-v4-flash-20260423",
     "source_model_name": "deepseek/deepseek-v4-flash-20260423",
     "p": 0.7755553333333334,
     "p_star": 0.7701522875816994,
     "y": 1.2091713016681858,
     "v": 0.10859575690156835,
     "family_factor": 1.0,
     "w": 3.389842591669855
    }
   ]
  },
  {
   "slug": "tencent-hy4-preview",
   "name": "Tencent Hy4 preview",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.944163105935159,
   "se": 0.5575601818470542,
   "si_iq": 129.16244658902738,
   "si_iq_low": 115.40587015874956,
   "si_iq_high": 142.9190230193052,
   "si_iq_display": 129,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8973063333333335,
     "source_value_text": "0.897306",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "tencent/hy4-preview-20260827",
     "source_model_name": "tencent/hy4-preview-20260827",
     "p": 0.8630751111111113,
     "p_star": 0.8612506130653269,
     "y": 1.8257162000316949,
     "v": 0.058034406923507295,
     "family_factor": 1.0,
     "w": 2.7145945367029833
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7777776666666667,
     "source_value_text": "0.777778",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "tencent/hy4-preview-20260827",
     "source_model_name": "tencent/hy4-preview-20260827",
     "p": 0.7777776666666667,
     "p_star": 0.7723310457516339,
     "y": 1.2215206550547977,
     "v": 0.10932572012413931,
     "family_factor": 1.0,
     "w": 3.378021490943407
    }
   ]
  },
  {
   "slug": "muse-spark-1-3",
   "name": "Muse Spark 1.3",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.8600913301808721,
   "se": 0.12835621478311504,
   "si_iq": 127.90136995271308,
   "si_iq_low": 124.73446145305009,
   "si_iq_high": 131.06827845237606,
   "si_iq_display": 128,
   "domains": {
    "reasoning": {
     "si_iq": 123.27346178563616,
     "n": 2
    },
    "math": {
     "si_iq": 130.04235144433505,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.37,
     "source_value_text": "0.37",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "XkHyFXCWYDv2nAB5vmmWrU",
     "source_model_name": "muse-spark-1.3_max",
     "p": 0.33712121212121215,
     "p_star": 0.3387338733873388,
     "y": -0.6689416061231427,
     "v": 0.050507317607186304,
     "family_factor": 1.0,
     "w": 4.698155494552413
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.25,
     "source_value_text": "0.25",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-18",
     "source_row_id": "6Rcc2q3USiUNB6U44bpvGH",
     "source_model_name": "muse-spark-1.3_max",
     "p": 0.17382683410442828,
     "p_star": 0.17705627139052307,
     "y": -1.5364202253301036,
     "v": 0.10587112786656308,
     "family_factor": 1.0,
     "w": 3.434705917795642
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.4634146341463415,
     "source_value_text": "0.4634146341463415",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-18",
     "source_row_id": "naZno5TPpgMJfv2b5mhvUW",
     "source_model_name": "muse-spark-1.3_max",
     "p": 0.4634146341463415,
     "p_star": 0.4642857142857143,
     "y": -0.1431008436406733,
     "v": 0.09344729344729347,
     "family_factor": 1.0,
     "w": 2.584683357879234
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.743859649122807,
     "source_value_text": "0.743859649122807",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-16",
     "source_row_id": "JeYksd3f2RkegmxCcZyBMQ",
     "source_model_name": "muse-spark-1.3_xhigh",
     "p": 0.743859649122807,
     "p_star": 0.743006993006993,
     "y": 1.0616565821456807,
     "v": 0.018247298919567827,
     "family_factor": 1.0,
     "w": 4.228426395939086
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9916666666666667,
     "source_value_text": "0.9916666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-17",
     "source_row_id": "Wmxkx5m3qaQuwzem6gzZmg",
     "source_model_name": "muse-spark-1.3_xhigh",
     "p": 0.9916583249916584,
     "p_star": 0.9809701005353181,
     "y": 3.942530582240475,
     "v": 1.1403745660112583,
     "family_factor": 1.0,
     "w": 0.403104041070334
    }
   ]
  },
  {
   "slug": "qwen3-8-max-0902",
   "name": "Qwen3.8 Max (0902)",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.7701064303258003,
   "se": 0.13158150151575562,
   "si_iq": 126.551596454887,
   "si_iq_low": 123.30511106847405,
   "si_iq_high": 129.79808184129996,
   "si_iq_display": 127,
   "domains": {
    "math": {
     "si_iq": 126.61136097556405,
     "n": 3
    },
    "knowledge": {
     "si_iq": 128.29635773676435,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.37,
     "source_value_text": "0.37",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "Ut4d4rvkUygdLTRomFb5rh",
     "source_model_name": "qwen3.8-max-0902_xhigh",
     "p": 0.33712121212121215,
     "p_star": 0.3387338733873388,
     "y": -0.6689416061231427,
     "v": 0.050507317607186304,
     "family_factor": 1.0,
     "w": 4.698155494552413
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.34146341463414637,
     "source_value_text": "0.34146341463414637",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "kZUdrqdGtCEJa3ip6L9YnH",
     "source_model_name": "qwen3.8-max-0902_xhigh",
     "p": 0.34146341463414637,
     "p_star": 0.3452380952380953,
     "y": -0.6400373552459966,
     "v": 0.10282131661442005,
     "family_factor": 1.0,
     "w": 2.465224111282844
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.656140350877193,
     "source_value_text": "0.656140350877193",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "FpQf5xBwJPb4ZEo6SgdKWq",
     "source_model_name": "qwen3.8-max-0902_xhigh",
     "p": 0.656140350877193,
     "p_star": 0.6555944055944056,
     "y": 0.6437222972324225,
     "v": 0.015431472081218277,
     "family_factor": 1.0,
     "w": 4.331574318381706
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 1.0,
     "source_value_text": "1.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "2f8Vn5QBdJnc9i5y9jzXS7",
     "source_model_name": "qwen3.8-max-0902_xhigh",
     "p": 1.0,
     "p_star": 0.9891304347826086,
     "y": 4.510859506516845,
     "v": 1.9800237382654968,
     "family_factor": 1.0,
     "w": 0.24038187199581823
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.922979797979798,
     "source_value_text": "0.922979797979798",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "VzeQXKBH9maR2nDcZJ8b7S",
     "source_model_name": "qwen3.8-max-0902_xhigh",
     "p": 0.8973063973063974,
     "p_star": 0.8953098827470688,
     "y": 2.1461651737227454,
     "v": 0.07320359025203005,
     "family_factor": 1.0,
     "w": 3.333362018359541
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.473,
     "source_value_text": "0.473",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-02",
     "source_row_id": "nBcLJJomVoeg2zh5F8Mnsu",
     "source_model_name": "qwen3.8-max-0902_xhigh",
     "p": 0.473,
     "p_star": 0.47302697302697305,
     "y": -0.10799695272408856,
     "v": 0.00400366335196705,
     "family_factor": 1.0,
     "w": 1.6913758545136417
    }
   ]
  },
  {
   "slug": "muse-spark-1-1",
   "name": "Muse Spark 1.1",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.643879985586499,
   "se": 0.33586873846759197,
   "si_iq": 124.65819978379749,
   "si_iq_low": 116.37137421464689,
   "si_iq_high": 132.94502535294808,
   "si_iq_display": 125,
   "domains": {},
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.34,
     "source_value_text": "0.34",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "4pbEvTxsbzNRCh9kU9Xhun",
     "source_model_name": "muse-spark-1.1_xhigh",
     "p": 0.3055555555555556,
     "p_star": 0.3074807480748075,
     "y": -0.8119235608892479,
     "v": 0.05385089345701696,
     "family_factor": 1.0,
     "w": 4.596052484960705
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.5778894472361809,
     "source_value_text": "0.5778894472361809",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "bCdwpRXgZtvQLYC4wA9JXr",
     "source_model_name": "muse-spark-1.1",
     "p": 0.5778894472361809,
     "p_star": 0.5778116356005804,
     "y": 0.3137963500117298,
     "v": 0.0040910925279050115,
     "family_factor": 1.0,
     "w": 1.6909427566469757
    }
   ]
  },
  {
   "slug": "qwen3-8-flash",
   "name": "Qwen3.8 Flash",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.6387913613295602,
   "se": 0.5509867192756351,
   "si_iq": 124.5818704199434,
   "si_iq_low": 110.98747978273232,
   "si_iq_high": 138.17626105715448,
   "si_iq_display": 125,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8962022556962025,
     "source_value_text": "0.896202",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-10",
     "source_row_id": "qwen/qwen3.8-flash-20260826",
     "source_model_name": "qwen/qwen3.8-flash-20260826",
     "p": 0.8616030075949367,
     "p_star": 0.8597859070542586,
     "y": 1.8135129231233957,
     "v": 0.05755334573040824,
     "family_factor": 1.0,
     "w": 2.7207484917457574
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7,
     "source_value_text": "0.7",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "qwen/qwen3.8-flash-20260826",
     "source_model_name": "qwen/qwen3.8-flash-20260826",
     "p": 0.7,
     "p_star": 0.696078431372549,
     "y": 0.8286926725561691,
     "v": 0.09086778736937755,
     "family_factor": 1.0,
     "w": 3.704694180889291
    }
   ]
  },
  {
   "slug": "grok-4-5",
   "name": "Grok 4.5",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.6101896145593073,
   "se": 0.13277293750086389,
   "si_iq": 124.15284421838962,
   "si_iq_low": 120.87696275828893,
   "si_iq_high": 127.4287256784903,
   "si_iq_display": 124,
   "domains": {
    "math": {
     "si_iq": 123.4500647637369,
     "n": 3
    },
    "knowledge": {
     "si_iq": 129.51737485108802,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.35,
     "source_value_text": "0.35",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "jTuYE8VJTos73Kw77UFevq",
     "source_model_name": "grok-4.5_high",
     "p": 0.31607744107744107,
     "p_star": 0.3178984565123179,
     "y": -0.763446524861428,
     "v": 0.05263022440104879,
     "family_factor": 1.0,
     "w": 4.632809680791432
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.24390243902439024,
     "source_value_text": "0.24390243902439024",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "7vThbrtbczScg2UcsAYXtF",
     "source_model_name": "grok-4.5_high",
     "p": 0.24390243902439024,
     "p_star": 0.25,
     "y": -1.0986122886681098,
     "v": 0.12396069538926682,
     "family_factor": 1.0,
     "w": 2.2325345933175833
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5719298245614035,
     "source_value_text": "0.5719298245614035",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-09",
     "source_row_id": "djbbEqvBW9qux3pZwcZN2i",
     "source_model_name": "grok-4.5_high",
     "p": 0.5719298245614035,
     "p_star": 0.5716783216783217,
     "y": 0.28870196035252643,
     "v": 0.014229545029020782,
     "family_factor": 1.0,
     "w": 4.377151286674316
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9777777777777777,
     "source_value_text": "0.9777777777777777",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-08",
     "source_row_id": "f8Pac6hqib4t7x2s4HCRoT",
     "source_model_name": "grok-4.5_high",
     "p": 0.9777555333110889,
     "p_star": 0.9673695434565,
     "y": 3.3893344749741634,
     "v": 0.6744200157422331,
     "family_factor": 1.0,
     "w": 0.6456444691977407
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9343434343434344,
     "source_value_text": "0.9343434343434344",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-08",
     "source_row_id": "9kSgmUd9vh4CBXz3tJhctN",
     "source_model_name": "grok-4.5_high",
     "p": 0.9124579124579125,
     "p_star": 0.9103852596314909,
     "y": 2.3183480526593043,
     "v": 0.08372425250528007,
     "family_factor": 1.0,
     "w": 3.1424826135734762
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.483,
     "source_value_text": "0.483",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "7HWW3sjRstKzb9JpcnvLaV",
     "source_model_name": "grok-4.5_high",
     "p": 0.483,
     "p_star": 0.48301698301698304,
     "y": -0.067958210246175,
     "v": 0.003996622853688634,
     "family_factor": 1.0,
     "w": 1.6914107406789642
    }
   ]
  },
  {
   "slug": "gpt-5-pro",
   "name": "GPT-5 Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.5994453974698533,
   "se": 0.1433907399916894,
   "si_iq": 123.9916809620478,
   "si_iq_low": 120.45382847847344,
   "si_iq_high": 127.52953344562215,
   "si_iq_display": 124,
   "domains": {
    "math": {
     "si_iq": 121.91598246186533,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.48,
     "source_value_text": "0.48",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-14",
     "source_row_id": "RwHkGk6Qhd4NVTtRLDwLmc",
     "source_model_name": "gpt-5-pro-2025-10-06_high",
     "p": 0.45286195286195285,
     "p_star": 0.4533286661999533,
     "y": -0.1872303746909695,
     "v": 0.04411035357981414,
     "family_factor": 1.0,
     "w": 4.906703533933967
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.1951219512195122,
     "source_value_text": "0.1951219512195122",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "HfDahF4ZXTN6bjfDFwcHTU",
     "source_model_name": "gpt-5-pro-2025-10-06_high",
     "p": 0.1951219512195122,
     "p_star": 0.20238095238095238,
     "y": -1.37147927533475,
     "v": 0.1439859525899912,
     "family_factor": 1.0,
     "w": 2.0492983087441528
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5578947368421052,
     "source_value_text": "0.5578947368421052",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-12",
     "source_row_id": "TFDQUeRKbWiEodRQRrKdpy",
     "source_model_name": "gpt-5-pro-2025-10-06_high",
     "p": 0.5578947368421052,
     "p_star": 0.5576923076923077,
     "y": 0.23180161405732438,
     "v": 0.014125168820548404,
     "family_factor": 1.0,
     "w": 4.381154526800351
    }
   ]
  },
  {
   "slug": "grok-4-7",
   "name": "Grok 4.7",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.5588947745774695,
   "se": 0.12858712741754635,
   "si_iq": 123.38342161866204,
   "si_iq_low": 120.21081585544313,
   "si_iq_high": 126.55602738188095,
   "si_iq_display": 123,
   "domains": {
    "reasoning": {
     "si_iq": 125.50761089667836,
     "n": 2
    },
    "math": {
     "si_iq": 121.39500661981197,
     "n": 3
    },
    "knowledge": {
     "si_iq": 129.64322407594778,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.41,
     "source_value_text": "0.41",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "L5Ck7pMy8bVmVMMLwxJN7f",
     "source_model_name": "grok-4.7_xhigh",
     "p": 0.3792087542087542,
     "p_star": 0.3804047071373804,
     "y": -0.487830806682605,
     "v": 0.04729738458946777,
     "family_factor": 1.0,
     "w": 4.80053860533453
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.29,
     "source_value_text": "0.29",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "Hk8bjr4u6KGqVE8SrPFKLq",
     "source_model_name": "grok-4.7_xhigh",
     "p": 0.2178894029521921,
     "p_star": 0.22068257718038825,
     "y": -1.2616930709162055,
     "v": 0.08323296845406493,
     "family_factor": 1.0,
     "w": 3.8590587008025987
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.17073170731707318,
     "source_value_text": "0.17073170731707318",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "Ymgj5VeEceBbzsLq6xEZRi",
     "source_model_name": "grok-4.7_xhigh",
     "p": 0.17073170731707318,
     "p_star": 0.1785714285714286,
     "y": -1.5260563034950492,
     "v": 0.1584541062801932,
     "family_factor": 1.0,
     "w": 1.9345794392523366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5298245614035088,
     "source_value_text": "0.5298245614035088",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "F4unBbW5M4VJogzCq4vGAb",
     "source_model_name": "grok-4.7_xhigh",
     "p": 0.5298245614035088,
     "p_star": 0.5297202797202797,
     "y": 0.1190214259075298,
     "v": 0.013986528764400603,
     "family_factor": 1.0,
     "w": 4.386483257450999
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9805555555555555,
     "source_value_text": "0.9805555555555555",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "Jhgwm7QpspGcvm7DUVqUDg",
     "source_model_name": "grok-4.7_xhigh",
     "p": 0.9805360916472027,
     "p_star": 0.9700896548722635,
     "y": 3.479184083479825,
     "v": 0.7336880657732289,
     "family_factor": 1.0,
     "w": 0.5997447013185443
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.92739898989899,
     "source_value_text": "0.92739898989899",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "hxAhYJfXdPNanxatXpG5hC",
     "source_model_name": "grok-4.7_xhigh",
     "p": 0.9031986531986532,
     "p_star": 0.9011725293132329,
     "y": 2.2103211162560656,
     "v": 0.0769057168401652,
     "family_factor": 1.0,
     "w": 3.26360436226752
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.56,
     "source_value_text": "0.56",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-09-22",
     "source_row_id": "6izDCw5ygCLZJEKPS8jV5T",
     "source_model_name": "grok-4.7_xhigh",
     "p": 0.56,
     "p_star": 0.5599400599400599,
     "y": 0.24091879713598022,
     "v": 0.0040502186611799705,
     "family_factor": 1.0,
     "w": 1.6911452058895993
    }
   ]
  },
  {
   "slug": "gemini-3-pro",
   "name": "Gemini 3 Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.4940392098268076,
   "se": 0.2877189677908233,
   "si_iq": 122.41058814740211,
   "si_iq_low": 115.31175272170302,
   "si_iq_high": 129.50942357310123,
   "si_iq_display": 122,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9138888888888889,
     "source_value_text": "0.9138888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-11-19",
     "source_row_id": "4QM4h7ndQiDRL2anjKeddK",
     "source_model_name": "gemini-3-pro-preview",
     "p": 0.9138026915804693,
     "p_star": 0.9048069808939374,
     "y": 2.2518150297813584,
     "v": 0.24718152508278973,
     "family_factor": 1.0,
     "w": 1.4401687989612026
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7293388429752066,
     "source_value_text": "0.7293388429752066",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-13",
     "source_row_id": "5XdYZBG5Wy8DUMRqcYv4fn",
     "source_model_name": "gemini-3-pro-preview",
     "p": 0.7293388429752066,
     "p_star": 0.7288650023905471,
     "y": 0.988871689947966,
     "v": 0.010433348903288803,
     "family_factor": 1.0,
     "w": 6.403018546560523
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.9261363636363636,
     "source_value_text": "0.9261363636363636",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-11-19",
     "source_row_id": "Cg54udQGcTCnfDGX2qePLZ",
     "source_model_name": "gemini-3-pro-preview",
     "p": 0.9015151515151515,
     "p_star": 0.8994974874371859,
     "y": 2.191653532286764,
     "v": 0.07580287756312226,
     "family_factor": 1.0,
     "w": 3.2840774689955086
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.7251000000000001,
     "source_value_text": "72.51%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "3",
     "source_model_name": "Gemini-3-Pro-Preview (Prompt)",
     "p": 0.7251000000000001,
     "p_star": 0.722871287128713,
     "y": 0.9587491145406326,
     "v": 0.04893445469572337,
     "family_factor": 1.0,
     "w": 4.747771646468129
    }
   ]
  },
  {
   "slug": "gpt-5-3-codex",
   "name": "GPT-5.3 Codex",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.4896819746064427,
   "se": 0.5720986174225696,
   "si_iq": 122.34522961909664,
   "si_iq_low": 108.22994913016689,
   "si_iq_high": 136.46051010802637,
   "si_iq_display": 122,
   "domains": {},
   "inputs": [
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7479338842975206,
     "source_value_text": "0.7479338842975206",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-25",
     "source_row_id": "6w5buMbgeEqtRoE55cLZVv",
     "source_model_name": "gpt-5.3-codex_high",
     "p": 0.7479338842975206,
     "p_star": 0.7474216242059968,
     "y": 1.0849078494713724,
     "v": 0.010921809134179583,
     "family_factor": 1.0,
     "w": 6.374821928221316
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.753333,
     "source_value_text": "0.753333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-02",
     "source_row_id": "openai/gpt-5.3-codex-20260224",
     "source_model_name": "openai/gpt-5.3-codex-20260224",
     "p": 0.753333,
     "p_star": 0.7483656862745098,
     "y": 1.0899148463187824,
     "v": 0.10208123679273078,
     "family_factor": 1.0,
     "w": 3.4991214048823727
    }
   ]
  },
  {
   "slug": "mistral-large-4",
   "name": "Mistral Large 4",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.4606788757585445,
   "se": 0.1279983769549124,
   "si_iq": 121.91018313637817,
   "si_iq_low": 118.75210350146124,
   "si_iq_high": 125.0682627712951,
   "si_iq_display": 122,
   "domains": {
    "reasoning": {
     "si_iq": 118.77344737330056,
     "n": 2
    },
    "math": {
     "si_iq": 124.04172540777343,
     "n": 3
    },
    "knowledge": {
     "si_iq": 116.27615914008572,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.33,
     "source_value_text": "0.33",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-15",
     "source_row_id": "eNdDCt2u6A8mPisK56SApU",
     "source_model_name": "mistral-large-4-0_high",
     "p": 0.2950336700336701,
     "p_star": 0.29706303963729713,
     "y": -0.8613228445241748,
     "v": 0.0551927491039482,
     "family_factor": 1.0,
     "w": 4.556313263791254
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.17,
     "source_value_text": "0.17",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "LT9xLJnaU4UHsBQrvu3rbU",
     "source_model_name": "mistral-large-4-0_high",
     "p": 0.08570169640890066,
     "p_star": 0.08980365981079273,
     "y": -2.316034605079059,
     "v": 0.25556603990154425,
     "family_factor": 1.0,
     "w": 1.9886791814604803
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.2682926829268293,
     "source_value_text": "0.2682926829268293",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-12",
     "source_row_id": "TzoNRjKto6wEuZ5PmQPAw8",
     "source_model_name": "mistral-large-4-0_high",
     "p": 0.2682926829268293,
     "p_star": 0.27380952380952384,
     "y": -0.9753796482441615,
     "v": 0.11689237348538843,
     "family_factor": 1.0,
     "w": 2.305290831416366
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.5859649122807018,
     "source_value_text": "0.5859649122807018",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-12",
     "source_row_id": "CAstp8hQG6Aehvtw85bMDX",
     "source_model_name": "mistral-large-4-0_high",
     "p": 0.5859649122807018,
     "p_star": 0.5856643356643356,
     "y": 0.3460703906899351,
     "v": 0.014358586812771584,
     "family_factor": 1.0,
     "w": 4.372212126218404
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9833333333333333,
     "source_value_text": "0.9833333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-12",
     "source_row_id": "Pby5WuP8Muu6Jzs2v5gB7F",
     "source_model_name": "mistral-large-4-0_high",
     "p": 0.9833166499833166,
     "p_star": 0.9728097662880271,
     "y": 3.57733069640059,
     "v": 0.8048271865249628,
     "family_factor": 1.0,
     "w": 0.5525917075063547
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8806818181818182,
     "source_value_text": "0.8806818181818182",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-12",
     "source_row_id": "Ekx5phukyiJhAcQodMfS2p",
     "source_model_name": "mistral-large-4-0_high",
     "p": 0.8409090909090909,
     "p_star": 0.8391959798994975,
     "y": 1.6522579096170285,
     "v": 0.051767722040948046,
     "family_factor": 1.0,
     "w": 3.804170356025061
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.2,
     "source_value_text": "0.2",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-09",
     "source_row_id": "hvNNKdnzLvr9X8zVxWKcfk",
     "source_model_name": "mistral-large-4-0_high",
     "p": 0.2,
     "p_star": 0.2002997002997003,
     "y": -1.3844222856901458,
     "v": 0.006230519890155933,
     "family_factor": 1.0,
     "w": 1.680413366779072
    }
   ]
  },
  {
   "slug": "mimo-v2-5-pro",
   "name": "MiMo-V2.5-Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.4211646343691313,
   "se": 0.5430370309818329,
   "si_iq": 121.31746951553697,
   "si_iq_low": 107.91922002715809,
   "si_iq_high": 134.71571900391584,
   "si_iq_display": 121,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8550657272727274,
     "source_value_text": "0.855066",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "xiaomi/mimo-v2.5-pro-20260422",
     "source_model_name": "xiaomi/mimo-v2.5-pro-20260422",
     "p": 0.8067543030303033,
     "p_star": 0.8052128241206032,
     "y": 1.4191990634663754,
     "v": 0.045074192208758315,
     "family_factor": 1.0,
     "w": 2.890746636162716
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.743889,
     "source_value_text": "0.743889",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "xiaomi/mimo-v2.5-pro-20260422",
     "source_model_name": "xiaomi/mimo-v2.5-pro-20260422",
     "p": 0.743889,
     "p_star": 0.7391068627450981,
     "y": 1.0413316273445,
     "v": 0.09969187450811329,
     "family_factor": 1.0,
     "w": 3.5409892512067054
    }
   ]
  },
  {
   "slug": "muse-spark-1-2",
   "name": "Muse Spark 1.2",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.368912780872829,
   "se": 0.3473663644703433,
   "si_iq": 120.53369171309244,
   "si_iq_low": 111.9631874021249,
   "si_iq_high": 129.10419602405997,
   "si_iq_display": 121,
   "domains": {},
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.27,
     "source_value_text": "0.27",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "FueK5bFAzGbkUao9JAibms",
     "source_model_name": "muse-spark-1.2_xhigh",
     "p": 0.23190235690235692,
     "p_star": 0.23455678901223456,
     "y": -1.1827572976345744,
     "v": 0.06674897978246991,
     "family_factor": 1.0,
     "w": 4.240546371611951
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.6030150753768844,
     "source_value_text": "0.6030150753768844",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "mLLmVVvo6t23MM5yxq7ryW",
     "source_model_name": "muse-spark-1.2_xhigh",
     "p": 0.6030150753768844,
     "p_star": 0.6029121632136707,
     "y": 0.41761401223882194,
     "v": 0.0041686095123496195,
     "family_factor": 1.0,
     "w": 1.6905589462625554
    }
   ]
  },
  {
   "slug": "minimax-m2-7",
   "name": "MiniMax-M2.7",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.3559517424109335,
   "se": 0.5417764014316793,
   "si_iq": 120.339276136164,
   "si_iq_low": 106.97212992115645,
   "si_iq_high": 133.70642235117157,
   "si_iq_display": 120,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8570973081339713,
     "source_value_text": "0.857097",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "minimax/minimax-m2.7-20260318",
     "source_model_name": "minimax/minimax-m2.7-20260318",
     "p": 0.8094630775119618,
     "p_star": 0.8079079866701931,
     "y": 1.4364736808295082,
     "v": 0.04550964141544712,
     "family_factor": 1.0,
     "w": 2.8844577701056417
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7203921764705883,
     "source_value_text": "0.720392",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "minimax/minimax-m2.7-20260318",
     "source_model_name": "minimax/minimax-m2.7-20260318",
     "p": 0.7203921764705883,
     "p_star": 0.7160707612456748,
     "y": 0.9250539428327269,
     "v": 0.09455044848844554,
     "family_factor": 1.0,
     "w": 3.6345677261625173
    }
   ]
  },
  {
   "slug": "minimax-m2-1",
   "name": "MiniMax-M2.1",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.3077480632258591,
   "se": 0.5418613687001224,
   "si_iq": 119.61622094838789,
   "si_iq_low": 106.24697835210982,
   "si_iq_high": 132.98546354466595,
   "si_iq_display": 120,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.868687,
     "source_value_text": "0.868687",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-08-01",
     "source_row_id": "minimax/minimax-m2.1",
     "source_model_name": "minimax/minimax-m2.1",
     "p": 0.824916,
     "p_star": 0.8232832562814071,
     "y": 1.538752184050706,
     "v": 0.04828054772744606,
     "family_factor": 1.0,
     "w": 2.8450719486285716
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6783334999999999,
     "source_value_text": "0.678333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "minimax/minimax-m2.1",
     "source_model_name": "minimax/minimax-m2.1",
     "p": 0.6783334999999999,
     "p_star": 0.6748367647058823,
     "y": 0.7301435128799505,
     "v": 0.08760511850718986,
     "family_factor": 1.0,
     "w": 3.7691230751758407
    }
   ]
  },
  {
   "slug": "qwen-3-8-27b",
   "name": "Qwen 3.8 27B",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.3031242595074577,
   "se": 0.5407041006352298,
   "si_iq": 119.54686389261187,
   "si_iq_low": 106.20617435141796,
   "si_iq_high": 132.88755343380578,
   "si_iq_display": 120,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.83367,
     "source_value_text": "0.83367",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.8-27b-20260814",
     "source_model_name": "qwen/qwen3.8-27b-20260814",
     "p": 0.7782266666666667,
     "p_star": 0.7768285427135679,
     "y": 1.2472793174802799,
     "v": 0.04121509912425117,
     "family_factor": 1.0,
     "w": 2.9477026494050884
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7592592222222222,
     "source_value_text": "0.759259",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.8-27b-20260814",
     "source_model_name": "qwen/qwen3.8-27b-20260814",
     "p": 0.7592592222222222,
     "p_star": 0.7541757080610022,
     "y": 1.1210083551069947,
     "v": 0.10368891153198137,
     "family_factor": 1.0,
     "w": 3.4715035583835596
    }
   ]
  },
  {
   "slug": "o3-pro",
   "name": "o3-pro",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.278795498037845,
   "se": 0.6373649751496463,
   "si_iq": 119.18193247056767,
   "si_iq_low": 103.45634753804573,
   "si_iq_high": 134.90751740308963,
   "si_iq_display": 119,
   "domains": {},
   "inputs": [
    {
     "benchmark": "aider_polyglot",
     "score": 0.8490000000000001,
     "source_value_text": "84.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-06-28",
     "source_row_id": "2025-06-28-00-38-18--o3-pro-high",
     "source_model_name": "o3-pro (high)",
     "p": 0.8490000000000001,
     "p_star": 0.8474557522123894,
     "y": 1.7147839247235195,
     "v": 0.03407632661742576,
     "family_factor": 1.0,
     "w": 1.3860722008793416
    }
   ]
  },
  {
   "slug": "minimax-m2-5",
   "name": "MiniMax-M2.5",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.2279288854983839,
   "se": 0.5394436483948786,
   "si_iq": 118.41893328247576,
   "si_iq_low": 105.10934263992212,
   "si_iq_high": 131.7285239250294,
   "si_iq_display": 118,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8539973475609757,
     "source_value_text": "0.853997",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-29",
     "source_row_id": "minimax/minimax-m2.5-20260211",
     "source_model_name": "minimax/minimax-m2.5-20260211",
     "p": 0.8053297967479676,
     "p_star": 0.8037954761612944,
     "y": 1.4101872497868588,
     "v": 0.04485063211671076,
     "family_factor": 1.0,
     "w": 2.8939860121886647
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6905556666666667,
     "source_value_text": "0.690556",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-29",
     "source_row_id": "minimax/minimax-m2.5-20260211",
     "source_model_name": "minimax/minimax-m2.5-20260211",
     "p": 0.6905556666666667,
     "p_star": 0.6868192810457516,
     "y": 0.7852908015979864,
     "v": 0.08937008207644564,
     "family_factor": 1.0,
     "w": 3.7339941633499416
    }
   ]
  },
  {
   "slug": "muse-spark",
   "name": "Muse Spark",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.1990070889264601,
   "se": 0.3153192196554329,
   "si_iq": 117.98510633389691,
   "si_iq_low": 110.20529513799013,
   "si_iq_high": 125.76491752980365,
   "si_iq_display": 118,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.889,
     "source_value_text": "0.889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-08",
     "source_row_id": "muse-spark-pre-release-mock-aime",
     "source_model_name": "muse-spark",
     "p": 0.888888888888889,
     "p_star": 0.8804347826086957,
     "y": 1.9965538818740685,
     "v": 0.20224988674920089,
     "family_factor": 1.0,
     "w": 1.6542603386147403
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.898,
     "source_value_text": "0.898",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-04-08",
     "source_row_id": "muse-spark-pre-release-gpqa",
     "source_model_name": "muse-spark",
     "p": 0.864,
     "p_star": 0.8621708542713568,
     "y": 1.8334386141548742,
     "v": 0.058342146023962226,
     "family_factor": 1.0,
     "w": 3.6462198074684062
    }
   ]
  },
  {
   "slug": "qwen-3-6-max-preview",
   "name": "Qwen 3.6 Max (Preview)",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.1789422648894914,
   "se": 0.24357625125392002,
   "si_iq": 117.68413397334237,
   "si_iq_low": 111.67442340564214,
   "si_iq_high": 123.69384454104261,
   "si_iq_display": 118,
   "domains": {
    "knowledge": {
     "si_iq": 120.5220248932543,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.19,
     "source_value_text": "0.19",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "mbySBWyYrKdtd7joxHyBdq",
     "source_model_name": "qwen3.6-max-preview_none",
     "p": 0.10773298083278256,
     "p_star": 0.11161681270572531,
     "y": -2.0743314770532617,
     "v": 0.18881924298033745,
     "family_factor": 1.0,
     "w": 2.4482675527083444
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9111111111111111,
     "source_value_text": "0.9111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "EfJpx5HztMmL5EQSwsyqMe",
     "source_model_name": "qwen3.6-max-preview",
     "p": 0.9110221332443554,
     "p_star": 0.9020868694781738,
     "y": 2.2206301607323202,
     "v": 0.24104004547939525,
     "family_factor": 1.0,
     "w": 1.4661034873401948
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7665289256198347,
     "source_value_text": "0.7665289256198347",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-05-28",
     "source_row_id": "FkDMVLdEnJDR5PyUCT6BNQ",
     "source_model_name": "qwen3.6-max-preview",
     "p": 0.7665289256198347,
     "p_star": 0.7659782460214466,
     "y": 1.1857396931305404,
     "v": 0.011502274869220038,
     "family_factor": 1.0,
     "w": 6.341635469015374
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8737373737373737,
     "source_value_text": "0.8737373737373737",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "Jv2hJvjpvA8xJW3Bzv7bfw",
     "source_model_name": "qwen3.6-max-preview",
     "p": 0.8316498316498316,
     "p_star": 0.8299832495812395,
     "y": 1.5855085552882002,
     "v": 0.04966227264781261,
     "family_factor": 1.0,
     "w": 3.8576874383583273
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.5200400801603207,
     "source_value_text": "0.5200400801603207",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "iyPiR8GUuyNNA6Fssziq32",
     "source_model_name": "qwen3.6-max-preview",
     "p": 0.5200400801603207,
     "p_star": 0.5200200601002205,
     "y": 0.08012307679403138,
     "v": 0.003998422299535544,
     "family_factor": 1.0,
     "w": 1.691401824161029
    }
   ]
  },
  {
   "slug": "mimo-v2-5",
   "name": "MiMo-V2.5",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.1558495480333948,
   "se": 0.537718214295598,
   "si_iq": 117.33774322050093,
   "si_iq_low": 104.07072388564634,
   "si_iq_high": 130.60476255535548,
   "si_iq_display": 117,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8239975454545455,
     "source_value_text": "0.823998",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "xiaomi/mimo-v2.5-20260422",
     "source_model_name": "xiaomi/mimo-v2.5-20260422",
     "p": 0.7653300606060607,
     "p_star": 0.763996743718593,
     "y": 1.174717924276006,
     "v": 0.039828624690747064,
     "family_factor": 1.0,
     "w": 2.9687174381374524
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7372220833333334,
     "source_value_text": "0.737222",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "xiaomi/mimo-v2.5-20260422",
     "source_model_name": "xiaomi/mimo-v2.5-20260422",
     "p": 0.7372220833333334,
     "p_star": 0.7325706699346406,
     "y": 1.0077044692029562,
     "v": 0.0981230612750438,
     "family_factor": 1.0,
     "w": 3.569028141579684
    }
   ]
  },
  {
   "slug": "grok-4-3-beta",
   "name": "Grok 4.3 Beta",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.1477158050696266,
   "se": 0.13726963709647172,
   "si_iq": 117.2157370760444,
   "si_iq_low": 113.8289094011942,
   "si_iq_high": 120.6025647508946,
   "si_iq_display": 117,
   "domains": {
    "math": {
     "si_iq": 118.32013840770264,
     "n": 3
    },
    "knowledge": {
     "si_iq": 118.74024555866858,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.18,
     "source_value_text": "0.18",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "m4WQuAN88hKsqbT9zXbg7z",
     "source_model_name": "grok-4.3_high",
     "p": 0.1372053872053872,
     "p_star": 0.14079741307464078,
     "y": -1.8086826640978757,
     "v": 0.11107032742096709,
     "family_factor": 1.0,
     "w": 3.35010036619816
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.14634146341463414,
     "source_value_text": "0.14634146341463414",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-17",
     "source_row_id": "3iRQkf5v7Wu7YuZhxa76Gg",
     "source_model_name": "grok-4.3_high",
     "p": 0.14634146341463414,
     "p_star": 0.15476190476190477,
     "y": -1.6977305195797787,
     "v": 0.17768147345612137,
     "family_factor": 1.0,
     "w": 1.800624268435427
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.4280701754385965,
     "source_value_text": "0.4280701754385965",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-17",
     "source_row_id": "bdsZjrG4ayzP8NAJg5q586",
     "source_model_name": "grok-4.3_high",
     "p": 0.4280701754385965,
     "p_star": 0.42832167832167833,
     "y": -0.2887019603525264,
     "v": 0.014229545029020782,
     "family_factor": 1.0,
     "w": 4.377151286674316
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9333333333333333,
     "source_value_text": "0.9333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-17",
     "source_row_id": "fzoUFmy77NpEDtXyA6w6ap",
     "source_model_name": "grok-4.3_high",
     "p": 0.9332665999332667,
     "p_star": 0.9238477608042825,
     "y": 2.4958128130586847,
     "v": 0.3026105541876743,
     "family_factor": 1.0,
     "w": 1.2418949150720182
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8882575757575758,
     "source_value_text": "0.8882575757575758",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-17",
     "source_row_id": "Vw7spGUnJyf3vuzSjTcj2F",
     "source_model_name": "grok-4.3_high",
     "p": 0.8510101010101011,
     "p_star": 0.849246231155779,
     "y": 1.7287013332609191,
     "v": 0.0543818493750219,
     "family_factor": 1.0,
     "w": 3.7397548450604177
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.332,
     "source_value_text": "0.332",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "Y39ZRp553ULpUDBV2XrBbc",
     "source_model_name": "grok-4.3_high",
     "p": 0.332,
     "p_star": 0.3321678321678322,
     "y": -0.698396536446089,
     "v": 0.004498906203429291,
     "family_factor": 1.0,
     "w": 1.6889254969566034
    }
   ]
  },
  {
   "slug": "glm-4-6",
   "name": "GLM-4.6",
   "tier": "insufficient",
   "rank": null,
   "theta": 1.121644519803433,
   "se": 0.44939884964643867,
   "si_iq": 116.82466779705149,
   "si_iq_low": 105.73673536550635,
   "si_iq_high": 127.91260022859665,
   "si_iq_display": 117,
   "domains": {
    "agentic": {
     "si_iq": 123.32818393805809,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7646065075987841,
     "source_value_text": "0.7646065075987841",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-08-29",
     "source_row_id": "z-ai/glm-4.6",
     "source_model_name": "z-ai/glm-4.6",
     "p": 0.6861420101317122,
     "p_star": 0.6852066231461257,
     "y": 0.7778039553045492,
     "v": 0.03445628233812761,
     "family_factor": 1.0,
     "w": 3.0530563495643475
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.7238,
     "source_value_text": "72.38%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "4",
     "source_model_name": "GLM-4.6 (FC thinking)",
     "p": 0.7238,
     "p_star": 0.7215841584158416,
     "y": 0.9523331860092387,
     "v": 0.048795112056998935,
     "family_factor": 1.0,
     "w": 4.752217807502145
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7344445,
     "source_value_text": "0.734444",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-4.6",
     "source_model_name": "z-ai/glm-4.6",
     "p": 0.7344445,
     "p_star": 0.7298475490196077,
     "y": 0.9938492424598152,
     "v": 0.0974964014033119,
     "family_factor": 1.0,
     "w": 3.580352736364794
    }
   ]
  },
  {
   "slug": "glm-4-5-air",
   "name": "GLM-4.5-Air",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.9501909697768023,
   "se": 0.9232574594875482,
   "si_iq": 114.25286454665203,
   "si_iq_low": 91.47350866763306,
   "si_iq_high": 137.032220425671,
   "si_iq_display": 114,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_tau2_airline",
     "score": 0.68,
     "source_value_text": "0.68",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "z-ai/glm-4.5-air",
     "source_model_name": "z-ai/glm-4.5-air",
     "p": 0.68,
     "p_star": 0.6764705882352942,
     "y": 0.7375989431307793,
     "v": 0.08783487044356611,
     "family_factor": 1.0,
     "w": 3.7645128378811514
    }
   ]
  },
  {
   "slug": "deepseek-v3-2",
   "name": "DeepSeek-V3.2",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.9466862532684474,
   "se": 0.5342354866137241,
   "si_iq": 114.20029379902671,
   "si_iq_low": 101.01920314254875,
   "si_iq_high": 127.38138445550467,
   "si_iq_display": 114,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.802714625,
     "source_value_text": "0.802714625",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-10-17",
     "source_row_id": "deepseek/deepseek-v3.2-20251201",
     "source_model_name": "deepseek/deepseek-v3.2-20251201",
     "p": 0.7369528333333334,
     "p_star": 0.7357621155778895,
     "y": 1.0240570791781043,
     "v": 0.037368493536740904,
     "family_factor": 1.0,
     "w": 3.0067526157902127
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7193332,
     "source_value_text": "0.7193332",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-04",
     "source_row_id": "deepseek/deepseek-v3.2-20251201",
     "source_model_name": "deepseek/deepseek-v3.2-20251201",
     "p": 0.7193332,
     "p_star": 0.7150325490196078,
     "y": 0.9199530981020275,
     "v": 0.09434276115026165,
     "family_factor": 1.0,
     "w": 3.638451862067698
    }
   ]
  },
  {
   "slug": "nemotron-3-ultra",
   "name": "Nemotron 3 Ultra",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.9440695609274934,
   "se": 0.2468979995347986,
   "si_iq": 114.1610434139124,
   "si_iq_low": 108.06937598201023,
   "si_iq_high": 120.25271084581458,
   "si_iq_display": 114,
   "domains": {},
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.2,
     "source_value_text": "0.2",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "U8H8juE3Ko83jsR6TRntbh",
     "source_model_name": "nemotron-3-ultra",
     "p": 0.11874862304472353,
     "p_star": 0.12252338915319162,
     "y": -1.968748357056755,
     "v": 0.16676370900472426,
     "family_factor": 1.0,
     "w": 2.6506858216385987
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8666666666666667,
     "source_value_text": "0.8666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "WYTWr3Xk4qxymhMsm7vRQ2",
     "source_model_name": "nemotron-3-ultra",
     "p": 0.8665331998665332,
     "p_star": 0.8585650868259564,
     "y": 1.8034228583617016,
     "v": 0.17533678826674742,
     "family_factor": 1.0,
     "w": 1.8159578425662388
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8535353535353535,
     "source_value_text": "0.8535353535353535",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-10",
     "source_row_id": "bpZy8tAbh7UV6A6U7XZtBg",
     "source_model_name": "nemotron-3-ultra",
     "p": 0.8047138047138046,
     "p_star": 0.803182579564489,
     "y": 1.4063055607392787,
     "v": 0.04475509281004857,
     "family_factor": 1.0,
     "w": 3.9884625679266423
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.72,
     "source_value_text": "0.72",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-04",
     "source_row_id": "nvidia/nemotron-3-ultra-550b-a55b-20260604",
     "source_model_name": "nvidia/nemotron-3-ultra-550b-a55b-20260604",
     "p": 0.72,
     "p_star": 0.7156862745098039,
     "y": 0.923163611161917,
     "v": 0.0944733112895607,
     "family_factor": 1.0,
     "w": 3.6360093654892425
    }
   ]
  },
  {
   "slug": "grok-4",
   "name": "Grok 4",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.9074981203824216,
   "se": 0.25876863431993213,
   "si_iq": 113.61247180573632,
   "si_iq_low": 107.22792245720116,
   "si_iq_high": 119.9970211542715,
   "si_iq_display": 114,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.84,
     "source_value_text": "0.84",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "",
     "source_row_id": "cvTPRDCM38zSTn9Y3MUb9d",
     "source_model_name": "grok-4-0709",
     "p": 0.8398398398398398,
     "p_star": 0.8324520172346258,
     "y": 1.6031058087251644,
     "v": 0.152658274972709,
     "family_factor": 1.0,
     "w": 1.9789575467259395
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.7959999999999999,
     "source_value_text": "79.6",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-07-11",
     "source_row_id": "2025-07-11-19-37-40--xai-or-grok4-high",
     "source_model_name": "grok-4 (high)",
     "p": 0.7959999999999999,
     "p_star": 0.7946902654867256,
     "y": 1.3534326966358894,
     "v": 0.02699965440442362,
     "family_factor": 1.0,
     "w": 1.4055698551571678
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.87,
     "source_value_text": "0.87",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "",
     "source_row_id": "A85Zfq2qguE4X9xXBweBHP",
     "source_model_name": "grok-4-0709",
     "p": 0.8266666666666667,
     "p_star": 0.8250251256281408,
     "y": 1.5507714525800778,
     "v": 0.048628622969055506,
     "family_factor": 1.0,
     "w": 3.8845160350427936
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.6297,
     "source_value_text": "62.97%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "9",
     "source_model_name": "Grok-4-0709 (Prompt)",
     "p": 0.6297,
     "p_star": 0.6284158415841585,
     "y": 0.5254267401714497,
     "v": 0.0419810152613165,
     "family_factor": 1.0,
     "w": 4.98029106134447
    }
   ]
  },
  {
   "slug": "qwen-3-6-plus",
   "name": "Qwen 3.6 Plus",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.8424256526957684,
   "se": 0.16722562708295727,
   "si_iq": 112.63638479043652,
   "si_iq_low": 108.51045866628786,
   "si_iq_high": 116.76231091458519,
   "si_iq_display": 113,
   "domains": {
    "reasoning": {
     "si_iq": 104.62607756732463,
     "n": 2
    },
    "math": {
     "si_iq": 115.63953223960341,
     "n": 2
    },
    "knowledge": {
     "si_iq": 118.99321544921702,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.14,
     "source_value_text": "0.14",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "SP9UFPzxVnsbzs2kExP2bh",
     "source_model_name": "qwen3.6-plus",
     "p": 0.09511784511784513,
     "p_star": 0.09912657932459913,
     "y": -2.206967147657535,
     "v": 0.167569741192018,
     "family_factor": 1.0,
     "w": 2.6427008451568565
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.12,
     "source_value_text": "0.12",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "jGgkDRHbodcaTzQ3Mp6SxS",
     "source_model_name": "qwen3.6-plus_none",
     "p": 0.03062348534919585,
     "p_star": 0.03527077757346124,
     "y": -3.30879267312414,
     "v": 1.1176837657418708,
     "family_factor": 1.0,
     "w": 0.5806982084184594
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.3824561403508772,
     "source_value_text": "0.3824561403508772",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "jbyVWnEvvFVNNc8AEF6WcQ",
     "source_model_name": "qwen3.6-plus",
     "p": 0.3824561403508772,
     "p_star": 0.38286713286713286,
     "y": -0.4773963271167958,
     "v": 0.014746400714036245,
     "family_factor": 1.0,
     "w": 4.357435151679123
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.9333333333333333,
     "source_value_text": "0.9333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "jYiGAFfUQKJuRStPzU3PX3",
     "source_model_name": "qwen3.6-plus",
     "p": 0.9332665999332667,
     "p_star": 0.9238477608042825,
     "y": 2.4958128130586847,
     "v": 0.3026105541876743,
     "family_factor": 1.0,
     "w": 1.2418949150720182
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.5785123966942148,
     "source_value_text": "0.5785123966942148",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-05-14",
     "source_row_id": "8HV4HP9EM5KuLSwzifuLye",
     "source_model_name": "qwen3.6-plus",
     "p": 0.5785123966942148,
     "p_star": 0.5783501809985656,
     "y": 0.31600437794018077,
     "v": 0.008455000028400628,
     "family_factor": 1.0,
     "w": 6.519817260627731
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8838383838383839,
     "source_value_text": "0.8838383838383839",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "f6ZdMtRpdfskGbrBCzrKSn",
     "source_model_name": "qwen3.6-plus",
     "p": 0.8451178451178452,
     "p_star": 0.8433835845896148,
     "y": 1.6836222758639763,
     "v": 0.05281331978794622,
     "family_factor": 1.0,
     "w": 3.778141002307881
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.44144144144144143,
     "source_value_text": "0.44144144144144143",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "4LWNorP8Fy8V8doxirNFcH",
     "source_model_name": "qwen3.6-plus",
     "p": 0.44144144144144143,
     "p_star": 0.4414999414999415,
     "y": -0.235076835713165,
     "v": 0.004047417188726811,
     "family_factor": 1.0,
     "w": 1.6911590834250416
    }
   ]
  },
  {
   "slug": "kimi-k2-thinking",
   "name": "Kimi K2 Thinking",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.8267368760977948,
   "se": 0.5323119057615078,
   "si_iq": 112.40105314146692,
   "si_iq_low": 99.26742262987534,
   "si_iq_high": 125.53468365305851,
   "si_iq_display": 112,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.796581,
     "source_value_text": "0.796581",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "moonshotai/kimi-k2-thinking-20251106",
     "source_model_name": "moonshotai/kimi-k2-thinking-20251106",
     "p": 0.7287746666666667,
     "p_star": 0.7276250452261306,
     "y": 0.9826062405265688,
     "v": 0.03678535355828951,
     "family_factor": 1.0,
     "w": 3.015911651587125
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.695,
     "source_value_text": "0.695",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-01",
     "source_row_id": "moonshotai/kimi-k2-thinking-20251106",
     "source_model_name": "moonshotai/kimi-k2-thinking-20251106",
     "p": 0.695,
     "p_star": 0.6911764705882353,
     "y": 0.8056251639866356,
     "v": 0.09005966452774962,
     "family_factor": 1.0,
     "w": 3.7204463290174146
    }
   ]
  },
  {
   "slug": "qwen3-5-122b-a10b",
   "name": "Qwen3.5-122B-A10B",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.8153236145443499,
   "se": 0.3747115309780684,
   "si_iq": 112.22985421816524,
   "si_iq_low": 102.98466780953424,
   "si_iq_high": 121.47504062679624,
   "si_iq_display": 112,
   "domains": {},
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.17,
     "source_value_text": "0.17",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "X5FL4gkJQYjzJ7axz23rfd",
     "source_model_name": "qwen3.5-122b-a10b_none",
     "p": 0.08570169640890066,
     "p_star": 0.08980365981079273,
     "y": -2.316034605079059,
     "v": 0.25556603990154425,
     "family_factor": 1.0,
     "w": 1.9886791814604803
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8073469346289753,
     "source_value_text": "0.807347",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.5-122b-a10b-20260224",
     "source_model_name": "qwen/qwen3.5-122b-a10b-20260224",
     "p": 0.7431292461719671,
     "p_star": 0.7419074911660778,
     "y": 1.0559064783908352,
     "v": 0.037843375834735106,
     "family_factor": 1.0,
     "w": 2.9993349157203864
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7471783002257337,
     "source_value_text": "0.747178",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3.5-122b-a10b-20260224",
     "source_model_name": "qwen/qwen3.5-122b-a10b-20260224",
     "p": 0.7471783002257337,
     "p_star": 0.7423316668879741,
     "y": 1.0581229063671722,
     "v": 0.10050105408671076,
     "family_factor": 1.0,
     "w": 3.526698572271569
    }
   ]
  },
  {
   "slug": "mimo-v2-6-flash",
   "name": "MiMo-V2.6 Flash",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.7930050936888496,
   "se": 0.5340337668376325,
   "si_iq": 111.89507640533274,
   "si_iq_low": 98.71896274256353,
   "si_iq_high": 125.07119006810196,
   "si_iq_display": 112,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.758698,
     "source_value_text": "0.758698",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "xiaomi/mimo-v2.6-flash-20260921",
     "source_model_name": "xiaomi/mimo-v2.6-flash-20260921",
     "p": 0.678264,
     "p_star": 0.677368201005025,
     "y": 0.7417032647635989,
     "v": 0.034136986699734806,
     "family_factor": 1.0,
     "w": 3.058220003853409
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.76,
     "source_value_text": "0.76",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "xiaomi/mimo-v2.6-flash-20260921",
     "source_model_name": "xiaomi/mimo-v2.6-flash-20260921",
     "p": 0.76,
     "p_star": 0.7549019607843137,
     "y": 1.124929596985483,
     "v": 0.10389610389610388,
     "family_factor": 1.0,
     "w": 3.4679759332079083
    }
   ]
  },
  {
   "slug": "deepseek-v3-2-exp",
   "name": "DeepSeek-V3.2-Exp",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.7831579484367787,
   "se": 0.3725378549745811,
   "si_iq": 111.74736922655168,
   "si_iq_low": 102.55581351295629,
   "si_iq_high": 120.93892494014707,
   "si_iq_display": 112,
   "domains": {
    "agentic": {
     "si_iq": 110.99864434790302,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "aider_polyglot",
     "score": 0.742,
     "source_value_text": "74.2",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-10-03",
     "source_row_id": "2025-10-03-09-45-34--deepseek-v3.2-reasoner",
     "source_model_name": "DeepSeek-V3.2-Exp (Reasoner)",
     "p": 0.742,
     "p_star": 0.740929203539823,
     "y": 1.0508037091964868,
     "v": 0.02294935409042912,
     "family_factor": 1.0,
     "w": 1.4169780725273853
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.8265989999999999,
     "source_value_text": "0.826599",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "deepseek/deepseek-v3.2-exp",
     "source_model_name": "deepseek/deepseek-v3.2-exp",
     "p": 0.7687986666666665,
     "p_star": 0.7674479195979899,
     "y": 1.1939564182857867,
     "v": 0.04018296755720072,
     "family_factor": 1.0,
     "w": 2.9633182125271165
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5672999999999999,
     "source_value_text": "56.73%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "14",
     "source_model_name": "DeepSeek-V3.2-Exp (Prompt + Thinking)",
     "p": 0.5672999999999999,
     "p_star": 0.5666336633663366,
     "y": 0.26812958521820673,
     "v": 0.03992084335496205,
     "family_factor": 1.0,
     "w": 5.0536200628286965
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.693333,
     "source_value_text": "0.693333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-01",
     "source_row_id": "deepseek/deepseek-v3.2-exp",
     "source_model_name": "deepseek/deepseek-v3.2-exp",
     "p": 0.693333,
     "p_star": 0.689542156862745,
     "y": 0.7979797153107386,
     "v": 0.08979790263632963,
     "family_factor": 1.0,
     "w": 3.725577424011
    }
   ]
  },
  {
   "slug": "glm-5",
   "name": "GLM-5",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.7740692666683506,
   "se": 0.2508896269806718,
   "si_iq": 111.61103900002526,
   "si_iq_low": 105.42088690256027,
   "si_iq_high": 117.80119109749025,
   "si_iq_display": 112,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8,
     "source_value_text": "0.8",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-12",
     "source_row_id": "ccbx7KQY9bTD563vzBXwSg",
     "source_model_name": "glm-5",
     "p": 0.7997997997997999,
     "p_star": 0.7932824128476303,
     "y": 1.3448257419821712,
     "v": 0.1298491959985025,
     "family_factor": 1.0,
     "w": 2.1753393472964664
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7207792207792207,
     "source_value_text": "0.7207792207792207",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-15",
     "source_row_id": "hKkJEu4ueLiNWsTtrJ78PS",
     "source_model_name": "glm-5",
     "p": 0.7207792207792207,
     "p_star": 0.7203230653643876,
     "y": 0.9460646811173473,
     "v": 0.010234636793241705,
     "family_factor": 1.0,
     "w": 6.414560810980047
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8781725888324873,
     "source_value_text": "0.8781725888324873",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-12",
     "source_row_id": "n4hyz75SVpwPEisKVVjvNg",
     "source_model_name": "glm-5",
     "p": 0.8375634517766497,
     "p_star": 0.8358671530240033,
     "y": 1.6277935501381084,
     "v": 0.05097743785134455,
     "family_factor": 0.5,
     "w": 1.912041552056595
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7285024173913045,
     "source_value_text": "0.728502",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5-20260211",
     "source_model_name": "z-ai/glm-5-20260211",
     "p": 0.638003223188406,
     "p_star": 0.6373097396547959,
     "y": 0.5637065921572825,
     "v": 0.03294439925335157,
     "family_factor": 0.5,
     "w": 1.5388309922322065
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7422222222222222,
     "source_value_text": "0.742222",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "z-ai/glm-5-20260211",
     "source_model_name": "z-ai/glm-5-20260211",
     "p": 0.7422222222222222,
     "p_star": 0.7374727668845317,
     "y": 1.0328743394216204,
     "v": 0.09929086707894852,
     "family_factor": 1.0,
     "w": 3.548114329325634
    }
   ]
  },
  {
   "slug": "gemini-3-1-flash-lite",
   "name": "Gemini 3.1 Flash-Lite",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.6199329233606594,
   "se": 0.17843630795872797,
   "si_iq": 109.29899385040989,
   "si_iq_low": 104.8964687270427,
   "si_iq_high": 113.70151897377707,
   "si_iq_display": 109,
   "domains": {
    "math": {
     "si_iq": 109.32347587514525,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "frontiermath_t13",
     "score": 0.2771929824561403,
     "source_value_text": "0.2771929824561403",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "MVZf59jt9uEoWG9w5W9apB",
     "source_model_name": "gemini-3.1-flash-lite_high",
     "p": 0.2771929824561403,
     "p_star": 0.2779720279720279,
     "y": -0.9545433907408014,
     "v": 0.017360317967929098,
     "family_factor": 1.0,
     "w": 4.260383821869282
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8,
     "source_value_text": "0.8",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "NMdaAXyqqPRmWfuxZUfHFF",
     "source_model_name": "gemini-3.1-flash-lite_high",
     "p": 0.7997997997997999,
     "p_star": 0.7932824128476303,
     "y": 1.3448257419821712,
     "v": 0.1298491959985025,
     "family_factor": 1.0,
     "w": 2.1753393472964664
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8181818181818182,
     "source_value_text": "0.8181818181818182",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "nE4hmJo3QV6X5jeGWAeAze",
     "source_model_name": "gemini-3.1-flash-lite_high",
     "p": 0.7575757575757577,
     "p_star": 0.756281407035176,
     "y": 1.1323992862454935,
     "v": 0.039081974585064655,
     "family_factor": 1.0,
     "w": 4.151150937510667
    }
   ]
  },
  {
   "slug": "qwen-3-5-plus-hosted-397b-a17b",
   "name": "Qwen 3.5 Plus (hosted 397B-A17B)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.5974130687768725,
   "se": 0.24255095894391862,
   "si_iq": 108.96119603165309,
   "si_iq_low": 102.97678230631199,
   "si_iq_high": 114.94560975699419,
   "si_iq_display": 109,
   "domains": {
    "reasoning": {
     "si_iq": 104.69364095721772,
     "n": 2
    },
    "knowledge": {
     "si_iq": 110.99508700377623,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.08,
     "source_value_text": "0.08",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "XEaDaqM3oaPcrtQ6XH5fGS",
     "source_model_name": "qwen3.5-plus",
     "p": 0.03198653198653199,
     "p_star": 0.03662032869953662,
     "y": -3.2698440778146587,
     "v": 0.6738631312623583,
     "family_factor": 1.0,
     "w": 0.9137362314096615
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.17,
     "source_value_text": "0.17",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "XbtWdvRz65dbPPnHcSBvmF",
     "source_model_name": "qwen3.5-plus_none",
     "p": 0.08570169640890066,
     "p_star": 0.08980365981079273,
     "y": -2.316034605079059,
     "v": 0.25556603990154425,
     "family_factor": 1.0,
     "w": 1.9886791814604803
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8666666666666667,
     "source_value_text": "0.8666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "cFbntXuxUtfreULvt7vEt7",
     "source_model_name": "qwen3.5-plus",
     "p": 0.8665331998665332,
     "p_star": 0.8585650868259564,
     "y": 1.8034228583617016,
     "v": 0.17533678826674742,
     "family_factor": 1.0,
     "w": 1.8159578425662388
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8484848484848485,
     "source_value_text": "0.8484848484848485",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "mGXYSUNCMisvaRzhQp6g2L",
     "source_model_name": "qwen3.5-plus",
     "p": 0.797979797979798,
     "p_star": 0.7964824120603015,
     "y": 1.3644526192048416,
     "v": 0.0437534530221292,
     "family_factor": 1.0,
     "w": 4.01625322419733
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.2535070140280561,
     "source_value_text": "0.2535070140280561",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "jrawnM2wHFbVfJFJsap4kS",
     "source_model_name": "qwen3.5-plus",
     "p": 0.2535070140280561,
     "p_star": 0.2537532607672888,
     "y": -1.0786939145719887,
     "v": 0.0052703294854141835,
     "family_factor": 1.0,
     "w": 1.6851227676840062
    }
   ]
  },
  {
   "slug": "gemini-2-5-pro-mar-2025",
   "name": "Gemini 2.5 Pro (Mar 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.5125529196912292,
   "se": 0.22480516488198587,
   "si_iq": 107.68829379536844,
   "si_iq_low": 102.14171867521652,
   "si_iq_high": 113.23486891552035,
   "si_iq_display": 108,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.9556268882175226,
     "source_value_text": "0.9556268882175226",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-07",
     "source_row_id": "XRkZCzSoQC5yYiQ3xitNdC",
     "source_model_name": "gemini-2.5-pro-preview-03-25",
     "p": 0.9556268882175226,
     "p_star": 0.9552830188679245,
     "y": 3.0616543308347786,
     "v": 0.017654348458369697,
     "family_factor": 1.0,
     "w": 4.249736678257309
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.7290000000000001,
     "source_value_text": "72.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-12",
     "source_row_id": "2025-04-12-04-55-50--gemini-25-pro-diff-fenced",
     "source_model_name": "Gemini 2.5 Pro Preview 03-25",
     "p": 0.7290000000000001,
     "p_star": 0.7279867256637169,
     "y": 0.9844319462399271,
     "v": 0.022246007598618257,
     "family_factor": 1.0,
     "w": 1.4189780408998751
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8383838383838383,
     "source_value_text": "0.8383838383838383",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-31",
     "source_row_id": "WKjzEQdfnBHnYeZoKeCWnB",
     "source_model_name": "gemini-2.5-pro-exp-03-25",
     "p": 0.7845117845117845,
     "p_star": 0.7830820770519263,
     "y": 1.2837184675891495,
     "v": 0.04196380445515395,
     "family_factor": 1.0,
     "w": 4.066883607448049
    }
   ]
  },
  {
   "slug": "qwen-3-6-flash",
   "name": "Qwen 3.6 Flash",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.4980973976913271,
   "se": 0.1619394219787388,
   "si_iq": 107.4714609653699,
   "si_iq_low": 103.47596037537866,
   "si_iq_high": 111.46696155536115,
   "si_iq_display": 107,
   "domains": {
    "reasoning": {
     "si_iq": 106.3449883672893,
     "n": 2
    },
    "math": {
     "si_iq": 108.19635241730087,
     "n": 2
    },
    "knowledge": {
     "si_iq": 106.93486093220707,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.12,
     "source_value_text": "0.12",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "j99TDv5LAYUSvTUcR47T75",
     "source_model_name": "qwen3.6-flash",
     "p": 0.07407407407407406,
     "p_star": 0.07829116244957827,
     "y": -2.465794650463951,
     "v": 0.22640239472187967,
     "family_factor": 1.0,
     "w": 2.166365175687689
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.18,
     "source_value_text": "0.18",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "3QtkFWzSLzd4hgYGsNd5cL",
     "source_model_name": "qwen3.6-flash_none",
     "p": 0.09671733862084159,
     "p_star": 0.10071023625825899,
     "y": -2.189357854798553,
     "v": 0.217395934326983,
     "family_factor": 1.0,
     "w": 2.227838181626115
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.22456140350877193,
     "source_value_text": "0.22456140350877193",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-29",
     "source_row_id": "RoscWx4NUGVqcHdko6QhKd",
     "source_model_name": "qwen3.6-flash_none",
     "p": 0.22456140350877193,
     "p_star": 0.22552447552447552,
     "y": -1.2337573656834635,
     "v": 0.019948553729854587,
     "family_factor": 1.0,
     "w": 4.1684537616525885
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8444444444444444,
     "source_value_text": "0.8444444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "9zx2EXPTvPmxsL9qFCjP3x",
     "source_model_name": "qwen3.6-flash",
     "p": 0.8442887331776221,
     "p_star": 0.8368041954998477,
     "y": 1.6346393725608352,
     "v": 0.15591331757211294,
     "family_factor": 1.0,
     "w": 1.9537865584471066
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8333333333333334,
     "source_value_text": "0.8333333333333334",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "H2FvRXagQRQmiNa7WrNMU2",
     "source_model_name": "qwen3.6-flash",
     "p": 0.7777777777777778,
     "p_star": 0.7763819095477387,
     "y": 1.2447049071656053,
     "v": 0.04116355168726432,
     "family_factor": 1.0,
     "w": 4.089938672474716
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.15915915915915915,
     "source_value_text": "0.15915915915915915",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "FoMSS4FmH3VxpsvZiUJPCv",
     "source_model_name": "qwen3.6-flash",
     "p": 0.15915915915915915,
     "p_star": 0.1594996594996595,
     "y": -1.661955570540748,
     "v": 0.007444476975651728,
     "family_factor": 1.0,
     "w": 1.6744968727587755
    }
   ]
  },
  {
   "slug": "qwen3-7-flash",
   "name": "Qwen3.7 Flash",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.49721949876039745,
   "se": 0.17775901449717824,
   "si_iq": 107.45829248140596,
   "si_iq_low": 103.07247809092983,
   "si_iq_high": 111.84410687188209,
   "si_iq_display": 107,
   "domains": {
    "math": {
     "si_iq": 107.33395584394465,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.15,
     "source_value_text": "0.15",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "5e4Jp9dxtNisWx2wbRRZxM",
     "source_model_name": "qwen3.7-flash",
     "p": 0.06367041198501872,
     "p_star": 0.06799050691586012,
     "y": -2.617974909094305,
     "v": 0.3857893753457996,
     "family_factor": 1.0,
     "w": 1.4555830511591725
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.19298245614035087,
     "source_value_text": "0.19298245614035087",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-29",
     "source_row_id": "doNrgGQY5SytQV22WRqw5L",
     "source_model_name": "qwen3.7-flash_none",
     "p": 0.19298245614035087,
     "p_star": 0.19405594405594406,
     "y": -1.4238678416843145,
     "v": 0.02227824353637803,
     "family_factor": 1.0,
     "w": 4.089034856403126
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8666666666666667,
     "source_value_text": "0.8666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "TjoS7sNuqVTc4LVyGRo4wa",
     "source_model_name": "qwen3.7-flash",
     "p": 0.8665331998665332,
     "p_star": 0.8585650868259564,
     "y": 1.8034228583617016,
     "v": 0.17533678826674742,
     "family_factor": 1.0,
     "w": 1.8159578425662388
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8232323232323232,
     "source_value_text": "0.8232323232323232",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "i6i3gQf3ng2aAipvowPpws",
     "source_model_name": "qwen3.7-flash",
     "p": 0.7643097643097643,
     "p_star": 0.7629815745393634,
     "y": 1.1690959996167205,
     "v": 0.039726851603820106,
     "family_factor": 1.0,
     "w": 4.131992258915545
    }
   ]
  },
  {
   "slug": "gpt-5-5-instant",
   "name": "GPT-5.5 Instant",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.4949561911506781,
   "se": 0.1591030982627605,
   "si_iq": 107.42434286726018,
   "si_iq_low": 103.49882235341175,
   "si_iq_high": 111.34986338110859,
   "si_iq_display": 107,
   "domains": {
    "math": {
     "si_iq": 107.07529999687743,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "frontiermath_t4",
     "score": 0.024390243902439025,
     "source_value_text": "0.024390243902439025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "2UmuBfhBvYbbnTg5BnQqov",
     "source_model_name": "gpt-5.5-instant",
     "p": 0.024390243902439025,
     "p_star": 0.03571428571428571,
     "y": -3.295836866004329,
     "v": 0.6748971193415636,
     "family_factor": 1.0,
     "w": 0.6452469463621882
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.2631578947368421,
     "source_value_text": "0.2631578947368421",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "gGcHjE6ppy54ahN2pfxsGH",
     "source_model_name": "gpt-5.5-instant",
     "p": 0.2631578947368421,
     "p_star": 0.263986013986014,
     "y": -1.025352996867457,
     "v": 0.017932705164304473,
     "family_factor": 1.0,
     "w": 4.239706019660935
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6805555555555556,
     "source_value_text": "0.6805555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "hGzLQWbxPdgQiiMbaDqF8k",
     "source_model_name": "gpt-5.5-instant",
     "p": 0.6802357913469025,
     "p_star": 0.6763176219697958,
     "y": 0.7369001004325827,
     "v": 0.0972902689956975,
     "family_factor": 1.0,
     "w": 2.534336855767093
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8251262626262627,
     "source_value_text": "0.8251262626262627",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-02",
     "source_row_id": "WPVhgi8NT9grAT7kfipT9G",
     "source_model_name": "gpt-5.5-instant",
     "p": 0.7668350168350169,
     "p_star": 0.7654941373534339,
     "y": 1.1830409682849006,
     "v": 0.039980765323955864,
     "family_factor": 1.0,
     "w": 4.124497161116892
    }
   ]
  },
  {
   "slug": "qwen-3-5-flash-hosted-35b-a3b",
   "name": "Qwen 3.5 Flash (hosted 35B-A3B)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.48919239145331234,
   "se": 0.15981683849686498,
   "si_iq": 107.33788587179968,
   "si_iq_low": 103.39475538076584,
   "si_iq_high": 111.28101636283353,
   "si_iq_display": 107,
   "domains": {
    "reasoning": {
     "si_iq": 109.04199665858691,
     "n": 2
    },
    "math": {
     "si_iq": 106.4879164266381,
     "n": 2
    },
    "knowledge": {
     "si_iq": 107.21740996803136,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.14,
     "source_value_text": "0.14",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "fEgRyzyFYZraNnkkbRVSSg",
     "source_model_name": "qwen3.5-flash",
     "p": 0.09511784511784513,
     "p_star": 0.09912657932459913,
     "y": -2.206967147657535,
     "v": 0.167569741192018,
     "family_factor": 1.0,
     "w": 2.6427008451568565
    },
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.2,
     "source_value_text": "0.2",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "b9csPZ2c9CAsRXmzzfVoEW",
     "source_model_name": "qwen3.5-flash",
     "p": 0.11874862304472353,
     "p_star": 0.12252338915319162,
     "y": -1.968748357056755,
     "v": 0.16676370900472426,
     "family_factor": 1.0,
     "w": 2.6506858216385987
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.1824561403508772,
     "source_value_text": "0.1824561403508772",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "afxoicJc4C6caVDwUpsiME",
     "source_model_name": "qwen3.5-flash_none",
     "p": 0.1824561403508772,
     "p_star": 0.18356643356643357,
     "y": -1.492368907511374,
     "v": 0.023248699908228813,
     "family_factor": 1.0,
     "w": 4.056837925043435
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8444444444444444,
     "source_value_text": "0.8444444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "awDKyKbPXRzBVZzfdQucef",
     "source_model_name": "qwen3.5-flash",
     "p": 0.8442887331776221,
     "p_star": 0.8368041954998477,
     "y": 1.6346393725608352,
     "v": 0.15591331757211294,
     "family_factor": 1.0,
     "w": 1.9537865584471066
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8232323232323232,
     "source_value_text": "0.8232323232323232",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "S7wbot7JR53BAjM8F9gaws",
     "source_model_name": "qwen3.5-flash",
     "p": 0.7643097643097643,
     "p_star": 0.7629815745393634,
     "y": 1.1690959996167205,
     "v": 0.039726851603820106,
     "family_factor": 1.0,
     "w": 4.131992258915545
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.2032032032032032,
     "source_value_text": "0.2032032032032032",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "K8zTckSXLKLesoLBv24TWc",
     "source_model_name": "qwen3.5-flash",
     "p": 0.2032032032032032,
     "p_star": 0.2034997034997035,
     "y": -1.3645629537263413,
     "v": 0.006157183862385602,
     "family_factor": 1.0,
     "w": 1.680772125919417
    }
   ]
  },
  {
   "slug": "qwen3-max",
   "name": "Qwen3-Max",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.416672241505493,
   "se": 0.1484151420493561,
   "si_iq": 106.2500836225824,
   "si_iq_low": 102.58826502167562,
   "si_iq_high": 109.91190222348916,
   "si_iq_display": 106,
   "domains": {
    "math": {
     "si_iq": 106.61366137358449,
     "n": 3
    },
    "knowledge": {
     "si_iq": 104.73499458808323,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.05,
     "source_value_text": "0.05",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "SfzmmHYZjuvWnvoYWit58g",
     "source_model_name": "qwen3-max-2025-09-23",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.18947368421052632,
     "source_value_text": "0.18947368421052632",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "NrTH3EYHjp4hPdxgpCPGTX",
     "source_model_name": "qwen3-max-2025-09-23",
     "p": 0.18947368421052632,
     "p_star": 0.19055944055944055,
     "y": -1.4463791718570904,
     "v": 0.022589018566588067,
     "family_factor": 1.0,
     "w": 4.078668757172644
    },
    {
     "benchmark": "math_level_5",
     "score": 0.9712990936555891,
     "source_value_text": "0.9712990936555891",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-09",
     "source_row_id": "f2vxirYMpXwkaZxb4ywnYM",
     "source_model_name": "qwen3-max-2025-09-23",
     "p": 0.9712990936555891,
     "p_star": 0.9709433962264151,
     "y": 3.5090223904280613,
     "v": 0.02673113905138782,
     "family_factor": 1.0,
     "w": 3.945360262226133
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7333333333333333,
     "source_value_text": "0.7333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-06",
     "source_row_id": "ULeuPtwp3ZoyuXQYuuQ82i",
     "source_model_name": "qwen3-max-2025-09-23",
     "p": 0.7330663997330663,
     "p_star": 0.727999738869304,
     "y": 0.9844976631657507,
     "v": 0.10754570019480768,
     "family_factor": 1.0,
     "w": 2.4091079676942826
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.726010101010101,
     "source_value_text": "0.726010101010101",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-06",
     "source_row_id": "46RCssznDADYeg8MuSgvsj",
     "source_model_name": "qwen3-max-2025-09-23",
     "p": 0.6346801346801346,
     "p_star": 0.6340033500837521,
     "y": 0.5494300583418585,
     "v": 0.03287581131965213,
     "family_factor": 1.0,
     "w": 4.345036643281339
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.4874874874874875,
     "source_value_text": "0.4874874874874875",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "fXG2GPt5F25tHRTPhAoZ4K",
     "source_model_name": "qwen3-max-2025-09-23",
     "p": 0.4874874874874875,
     "p_star": 0.4874999874999875,
     "y": -0.050010470605981,
     "v": 0.003994508556861157,
     "family_factor": 1.0,
     "w": 1.6914212174497825
    }
   ]
  },
  {
   "slug": "gemma-4-26b-a4b",
   "name": "Gemma 4 26B A4B",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.3999227358643659,
   "se": 0.26288394293140877,
   "si_iq": 105.99884103796549,
   "si_iq_low": 99.512755461968,
   "si_iq_high": 112.48492661396298,
   "si_iq_display": 106,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.8222222222222222,
     "source_value_text": "0.8222222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "mstwSH7noJfvhGcd6Lz5kd",
     "source_model_name": "gemma-4-26b-a4b-it_minimal",
     "p": 0.8220442664887109,
     "p_star": 0.8150433041737388,
     "y": 1.4831195247214983,
     "v": 0.14124697730020933,
     "family_factor": 1.0,
     "w": 2.0725648279430944
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7323232323232324,
     "source_value_text": "0.7323232323232324",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "Usx9KaiXvHZU4qrzgc4sLg",
     "source_model_name": "gemma-4-26b-a4b-it_minimal",
     "p": 0.6430976430976432,
     "p_star": 0.6423785594639867,
     "y": 0.585702788138632,
     "v": 0.033057881112878294,
     "family_factor": 0.5,
     "w": 2.1695455555159358
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7762077565217391,
     "source_value_text": "0.776208",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "google/gemma-4-26b-a4b-it-20260403",
     "source_model_name": "google/gemma-4-26b-a4b-it-20260403",
     "p": 0.7016103420289855,
     "p_star": 0.7005972247323574,
     "y": 0.8501434081092853,
     "v": 0.03517691600353135,
     "family_factor": 0.5,
     "w": 1.5207330475124037
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.5733334999999999,
     "source_value_text": "0.573333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "google/gemma-4-26b-a4b-it-20260403",
     "source_model_name": "google/gemma-4-26b-a4b-it-20260403",
     "p": 0.5733334999999999,
     "p_star": 0.5718955882352941,
     "y": 0.2895893181160693,
     "v": 0.07851691047927586,
     "family_factor": 1.0,
     "w": 3.961007275378743
    }
   ]
  },
  {
   "slug": "qwen3-5-35b-a3b",
   "name": "Qwen3.5-35B-A3B",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.3811265277892603,
   "se": 0.2518038003184793,
   "si_iq": 105.7168979168389,
   "si_iq_low": 99.50419059430313,
   "si_iq_high": 111.92960523937468,
   "si_iq_display": 106,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7,
     "source_value_text": "0.7",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "h9aoDxyWEhybvARHpyuoco",
     "source_model_name": "qwen3.5-35b-a3b_none",
     "p": 0.6996996996996997,
     "p_star": 0.6953584018801411,
     "y": 0.8252914012844569,
     "v": 0.10053648024210182,
     "family_factor": 1.0,
     "w": 2.493311937041902
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.8345959595959596,
     "source_value_text": "0.8345959595959596",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "RWjuCuVGvaRd4vDjJJ6aP2",
     "source_model_name": "qwen3.5-35b-a3b",
     "p": 0.7794612794612794,
     "p_star": 0.7780569514237855,
     "y": 1.2543789128276157,
     "v": 0.04135816980469651,
     "family_factor": 0.5,
     "w": 2.0421538775838193
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7500000000000001,
     "source_value_text": "0.75",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.5-35b-a3b-20260224",
     "source_model_name": "qwen/qwen3.5-35b-a3b-20260224",
     "p": 0.6666666666666669,
     "p_star": 0.6658291457286434,
     "y": 0.6893806977644692,
     "v": 0.033721041657186764,
     "family_factor": 0.5,
     "w": 1.5324864645921676
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.7351189375,
     "source_value_text": "0.735119",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.5-35b-a3b-20260224",
     "source_model_name": "qwen/qwen3.5-35b-a3b-20260224",
     "p": 0.7351189375,
     "p_star": 0.7305087622549019,
     "y": 0.9972053491767656,
     "v": 0.09764715030169864,
     "family_factor": 1.0,
     "w": 3.5776219394369395
    }
   ]
  },
  {
   "slug": "claude-opus-4-1",
   "name": "Claude Opus 4.1",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.3610123103699216,
   "se": 0.15057316185734712,
   "si_iq": 105.41518465554883,
   "si_iq_low": 101.70012164194326,
   "si_iq_high": 109.1302476691544,
   "si_iq_display": 105,
   "domains": {
    "math": {
     "si_iq": 102.62425336064864,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.21,
     "source_value_text": "0.21",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-07-25",
     "source_row_id": "2AbeCjy9w4KJWKhbKjtFTJ",
     "source_model_name": "claude-opus-4-1-20250805_24K",
     "p": 0.12976426525666446,
     "p_star": 0.13342996560065787,
     "y": -1.8709661924088827,
     "v": 0.1493151779008844,
     "family_factor": 1.0,
     "w": 2.8361962843179116
    },
    {
     "benchmark": "frontiermath_t4",
     "score": 0.024390243902439025,
     "source_value_text": "0.024390243902439025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tier_4_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tier-4-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "9zT72xRR6wZhiwraJTNPyz",
     "source_model_name": "claude-opus-4-1-20250805_32K",
     "p": 0.024390243902439025,
     "p_star": 0.03571428571428571,
     "y": -3.295836866004329,
     "v": 0.6748971193415636,
     "family_factor": 1.0,
     "w": 0.6452469463621882
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.12631578947368421,
     "source_value_text": "0.12631578947368421",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-06-11",
     "source_row_id": "5eRkmXCURH2pRbhJoukfnC",
     "source_model_name": "claude-opus-4-1-20250805_32K",
     "p": 0.12631578947368421,
     "p_star": 0.12762237762237763,
     "y": -1.9221466546031274,
     "v": 0.03129546764762402,
     "family_factor": 1.0,
     "w": 3.808204570640015
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6888888888888889,
     "source_value_text": "0.6888888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-08-05",
     "source_row_id": "UH9RY8MCAotDgFocHKA4j6",
     "source_model_name": "claude-opus-4-1-20250805_27K",
     "p": 0.6885774663552441,
     "p_star": 0.6844779562170866,
     "y": 0.7744278910982403,
     "v": 0.09861485469432998,
     "family_factor": 1.0,
     "w": 2.5174350668257137
    },
    {
     "benchmark": "swe_bench_verified",
     "score": 0.7334710743801653,
     "source_value_text": "0.7334710743801653",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#swe_bench_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/swe-bench-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-02-11",
     "source_row_id": "cA6Mq67yaynLhY8F5kes3c",
     "source_model_name": "claude-opus-4-1-20250805",
     "p": 0.7334710743801653,
     "p_star": 0.7329886961273138,
     "y": 1.009839286280275,
     "v": 0.010534877325037498,
     "family_factor": 1.0,
     "w": 6.397137250238565
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7727272727272727,
     "source_value_text": "0.7727272727272727",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-08-05",
     "source_row_id": "erLgyKQs2mg2memE9SJvK5",
     "source_model_name": "claude-opus-4-1-20250805_16K",
     "p": 0.6969696969696969,
     "p_star": 0.6959798994974874,
     "y": 0.8282269605905973,
     "v": 0.034947080575200316,
     "family_factor": 1.0,
     "w": 4.278345753970519
    }
   ]
  },
  {
   "slug": "kimi-k2-sep-2025",
   "name": "Kimi K2 (Sep 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.3413941200211385,
   "se": 0.5269275994063363,
   "si_iq": 105.12091180031707,
   "si_iq_low": 92.12012725640842,
   "si_iq_high": 118.12169634422573,
   "si_iq_display": 105,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7474749999999999,
     "source_value_text": "0.7474749999999999",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-01",
     "source_row_id": "moonshotai/kimi-k2-0905",
     "source_model_name": "moonshotai/kimi-k2-0905",
     "p": 0.6632999999999999,
     "p_star": 0.6624793969849245,
     "y": 0.6743629040661677,
     "v": 0.033611792240543524,
     "family_factor": 1.0,
     "w": 3.0667515566377808
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6366665,
     "source_value_text": "0.636667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "moonshotai/kimi-k2-0905",
     "source_model_name": "moonshotai/kimi-k2-0905",
     "p": 0.6366665,
     "p_star": 0.6339867647058824,
     "y": 0.5493585836077702,
     "v": 0.08284239968457145,
     "family_factor": 1.0,
     "w": 3.867302017510189
    }
   ]
  },
  {
   "slug": "deepseek-r1-may-2025",
   "name": "DeepSeek-R1 (May 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.28383413399271445,
   "se": 0.18511405995593547,
   "si_iq": 104.25751200989072,
   "si_iq_low": 99.69022798026931,
   "si_iq_high": 108.82479603951212,
   "si_iq_display": 104,
   "domains": {
    "math": {
     "si_iq": 105.20687951141392,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.9663897280966768,
     "source_value_text": "0.9663897280966768",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-29",
     "source_row_id": "2wd9khVKiBzsAMUquz2R5s",
     "source_model_name": "DeepSeek-R1-0528",
     "p": 0.9663897280966768,
     "p_star": 0.9660377358490566,
     "y": 3.347952867143343,
     "v": 0.022986111111111117,
     "family_factor": 1.0,
     "w": 4.06549971767363
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6638888888888889,
     "source_value_text": "0.6638888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-29",
     "source_row_id": "bBV5wCrrZtihrgxEsg9jPD",
     "source_model_name": "DeepSeek-R1-0528",
     "p": 0.6635524413302191,
     "p_star": 0.6599969534752143,
     "y": 0.6632806411260924,
     "v": 0.09491400422251765,
     "family_factor": 1.0,
     "w": 2.5652338424549024
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7632575757575758,
     "source_value_text": "0.7632575757575758",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-29",
     "source_row_id": "LiRiryJsGb3h5UuxX8bmJv",
     "source_model_name": "DeepSeek-R1-0528",
     "p": 0.6843434343434344,
     "p_star": 0.6834170854271356,
     "y": 0.769520159344519,
     "v": 0.03438066403031801,
     "family_factor": 0.5,
     "w": 2.148189523231438
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7851099187817259,
     "source_value_text": "0.7851099187817259",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "deepseek/deepseek-r1-0528",
     "source_model_name": "deepseek/deepseek-r1-0528",
     "p": 0.7134798917089679,
     "p_star": 0.7124071284340485,
     "y": 0.9071037179818474,
     "v": 0.03582187544474499,
     "family_factor": 0.5,
     "w": 1.5155836558609845
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.47874697986577186,
     "source_value_text": "0.47874697986577186",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "deepseek/deepseek-r1-0528",
     "source_model_name": "deepseek/deepseek-r1-0528",
     "p": 0.47874697986577186,
     "p_star": 0.47916370575075673,
     "y": -0.0833934732032994,
     "v": 0.07702726841016286,
     "family_factor": 1.0,
     "w": 3.994338203017505
    }
   ]
  },
  {
   "slug": "gemini-2-5-pro-may-2025",
   "name": "Gemini 2.5 Pro (May 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.26772962701170183,
   "se": 0.22414612462648614,
   "si_iq": 104.01594440517553,
   "si_iq_low": 98.48562966002991,
   "si_iq_high": 109.54625915032113,
   "si_iq_display": 104,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.9590256797583081,
     "source_value_text": "0.9590256797583081",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-08",
     "source_row_id": "Mi8LCxmduKukxazAtmuhqg",
     "source_model_name": "gemini-2.5-pro-preview-05-06",
     "p": 0.9590256797583081,
     "p_star": 0.9586792452830188,
     "y": 3.1441916417772307,
     "v": 0.019037707854222763,
     "family_factor": 1.0,
     "w": 4.200349696016621
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.769,
     "source_value_text": "76.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-05-07",
     "source_row_id": "2025-05-07-19-32-40--gemini0506-diff-fenced-completion_cost",
     "source_model_name": "Gemini 2.5 Pro Preview 05-06",
     "p": 0.769,
     "p_star": 0.7678097345132744,
     "y": 1.195984815518951,
     "v": 0.024709731014672852,
     "family_factor": 1.0,
     "w": 1.4119970605374952
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6666666666666666,
     "source_value_text": "0.6666666666666666",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-06-03",
     "source_row_id": "TT66gGiVoeYLGQMCESPrEG",
     "source_model_name": "gemini-2.5-pro-preview-05-06",
     "p": 0.5555555555555555,
     "p_star": 0.5552763819095476,
     "y": 0.22201296894392325,
     "v": 0.032401230002994844,
     "family_factor": 1.0,
     "w": 4.360611069674854
    }
   ]
  },
  {
   "slug": "gemma-4-31b-it",
   "name": "Gemma 4 31B IT",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.26456328873569296,
   "se": 0.2452914040093254,
   "si_iq": 103.9684493310354,
   "si_iq_low": 97.91642112528007,
   "si_iq_high": 110.02047753679072,
   "si_iq_display": 104,
   "domains": {
    "knowledge": {
     "si_iq": 100.07120293104059,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7333333333333333,
     "source_value_text": "0.7333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "jFJucVunfLgoQqoFvPVQWP",
     "source_model_name": "gemma-4-31b-it_minimal",
     "p": 0.7330663997330663,
     "p_star": 0.727999738869304,
     "y": 0.9844976631657507,
     "v": 0.10754570019480768,
     "family_factor": 1.0,
     "w": 2.4091079676942826
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7575757575757576,
     "source_value_text": "0.7575757575757576",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "P5L8qbXo42vTvbU3UvTNjk",
     "source_model_name": "gemma-4-31b-it_minimal",
     "p": 0.6767676767676768,
     "p_star": 0.6758793969849246,
     "y": 0.7348989752401669,
     "v": 0.03407977379566213,
     "family_factor": 0.5,
     "w": 2.153010304408437
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.81649825,
     "source_value_text": "0.81649825",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-10-17",
     "source_row_id": "google/gemma-4-31b-it-20260402",
     "source_model_name": "google/gemma-4-31b-it-20260402",
     "p": 0.755331,
     "p_star": 0.7540479296482411,
     "y": 1.1203192521794725,
     "v": 0.03887697777424204,
     "family_factor": 0.5,
     "w": 1.491657907416796
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.104,
     "source_value_text": "0.104",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "D5cbXacPnJ8akq2jAtifEQ",
     "source_model_name": "gemma-4-31b-it",
     "p": 0.104,
     "p_star": 0.1043956043956044,
     "y": -2.149311221640322,
     "v": 0.01067415280583449,
     "family_factor": 1.0,
     "w": 1.6589572987535623
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.756666625,
     "source_value_text": "0.756667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "google/gemma-4-31b-it-20260402",
     "source_model_name": "google/gemma-4-31b-it-20260402",
     "p": 0.756666625,
     "p_star": 0.7516339460784314,
     "y": 1.107345749815366,
     "v": 0.10297481703509688,
     "family_factor": 1.0,
     "w": 3.483716805441336
    }
   ]
  },
  {
   "slug": "qwen3-coder-next",
   "name": "qwen3-coder-next",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.21591787033614862,
   "se": 0.5258933035651309,
   "si_iq": 103.23876805504223,
   "si_iq_low": 90.26350249590743,
   "si_iq_high": 116.21403361417703,
   "si_iq_display": 103,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7575756666666668,
     "source_value_text": "0.757576",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3-coder-next-2025-02-03",
     "source_model_name": "qwen/qwen3-coder-next-2025-02-03",
     "p": 0.6767675555555557,
     "p_star": 0.6758792763819097,
     "y": 0.7348984247085361,
     "v": 0.034079769204514346,
     "family_factor": 1.0,
     "w": 3.0591471721328207
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.5762463812316716,
     "source_value_text": "0.576246",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3-coder-next-2025-02-03",
     "source_model_name": "qwen/qwen3-coder-next-2025-02-03",
     "p": 0.5762463812316716,
     "p_star": 0.5747513541486976,
     "y": 0.3012634727942811,
     "v": 0.07865144566349642,
     "family_factor": 1.0,
     "w": 3.9580244008684753
    }
   ]
  },
  {
   "slug": "o1",
   "name": "o1",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.1895505560011788,
   "se": 0.1441490813943678,
   "si_iq": 102.84325834001768,
   "si_iq_low": 99.28669544309992,
   "si_iq_high": 106.39982123693545,
   "si_iq_display": 103,
   "domains": {
    "math": {
     "si_iq": 102.91679923765554,
     "n": 3
    },
    "knowledge": {
     "si_iq": 105.68245161951582,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.1,
     "source_value_text": "0.1",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "UtRhB562A5f4SuFsg5MPrJ",
     "source_model_name": "o1-2024-12-17_high",
     "p": 0.05303030303030304,
     "p_star": 0.05745574557455746,
     "y": -2.797567863222301,
     "v": 0.34544158934032293,
     "family_factor": 1.0,
     "w": 1.5874287406206002
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.14736842105263157,
     "source_value_text": "0.14736842105263157",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "NMJhDtxtyQJCHQ4EApr9LM",
     "source_model_name": "o1-2024-12-17_high",
     "p": 0.14736842105263157,
     "p_star": 0.14860139860139857,
     "y": -1.7456128665922737,
     "v": 0.027539557917622907,
     "family_factor": 1.0,
     "w": 3.9203523060895913
    },
    {
     "benchmark": "math_level_5",
     "score": 0.947129909365559,
     "source_value_text": "0.947129909365559",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-13",
     "source_row_id": "jVXtRkTBDnqH8p4sjVUbgN",
     "source_model_name": "o1-2024-12-17_high",
     "p": 0.947129909365559,
     "p_star": 0.9467924528301886,
     "y": 2.8788796559882535,
     "v": 0.01497022068072668,
     "family_factor": 1.0,
     "w": 4.348952250761564
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7333333333333333,
     "source_value_text": "0.7333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-27",
     "source_row_id": "KvcqycaJpCQMBigiEosyzC",
     "source_model_name": "o1-2024-12-17_medium",
     "p": 0.7330663997330663,
     "p_star": 0.727999738869304,
     "y": 0.9844976631657507,
     "v": 0.10754570019480768,
     "family_factor": 1.0,
     "w": 2.4091079676942826
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7676767676767676,
     "source_value_text": "0.7676767676767676",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-13",
     "source_row_id": "NAkCFiFiDSN3NXMj7HMvMS",
     "source_model_name": "o1-2024-12-17_high",
     "p": 0.6902356902356902,
     "p_star": 0.6892797319932998,
     "y": 0.7967541380696347,
     "v": 0.034634567993666605,
     "family_factor": 1.0,
     "w": 4.288276612710527
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.411,
     "source_value_text": "0.411",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "LQfu4ngArcgMEyQZxuR7r4",
     "source_model_name": "o1-2024-12-17_high",
     "p": 0.411,
     "p_star": 0.4110889110889111,
     "y": -0.359465699860301,
     "v": 0.004122364134607556,
     "family_factor": 1.0,
     "w": 1.6907879003536281
    }
   ]
  },
  {
   "slug": "deepseek-v3-1-terminus",
   "name": "DeepSeek-V3.1-Terminus",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.15583811605956496,
   "se": 0.5275799794461019,
   "si_iq": 102.33757174089348,
   "si_iq_low": 89.3206911482159,
   "si_iq_high": 115.35445233357106,
   "si_iq_display": 102,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7942762,
     "source_value_text": "0.794276",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-29",
     "source_row_id": "deepseek/deepseek-v3.1-terminus",
     "source_model_name": "deepseek/deepseek-v3.1-terminus",
     "p": 0.7257016,
     "p_star": 0.7245674211055275,
     "y": 0.9672319403004438,
     "v": 0.036578934438520214,
     "family_factor": 1.0,
     "w": 3.019167141248652
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.48266679999999995,
     "source_value_text": "0.48266679999999995",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-29",
     "source_row_id": "deepseek/deepseek-v3.1-terminus",
     "source_model_name": "deepseek/deepseek-v3.1-terminus",
     "p": 0.48266679999999995,
     "p_star": 0.4830066666666666,
     "y": -0.06799952333896189,
     "v": 0.07698242439793049,
     "family_factor": 1.0,
     "w": 3.995350293070208
    }
   ]
  },
  {
   "slug": "gemini-2-5-flash-jun-2025",
   "name": "Gemini 2.5 Flash (Jun 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.14149741121350892,
   "se": 0.44064997722060506,
   "si_iq": 102.12246116820263,
   "si_iq_low": 91.25038800373432,
   "si_iq_high": 112.99453433267095,
   "si_iq_display": 102,
   "domains": {
    "agentic": {
     "si_iq": 102.12957500053899,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.738309,
     "source_value_text": "0.738309",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-2.5-flash",
     "source_model_name": "google/gemini-2.5-flash",
     "p": 0.6510786666666667,
     "p_star": 0.6503194773869347,
     "y": 0.6204438007129528,
     "v": 0.03325645160862508,
     "family_factor": 1.0,
     "w": 3.072550958270296
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5624,
     "source_value_text": "56.24%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "15",
     "source_model_name": "Gemini-2.5-Flash (FC)",
     "p": 0.5624,
     "p_star": 0.5617821782178218,
     "y": 0.24839809475780192,
     "v": 0.03981981692122414,
     "family_factor": 1.0,
     "w": 5.057271542451943
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.5511113333333334,
     "source_value_text": "0.5511113333333334",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "google/gemini-2.5-flash",
     "source_model_name": "google/gemini-2.5-flash",
     "p": 0.5511113333333334,
     "p_star": 0.5501091503267975,
     "y": 0.2011117166154716,
     "v": 0.07767363377938757,
     "family_factor": 1.0,
     "w": 3.979807054909128
    }
   ]
  },
  {
   "slug": "gemini-2-5-flash-may-2025",
   "name": "Gemini 2.5 Flash (May 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.10137695071003792,
   "se": 0.2933891890029259,
   "si_iq": 101.52065426065057,
   "si_iq_low": 94.28191854432728,
   "si_iq_high": 108.75938997697385,
   "si_iq_display": 102,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7083333333333334,
     "source_value_text": "0.7083333333333334",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-20",
     "source_row_id": "9e62UjoHQbcZD2xjgfRkdK",
     "source_model_name": "gemini-2.5-flash-preview-05-20",
     "p": 0.7080413747080414,
     "p_star": 0.7035187361274319,
     "y": 0.8641104834776007,
     "v": 0.10210368710081774,
     "family_factor": 1.0,
     "w": 2.4739776259033768
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.551,
     "source_value_text": "55.1",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-05-25",
     "source_row_id": "2025-05-25-22-58-44--flash25-05-20-24k-think",
     "source_model_name": "gemini-2.5-flash-preview-05-20 (24k think)",
     "p": 0.551,
     "p_star": 0.5507743362831858,
     "y": 0.2037998189558849,
     "v": 0.017804401732783724,
     "family_factor": 1.0,
     "w": 1.4317393329126793
    }
   ]
  },
  {
   "slug": "gemini-2-5-flash-apr-2025",
   "name": "Gemini 2.5 Flash (Apr 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.07960175569193662,
   "se": 0.29610520275964536,
   "si_iq": 101.19402633537905,
   "si_iq_low": 93.88827892767884,
   "si_iq_high": 108.49977374307926,
   "si_iq_display": 101,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7305555555555555,
     "source_value_text": "0.7305555555555555",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-22",
     "source_row_id": "KpZYG5nvdJ6QYweLz6dn5a",
     "source_model_name": "gemini-2.5-flash-preview-04-17",
     "p": 0.7302858413969525,
     "p_star": 0.7252796274535405,
     "y": 0.9708035202902046,
     "v": 0.10688074862731876,
     "family_factor": 1.0,
     "w": 2.4168512697172955
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.47100000000000003,
     "source_value_text": "47.1",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-20",
     "source_row_id": "2025-04-20-19-54-31--flash25-diff-no-think",
     "source_model_name": "gemini-2.5-flash-preview-04-17 (default)",
     "p": 0.47100000000000003,
     "p_star": 0.47112831858407084,
     "y": -0.11561533870288959,
     "v": 0.01767974989440033,
     "family_factor": 1.0,
     "w": 1.4321007854059227
    }
   ]
  },
  {
   "slug": "qwen3-5-9b",
   "name": "Qwen3.5-9B",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.05952251012071892,
   "se": 0.24643481195660116,
   "si_iq": 100.89283765181078,
   "si_iq_low": 94.81259835901983,
   "si_iq_high": 106.97307694460173,
   "si_iq_display": 101,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6166666666666667,
     "source_value_text": "0.6166666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "YBMTDnW5LmCN6tBp2QYHzi",
     "source_model_name": "qwen3.5-9B_none",
     "p": 0.6162829496162829,
     "p_star": 0.6137550594072333,
     "y": 0.46312419317091563,
     "v": 0.08985592001015927,
     "family_factor": 1.0,
     "w": 2.6335760295135637
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7897727272727273,
     "source_value_text": "0.7897727272727273",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "o6migB5WP27uLr9nUWpCiM",
     "source_model_name": "qwen3.5-9B",
     "p": 0.7196969696969697,
     "p_star": 0.7185929648241206,
     "y": 0.9374929395247581,
     "v": 0.036194574656113115,
     "family_factor": 0.5,
     "w": 2.1195788108572478
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7462993119730186,
     "source_value_text": "0.7462993119730186",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.5-9b-20260310",
     "source_model_name": "qwen/qwen3.5-9b-20260310",
     "p": 0.6617324159640248,
     "p_star": 0.6609196902556629,
     "y": 0.6673953539020316,
     "v": 0.03356263155197355,
     "family_factor": 0.5,
     "w": 1.5337762937007715
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.650067849593496,
     "source_value_text": "0.650067849593496",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "qwen/qwen3.5-9b-20260310",
     "source_model_name": "qwen/qwen3.5-9b-20260310",
     "p": 0.650067849593496,
     "p_star": 0.6471253427387216,
     "y": 0.6064270895568502,
     "v": 0.08418229759234107,
     "family_factor": 1.0,
     "w": 3.8391679897034328
    }
   ]
  },
  {
   "slug": "grok-3-mini",
   "name": "Grok-3 mini",
   "tier": "insufficient",
   "rank": null,
   "theta": 0.000997960578141549,
   "se": 0.1840098581281695,
   "si_iq": 100.01496940867213,
   "si_iq_low": 95.47492914094884,
   "si_iq_high": 104.5550096763954,
   "si_iq_display": 100,
   "domains": {
    "math": {
     "si_iq": 100.15950060810911,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.9093655589123867,
     "source_value_text": "0.9093655589123867",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-10",
     "source_row_id": "5QyCm49Lce2PpGVcZLomCz",
     "source_model_name": "grok-3-mini-beta_low",
     "p": 0.9093655589123867,
     "p_star": 0.9090566037735849,
     "y": 2.302170069124216,
     "v": 0.00912208540242417,
     "family_factor": 1.0,
     "w": 4.5820238694676965
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7777777777777778,
     "source_value_text": "0.7777777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-10",
     "source_row_id": "fPtize44vDPcDAzMFuAurw",
     "source_model_name": "grok-3-mini-beta_high",
     "p": 0.7775553331108886,
     "p_star": 0.7715215215215214,
     "y": 1.2169225472911813,
     "v": 0.12079991035982915,
     "family_factor": 1.0,
     "w": 2.2644936729601435
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.493,
     "source_value_text": "49.3",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-10",
     "source_row_id": "2025-04-10-23-59-02--xai-grok3-mini-whole-high",
     "source_model_name": "Grok 3 Mini Beta (high)",
     "p": 0.493,
     "p_star": 0.4930309734513274,
     "y": -0.02787791156256831,
     "v": 0.01762422422203859,
     "family_factor": 1.0,
     "w": 1.432261851761302
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7626262626262627,
     "source_value_text": "0.7626262626262627",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-10",
     "source_row_id": "McxfQdC5aypnD3STwZUBjH",
     "source_model_name": "grok-3-mini-beta_low",
     "p": 0.6835016835016835,
     "p_star": 0.6825795644891123,
     "y": 0.7656519081584366,
     "v": 0.03434583383277137,
     "family_factor": 1.0,
     "w": 4.297492915993879
    }
   ]
  },
  {
   "slug": "deepseek-v3-1",
   "name": "DeepSeek-V3.1",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.017231647368514586,
   "se": 0.5260277392180327,
   "si_iq": 99.74152528947228,
   "si_iq_low": 86.76294282501621,
   "si_iq_high": 112.72010775392835,
   "si_iq_display": 100,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7707982259154932,
     "source_value_text": "0.7707982259154932",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-10-17",
     "source_row_id": "deepseek/deepseek-chat-v3.1",
     "source_model_name": "deepseek/deepseek-chat-v3.1",
     "p": 0.694397634553991,
     "p_star": 0.6934207620185439,
     "y": 0.8161607279532848,
     "v": 0.03482483432169321,
     "family_factor": 1.0,
     "w": 3.0471177582529774
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.47222181249999995,
     "source_value_text": "0.472222",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-15",
     "source_row_id": "deepseek/deepseek-chat-v3.1",
     "source_model_name": "deepseek/deepseek-chat-v3.1",
     "p": 0.47222181249999995,
     "p_star": 0.47276648284313716,
     "y": -0.10904198415084115,
     "v": 0.07712229796793643,
     "family_factor": 1.0,
     "w": 3.9921951628842995
    }
   ]
  },
  {
   "slug": "qwen3-30b-a3b-thinking-jul-2025",
   "name": "Qwen3-30B-A3B-Thinking (Jul 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.019247504409591373,
   "se": 0.26863929905366773,
   "si_iq": 99.71128743385613,
   "si_iq_low": 93.0832010497718,
   "si_iq_high": 106.33937381794046,
   "si_iq_display": 100,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.7027777777777777,
     "source_value_text": "0.7027777777777777",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "6rZFxNR3GjfhWey6DzEiYz",
     "source_model_name": "qwen3-30b-a3b-thinking-2507",
     "p": 0.7024802580358135,
     "p_star": 0.6980785132959045,
     "y": 0.8381645738947885,
     "v": 0.10104640418974867,
     "family_factor": 1.0,
     "w": 2.486988026545838
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7007575757575758,
     "source_value_text": "0.7007575757575758",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "2gzNF2d53h2oCKDnojLtSP",
     "source_model_name": "qwen3-30b-a3b-thinking-2507",
     "p": 0.6010101010101011,
     "p_star": 0.6005025125628142,
     "y": 0.4075593497112795,
     "v": 0.032410510227709265,
     "family_factor": 1.0,
     "w": 4.360305448538367
    }
   ]
  },
  {
   "slug": "seed-oss-36b-instruct",
   "name": "seed-oss-36b-instruct",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.04066108438780608,
   "se": 0.2666217943438573,
   "si_iq": 99.39008373418291,
   "si_iq_low": 92.81177486047784,
   "si_iq_high": 105.96839260788798,
   "si_iq_display": 99,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.675,
     "source_value_text": "0.675",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "eJvV6RezECZwh3b4ekg4pm",
     "source_model_name": "seed-oss-36b-instruct",
     "p": 0.6746746746746747,
     "p_star": 0.6708773991382687,
     "y": 0.7121560782777935,
     "v": 0.09645916557446411,
     "family_factor": 1.0,
     "w": 2.5450581475186222
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7152777777777778,
     "source_value_text": "0.7152777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "BVat526nF6NUGoVaLCp7DT",
     "source_model_name": "seed-oss-36b-instruct",
     "p": 0.6203703703703703,
     "p_star": 0.6197654941373534,
     "y": 0.4885529881568672,
     "v": 0.03262801556169814,
     "family_factor": 1.0,
     "w": 4.353154699212432
    }
   ]
  },
  {
   "slug": "deepseek-r1",
   "name": "DeepSeek-R1",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.1469702853287647,
   "se": 0.17999820170874437,
   "si_iq": 97.79544572006853,
   "si_iq_low": 93.354384288967,
   "si_iq_high": 102.23650715117006,
   "si_iq_display": 98,
   "domains": {
    "math": {
     "si_iq": 97.69874238916532,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.9305135951661632,
     "source_value_text": "0.9305135951661632",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-31",
     "source_row_id": "XVqLs2khGFSNwEbHJTEgRU",
     "source_model_name": "DeepSeek-R1",
     "p": 0.9305135951661632,
     "p_star": 0.930188679245283,
     "y": 2.589591261398466,
     "v": 0.011613398388246264,
     "family_factor": 1.0,
     "w": 4.479748912050453
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5333333333333333,
     "source_value_text": "0.5333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-26",
     "source_row_id": "bBY5VZzpDkmTBdSSvu5Ups",
     "source_model_name": "DeepSeek-R1",
     "p": 0.5328661995328662,
     "p_star": 0.5321517169343256,
     "y": 0.1287845690164385,
     "v": 0.08558004342516144,
     "family_factor": 1.0,
     "w": 2.694255216087576
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.569,
     "source_value_text": "56.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-01-20",
     "source_row_id": "2025-01-20-19-11-38--ds-turns-upd-cur-msgs-fix-with-summarizer",
     "source_model_name": "DeepSeek R1",
     "p": 0.569,
     "p_star": 0.5686946902654866,
     "y": 0.2765275030729067,
     "v": 0.01795980685025946,
     "family_factor": 1.0,
     "w": 1.431288960695597
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7171717171717171,
     "source_value_text": "0.7171717171717171",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-26",
     "source_row_id": "fFGyQR2mfDufvrSV2rzWyV",
     "source_model_name": "DeepSeek-R1",
     "p": 0.6228956228956228,
     "p_star": 0.6222780569514237,
     "y": 0.4992287052150804,
     "v": 0.03266624131853972,
     "family_factor": 1.0,
     "w": 4.351900403987272
    }
   ]
  },
  {
   "slug": "qwen3-235b-a22b-instruct-jul-2025",
   "name": "Qwen3-235B-A22B-Instruct (Jul 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.27548595371933443,
   "se": 0.4409547326914388,
   "si_iq": 95.86771069420999,
   "si_iq_low": 84.98811835591333,
   "si_iq_high": 106.74730303250664,
   "si_iq_display": 96,
   "domains": {
    "agentic": {
     "si_iq": 92.4316493221294,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7388167142857143,
     "source_value_text": "0.738817",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3-235b-a22b-07-25",
     "source_model_name": "qwen/qwen3-235b-a22b-07-25",
     "p": 0.651755619047619,
     "p_star": 0.6509930279971285,
     "y": 0.6234070333809106,
     "v": 0.03327448756777659,
     "family_factor": 1.0,
     "w": 3.0722560707619904
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.5215,
     "source_value_text": "52.15%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "23",
     "source_model_name": "Qwen3-235B-A22B-Instruct-2507 (Prompt)",
     "p": 0.5215,
     "p_star": 0.5212871287128713,
     "y": 0.08520001668068128,
     "v": 0.0392830451430934,
     "family_factor": 1.0,
     "w": 5.076761356417045
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.3961905714285714,
     "source_value_text": "0.396191",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3-235b-a22b-07-25",
     "source_model_name": "qwen/qwen3-235b-a22b-07-25",
     "p": 0.3961905714285714,
     "p_star": 0.398226050420168,
     "y": -0.4128620658218975,
     "v": 0.08021703439335438,
     "family_factor": 1.0,
     "w": 3.923640090776138
    }
   ]
  },
  {
   "slug": "grok-3",
   "name": "Grok 3",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.2793299425713606,
   "se": 0.17866249149639157,
   "si_iq": 95.81005086142959,
   "si_iq_low": 91.4019451546125,
   "si_iq_high": 100.21815656824667,
   "si_iq_display": 96,
   "domains": {
    "math": {
     "si_iq": 94.5059905451847,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8874622356495468,
     "source_value_text": "0.8874622356495468",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-10",
     "source_row_id": "i9eqMbaVTDDuCxWxzGHxyU",
     "source_model_name": "grok-3-beta",
     "p": 0.8874622356495468,
     "p_star": 0.8871698113207547,
     "y": 2.0621524751493827,
     "v": 0.0075339747264737515,
     "family_factor": 1.0,
     "w": 4.6496932831862035
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5555555555555556,
     "source_value_text": "0.5555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-10",
     "source_row_id": "DKTzh9kSoipZGkDsC4NGf3",
     "source_model_name": "grok-3-beta",
     "p": 0.5551106662217774,
     "p_star": 0.5539126082604344,
     "y": 0.21649204905198607,
     "v": 0.08622233432330387,
     "family_factor": 1.0,
     "w": 2.68496258419756
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.5329999999999999,
     "source_value_text": "53.3",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-10",
     "source_row_id": "2025-04-10-04-21-31--grok3-diff-exuser",
     "source_model_name": "Grok 3 Beta",
     "p": 0.5329999999999999,
     "p_star": 0.5328539823008849,
     "y": 0.13160555169627694,
     "v": 0.01769720872250192,
     "family_factor": 1.0,
     "w": 1.4320501491138122
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7575757575757576,
     "source_value_text": "0.7575757575757576",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-26",
     "source_row_id": "FQ8Ykq4JWRSXnyF9rbmLc7",
     "source_model_name": "grok-3-beta",
     "p": 0.6767676767676768,
     "p_star": 0.6758793969849246,
     "y": 0.7348989752401669,
     "v": 0.03407977379566213,
     "family_factor": 1.0,
     "w": 4.306020608816874
    }
   ]
  },
  {
   "slug": "qwen3-5-4b",
   "name": "Qwen3.5-4B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.29573004109097345,
   "se": 0.3092464354019495,
   "si_iq": 95.56404938363539,
   "si_iq_low": 87.93407083978582,
   "si_iq_high": 103.19402792748497,
   "si_iq_display": 96,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5583333333333333,
     "source_value_text": "0.5583333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "SAZy8rk2HgyPjA8XZJFUmR",
     "source_model_name": "qwen3.5-4b_none",
     "p": 0.5578912245578912,
     "p_star": 0.5566327196761979,
     "y": 0.22750713049042331,
     "v": 0.08632662779806248,
     "family_factor": 1.0,
     "w": 2.6834597175337236
    }
   ]
  },
  {
   "slug": "mistral-small-4",
   "name": "Mistral Small 4",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.2993744598720248,
   "se": 0.5259049047036636,
   "si_iq": 95.50938310191962,
   "si_iq_low": 82.53383131009804,
   "si_iq_high": 108.48493489374123,
   "si_iq_display": 96,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.7528056666666667,
     "source_value_text": "0.752806",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-09-17",
     "source_row_id": "mistralai/mistral-small-2603",
     "source_model_name": "mistralai/mistral-small-2603",
     "p": 0.6704075555555556,
     "p_star": 0.6695512361809046,
     "y": 0.7061560702180875,
     "v": 0.03384840609121692,
     "family_factor": 1.0,
     "w": 3.062901984305521
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.41142871428571426,
     "source_value_text": "0.411429",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-09-17",
     "source_row_id": "mistralai/mistral-small-2603",
     "source_model_name": "mistralai/mistral-small-2603",
     "p": 0.41142871428571426,
     "p_star": 0.41316540616246494,
     "y": -0.35089498593581164,
     "v": 0.07928481062148897,
     "family_factor": 1.0,
     "w": 3.944041766479653
    }
   ]
  },
  {
   "slug": "gpt-oss-20b",
   "name": "gpt-oss-20b",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.3299745508842534,
   "se": 0.2471753236897023,
   "si_iq": 95.0503817367362,
   "si_iq_low": 88.95187193865168,
   "si_iq_high": 101.14889153482072,
   "si_iq_display": 95,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6527777777777778,
     "source_value_text": "0.6527777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "DB8ja6pEZWGocQbdciyisL",
     "source_model_name": "gpt-oss-20b_medium",
     "p": 0.6524302079857636,
     "p_star": 0.64911650781216,
     "y": 0.615157982287685,
     "v": 0.09351482563590983,
     "family_factor": 1.0,
     "w": 2.583781363298383
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6079545454545454,
     "source_value_text": "0.6079545454545454",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "GEwyLqZT93Hp55fdtHrJhm",
     "source_model_name": "gpt-oss-20b_medium",
     "p": 0.47727272727272724,
     "p_star": 0.47738693467336685,
     "y": -0.09051400754083186,
     "v": 0.03403366716386106,
     "family_factor": 0.5,
     "w": 2.1537509246978748
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.6311448,
     "source_value_text": "0.6311448",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:52:14Z",
     "eval_date": "2026-10-17",
     "source_row_id": "openai/gpt-oss-20b",
     "source_model_name": "openai/gpt-oss-20b",
     "p": 0.5081930666666666,
     "p_star": 0.5081518954773869,
     "y": 0.03261047154999797,
     "v": 0.03312740616543049,
     "family_factor": 0.5,
     "w": 1.537331250432092
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.4672696511627907,
     "source_value_text": "0.46727",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-17",
     "source_row_id": "openai/gpt-oss-20b",
     "source_model_name": "openai/gpt-oss-20b",
     "p": 0.4672696511627907,
     "p_star": 0.4679114227086183,
     "y": -0.12853096386266571,
     "v": 0.07721151411586064,
     "family_factor": 1.0,
     "w": 3.9901853145063817
    }
   ]
  },
  {
   "slug": "glm-4-7-flash",
   "name": "glm-4.7-flash",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.38081227632898956,
   "se": 0.24621281578420529,
   "si_iq": 94.28781585506516,
   "si_iq_low": 88.21305383165645,
   "si_iq_high": 100.36257787847386,
   "si_iq_display": 94,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5833333333333334,
     "source_value_text": "0.5833333333333334",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "9ekki5tJhyjmA7ZMLoUxzo",
     "source_model_name": "glm-4.7-flash",
     "p": 0.5829162495829163,
     "p_star": 0.5811137224180704,
     "y": 0.3273470041604021,
     "v": 0.08751591525121295,
     "family_factor": 1.0,
     "w": 2.666440335638474
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6054292929292929,
     "source_value_text": "0.6054292929292929",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "GL7htq7XRnbzqpAVK5f862",
     "source_model_name": "glm-4.7-flash",
     "p": 0.4739057239057239,
     "p_star": 0.474036850921273,
     "y": -0.10394608826501583,
     "v": 0.034154837138587774,
     "family_factor": 0.5,
     "w": 2.1518056355776345
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.49197393750000007,
     "source_value_text": "0.49197393750000007",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-30",
     "source_row_id": "z-ai/glm-4.7-flash-20260119",
     "source_model_name": "z-ai/glm-4.7-flash-20260119",
     "p": 0.32263191666666674,
     "p_star": 0.32352321356783925,
     "y": -0.7376272638872534,
     "v": 0.04638374138002472,
     "family_factor": 0.5,
     "w": 1.4359580170725672
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.6833333333333333,
     "source_value_text": "0.6833333333333333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-30",
     "source_row_id": "z-ai/glm-4.7-flash-20260119",
     "source_model_name": "z-ai/glm-4.7-flash-20260119",
     "p": 0.6833333333333333,
     "p_star": 0.6797385620915032,
     "y": 0.7525706010307457,
     "v": 0.08830455259026686,
     "family_factor": 1.0,
     "w": 3.7551231314366884
    }
   ]
  },
  {
   "slug": "qwen3-30b-a3b",
   "name": "Qwen3-30B-A3B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.4233223480829931,
   "se": 0.24621863066154173,
   "si_iq": 93.6501647787551,
   "si_iq_low": 87.57525928598271,
   "si_iq_high": 99.7250702715275,
   "si_iq_display": 94,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6277777777777778,
     "source_value_text": "0.6277777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "XfjRkSyP4ub4gDsWcgS7KY",
     "source_model_name": "Qwen3-30B-A3B",
     "p": 0.6274051829607385,
     "p_star": 0.6246355050702878,
     "y": 0.5092707473496673,
     "v": 0.0908473803135308,
     "family_factor": 1.0,
     "w": 2.6198944894008096
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6167929292929293,
     "source_value_text": "0.6167929292929293",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "BnX67AoZzgVbHgaM8F8Brz",
     "source_model_name": "Qwen3-30B-A3B",
     "p": 0.489057239057239,
     "p_star": 0.48911222780569513,
     "y": -0.043557974339129786,
     "v": 0.03364524147181061,
     "family_factor": 0.5,
     "w": 2.1600105728844996
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.604377,
     "source_value_text": "0.604377",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "qwen/qwen3-30b-a3b-04-28",
     "source_model_name": "qwen/qwen3-30b-a3b-04-28",
     "p": 0.47250266666666674,
     "p_star": 0.4726408442211056,
     "y": -0.10954604091222946,
     "v": 0.03420669978158327,
     "family_factor": 0.5,
     "w": 1.528545556418639
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.423333,
     "source_value_text": "0.423333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "qwen/qwen3-30b-a3b-04-28",
     "source_model_name": "qwen/qwen3-30b-a3b-04-28",
     "p": 0.423333,
     "p_star": 0.42483627450980394,
     "y": -0.3029508819952911,
     "v": 0.07867134448815434,
     "family_factor": 1.0,
     "w": 3.9575835913264066
    }
   ]
  },
  {
   "slug": "cohere-command-a",
   "name": "Cohere Command A",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.4340984960380447,
   "se": 0.7344366418393885,
   "si_iq": 93.48852255942933,
   "si_iq_low": 75.36790683828805,
   "si_iq_high": 111.60913828057062,
   "si_iq_display": 93,
   "domains": {},
   "inputs": [
    {
     "benchmark": "bfcl_overall",
     "score": 0.46490000000000004,
     "source_value_text": "46.49%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "35",
     "source_model_name": "Command A (FC)",
     "p": 0.46490000000000004,
     "p_star": 0.46524752475247527,
     "y": -0.13923440149007543,
     "v": 0.039402191526251365,
     "family_factor": 1.0,
     "w": 5.072422272883633
    }
   ]
  },
  {
   "slug": "deepseek-r1-distill-qwen-32b",
   "name": "DeepSeek-R1-Distill-Qwen-32B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.45086641286226303,
   "se": 0.26185287142914077,
   "si_iq": 93.23700380706606,
   "si_iq_low": 86.77635766234043,
   "si_iq_high": 99.69764995179167,
   "si_iq_display": 93,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5555555555555556,
     "source_value_text": "0.5555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "KbUNQf8nnwPa8ixg6AnEwB",
     "source_model_name": "DeepSeek-R1-Distill-Qwen-32B",
     "p": 0.5551106662217774,
     "p_star": 0.5539126082604344,
     "y": 0.21649204905198607,
     "v": 0.08622233432330387,
     "family_factor": 1.0,
     "w": 2.68496258419756
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6414141414141414,
     "source_value_text": "0.6414141414141414",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "dwyb2yzFewGT6w6oFdVMAc",
     "source_model_name": "DeepSeek-R1-Distill-Qwen-32B",
     "p": 0.521885521885522,
     "p_star": 0.5217755443886097,
     "y": 0.08715730913144296,
     "v": 0.03283834275421609,
     "family_factor": 1.0,
     "w": 4.346262210285679
    }
   ]
  },
  {
   "slug": "qwen3-14b",
   "name": "Qwen3-14B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.4615350596679188,
   "se": 0.239576996855949,
   "si_iq": 93.07697410498122,
   "si_iq_low": 87.1659363811838,
   "si_iq_high": 98.98801182877864,
   "si_iq_display": 93,
   "domains": {
    "agentic": {
     "si_iq": 86.24845972974364,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6638888888888889,
     "source_value_text": "0.6638888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "gRRQHECkYhz5UaYsRKDh2F",
     "source_model_name": "qwen3-14b",
     "p": 0.6635524413302191,
     "p_star": 0.6599969534752143,
     "y": 0.6632806411260924,
     "v": 0.09491400422251765,
     "family_factor": 1.0,
     "w": 2.5652338424549024
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6376262626262627,
     "source_value_text": "0.6376262626262627",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "XGK9DjJHHVWr2LyT298ooL",
     "source_model_name": "qwen3-14b",
     "p": 0.5168350168350169,
     "p_star": 0.516750418760469,
     "y": 0.06702675739728833,
     "v": 0.03293726940498149,
     "family_factor": 0.5,
     "w": 2.171513947043624
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.5331086666666667,
     "source_value_text": "0.533109",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-01",
     "source_row_id": "qwen/qwen3-14b-04-28",
     "source_model_name": "qwen/qwen3-14b-04-28",
     "p": 0.3774782222222222,
     "p_star": 0.37809390954773864,
     "y": -0.49764649863929816,
     "v": 0.04000970560934389,
     "family_factor": 0.5,
     "w": 1.4829778997365424
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.4103,
     "source_value_text": "41.03%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "43",
     "source_model_name": "Qwen3-14B (FC)",
     "p": 0.4103,
     "p_star": 0.4111881188118812,
     "y": -0.35905592607584,
     "v": 0.040489287121722256,
     "family_factor": 1.0,
     "w": 5.03317224874163
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.413333,
     "source_value_text": "0.413333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "qwen/qwen3-14b-04-28",
     "source_model_name": "qwen/qwen3-14b-04-28",
     "p": 0.413333,
     "p_star": 0.41503235294117646,
     "y": -0.34320006544311044,
     "v": 0.07918006474011914,
     "family_factor": 1.0,
     "w": 3.9463473920055088
    }
   ]
  },
  {
   "slug": "deepseek-r1-distill-llama-70b",
   "name": "DeepSeek-R1-Distill-Llama-70B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.5202061805967433,
   "se": 0.1849733266737964,
   "si_iq": 92.19690729104884,
   "si_iq_low": 87.63309554695834,
   "si_iq_high": 96.76071903513936,
   "si_iq_display": 92,
   "domains": {
    "math": {
     "si_iq": 94.35229101408717,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8989803625377644,
     "source_value_text": "0.8989803625377644",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-10",
     "source_row_id": "oPDoTJFMhMNvU4sybYu2jQ",
     "source_model_name": "DeepSeek-R1-Distill-Llama-70B",
     "p": 0.8989803625377644,
     "p_star": 0.8986792452830189,
     "y": 2.1826349062919963,
     "v": 0.008282340871655388,
     "family_factor": 1.0,
     "w": 4.617558098348083
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5138888888888888,
     "source_value_text": "0.5138888888888888",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-07",
     "source_row_id": "89zcekqEYnE8zhwG4pR5Nu",
     "source_model_name": "DeepSeek-R1-Distill-Llama-70B",
     "p": 0.5134022911800689,
     "p_star": 0.5131109370239804,
     "y": 0.05245577293137001,
     "v": 0.08529075843966384,
     "family_factor": 1.0,
     "w": 2.6984616189739152
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5574494949494949,
     "source_value_text": "0.5574494949494949",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-10",
     "source_row_id": "f6pnAATjxmrFJS353EjQKi",
     "source_model_name": "DeepSeek-R1-Distill-Llama-70B",
     "p": 0.40993265993265987,
     "p_star": 0.41038525963149075,
     "y": -0.36237296505337024,
     "v": 0.03744689712619742,
     "family_factor": 1.0,
     "w": 4.200533306034034
    }
   ]
  },
  {
   "slug": "qwq-32b",
   "name": "QwQ-32B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.55533170097359,
   "se": 0.24637611510599702,
   "si_iq": 91.67002448539616,
   "si_iq_low": 85.59123340884776,
   "si_iq_high": 97.74881556194454,
   "si_iq_display": 92,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5916666666666667,
     "source_value_text": "0.5916666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "2xMn6dbY9mw4pmkh8Tz9Gn",
     "source_model_name": "QwQ-32B",
     "p": 0.5912579245912579,
     "p_star": 0.589274056665361,
     "y": 0.36096517934469025,
     "v": 0.08801658301809122,
     "family_factor": 1.0,
     "w": 2.659339894246931
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.209,
     "source_value_text": "20.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-03-06",
     "source_row_id": "2025-03-06-17-40-24--qwq32b-diff-temp-topp-ex-sys-remind-user-for-real",
     "source_model_name": "QwQ-32B",
     "p": 0.209,
     "p_star": 0.21028761061946902,
     "y": -1.3231926470140314,
     "v": 0.02652668632539741,
     "family_factor": 1.0,
     "w": 1.4068925516240907
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6534090909090909,
     "source_value_text": "0.6534090909090909",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "PUXMxQiRY6XaG6NjwsEDLy",
     "source_model_name": "QwQ-32B",
     "p": 0.537878787878788,
     "p_star": 0.5376884422110554,
     "y": 0.1510402574128663,
     "v": 0.032583062124278944,
     "family_factor": 1.0,
     "w": 4.35463067407839
    }
   ]
  },
  {
   "slug": "o1-mini",
   "name": "o1-mini",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.5600101639701154,
   "se": 0.17862755078274287,
   "si_iq": 91.59984754044827,
   "si_iq_low": 87.1926039192203,
   "si_iq_high": 96.00709116167623,
   "si_iq_display": 92,
   "domains": {
    "math": {
     "si_iq": 93.09414562195772,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8918051359516617,
     "source_value_text": "0.8918051359516617",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-13",
     "source_row_id": "4DWnpJowAfeQDHc2xDNy2C",
     "source_model_name": "o1-mini-2024-09-12_high",
     "p": 0.8918051359516617,
     "p_star": 0.8915094339622641,
     "y": 2.1062527991304925,
     "v": 0.007797193466758683,
     "family_factor": 1.0,
     "w": 4.638339681396107
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.46944444444444444,
     "source_value_text": "0.46944444444444444",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-06",
     "source_row_id": "9zhPZLvNeUPQ7JBSpTwKPp",
     "source_model_name": "o1-mini-2024-09-12_high",
     "p": 0.4689133578022467,
     "p_star": 0.4695891543717631,
     "y": -0.12179371389292082,
     "v": 0.08556401919290424,
     "family_factor": 1.0,
     "w": 2.694487876338903
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.32899999999999996,
     "source_value_text": "32.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2024-12-22",
     "source_row_id": "2024-12-22-21-26-35--polyglot-o1mini-whole",
     "source_model_name": "o1-mini-2024-09-12",
     "p": 0.32899999999999996,
     "p_star": 0.3297566371681416,
     "y": -0.7092859552669177,
     "v": 0.019931481104485307,
     "family_factor": 1.0,
     "w": 1.4255994488781598
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6237373737373737,
     "source_value_text": "0.6237373737373737",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-13",
     "source_row_id": "X2gKewiGPZx5DLFEddUUqW",
     "source_model_name": "o1-mini-2024-09-12_high",
     "p": 0.49831649831649827,
     "p_star": 0.49832495812395305,
     "y": -0.006700192569819786,
     "v": 0.03337768299895821,
     "family_factor": 1.0,
     "w": 4.328687200197767
    }
   ]
  },
  {
   "slug": "qwen3-30b-a3b-instruct-jul-2025",
   "name": "Qwen3-30B-A3B-Instruct (Jul 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.5666840671290503,
   "se": 0.23837468865043704,
   "si_iq": 91.49973899306424,
   "si_iq_low": 85.61836559118285,
   "si_iq_high": 97.38111239494563,
   "si_iq_display": 91,
   "domains": {
    "agentic": {
     "si_iq": 84.34670002029918,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.6222222222222222,
     "source_value_text": "0.6222222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "Eo5cAQJK28CHpKDfCSDYG4",
     "source_model_name": "qwen3-30b-a3b-instruct-2507",
     "p": 0.6218440662885107,
     "p_star": 0.6191952822387605,
     "y": 0.48613401120369154,
     "v": 0.09033757161697789,
     "family_factor": 1.0,
     "w": 2.6269117324148974
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5561868686868687,
     "source_value_text": "0.5561868686868687",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "X3HfncZtnLKUPoUuRc9YsR",
     "source_model_name": "qwen3-30b-a3b-instruct-2507",
     "p": 0.4082491582491583,
     "p_star": 0.4087102177554439,
     "y": -0.3692998316400948,
     "v": 0.0375627230183485,
     "family_factor": 0.5,
     "w": 2.0984982578187887
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.6419754999999999,
     "source_value_text": "0.641975",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3-30b-a3b-instruct-2507",
     "source_model_name": "qwen/qwen3-30b-a3b-instruct-2507",
     "p": 0.5226339999999999,
     "p_star": 0.5225202613065326,
     "y": 0.09014203374233751,
     "v": 0.03282443793702117,
     "family_factor": 0.5,
     "w": 1.5398156640390115
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.4139,
     "source_value_text": "41.39%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "41",
     "source_model_name": "Qwen3-30B-A3B-Instruct-2507 (FC)",
     "p": 0.4139,
     "p_star": 0.41475247524752473,
     "y": -0.3443529798773348,
     "v": 0.04038579907685333,
     "family_factor": 1.0,
     "w": 5.036882546784139
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.3695237142857143,
     "source_value_text": "0.369524",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3-30b-a3b-instruct-2507",
     "source_model_name": "qwen/qwen3-30b-a3b-instruct-2507",
     "p": 0.3695237142857143,
     "p_star": 0.3720820728291317,
     "y": -0.5232950128856585,
     "v": 0.08227881415695598,
     "family_factor": 1.0,
     "w": 3.879259279016784
    }
   ]
  },
  {
   "slug": "qwen3-8b",
   "name": "Qwen3-8B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.6301976893595185,
   "se": 0.2512604552187285,
   "si_iq": 90.54703465960722,
   "si_iq_low": 84.34773318748202,
   "si_iq_high": 96.74633613173242,
   "si_iq_display": 91,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5611111111111111,
     "source_value_text": "0.5611111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "gG2B6fLUDBy5jRraxL2pz8",
     "source_model_name": "qwen3-8b",
     "p": 0.5606717828940051,
     "p_star": 0.5593528310919615,
     "y": 0.23853597196001297,
     "v": 0.08643637229776235,
     "family_factor": 1.0,
     "w": 2.68188011726294
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5675505050505051,
     "source_value_text": "0.5675505050505051",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "jRiWmBxtBAyiXiRBRMY8wX",
     "source_model_name": "qwen3-8b",
     "p": 0.42340067340067344,
     "p_star": 0.42378559463986604,
     "y": -0.30725216864587784,
     "v": 0.03658024834443703,
     "family_factor": 1.0,
     "w": 4.227187138608988
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.4257,
     "source_value_text": "42.57%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "39",
     "source_model_name": "Qwen3-8B (FC)",
     "p": 0.4257,
     "p_star": 0.4264356435643564,
     "y": -0.2964086860425137,
     "v": 0.040079435838654774,
     "family_factor": 1.0,
     "w": 5.04789855094078
    }
   ]
  },
  {
   "slug": "deepseek-r1-0528-qwen3-8b",
   "name": "deepseek-r1-0528-qwen3-8b",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.6343945036024091,
   "se": 0.3093702586574433,
   "si_iq": 90.48408244596386,
   "si_iq_low": 82.85104883445791,
   "si_iq_high": 98.11711605746981,
   "si_iq_display": 90,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.4388888888888889,
     "source_value_text": "0.4388888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "LWbCXNGMXtjQYxyM2uoFMV",
     "source_model_name": "deepseek-r1-0528-qwen3-8b",
     "p": 0.43832721610499387,
     "p_star": 0.4396679287983635,
     "y": -0.2425098575711678,
     "v": 0.08651954476860622,
     "family_factor": 1.0,
     "w": 2.680684217947742
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.0928030303030303,
     "source_value_text": "0.0928030303030303",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "dszRh7ELyCEukWnwYnUxMp",
     "source_model_name": "deepseek-r1-0528-qwen3-8b",
     "p": 0.0,
     "p_star": 0.002512562814070352,
     "y": -5.983936280687191,
     "v": 266.65994962216627,
     "family_factor": 1.0,
     "w": 0.0021643064110912218
    }
   ]
  },
  {
   "slug": "qwq-plus",
   "name": "QWQ-Plus",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.6457976350262365,
   "se": 0.46801879093097953,
   "si_iq": 90.31303547460645,
   "si_iq_low": 78.76569676953667,
   "si_iq_high": 101.86037417967623,
   "si_iq_display": 90,
   "domains": {},
   "inputs": [
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6540404040404041,
     "source_value_text": "0.6540404040404041",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-11",
     "source_row_id": "PtxHF8BH8WuNdNfDnutGBb",
     "source_model_name": "qwq-plus",
     "p": 0.5387205387205388,
     "p_star": 0.5385259631490789,
     "y": 0.15440991508470545,
     "v": 0.0325720337288027,
     "family_factor": 1.0,
     "w": 4.3549929268693885
    }
   ]
  },
  {
   "slug": "deepseek-r1-distill-qwen-14b",
   "name": "DeepSeek-R1-Distill-Qwen-14B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.7428254421862869,
   "se": 0.18594681639472777,
   "si_iq": 88.8576183672057,
   "si_iq_low": 84.26978789619369,
   "si_iq_high": 93.4454488382177,
   "si_iq_display": 89,
   "domains": {
    "math": {
     "si_iq": 92.1866032234687,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8712235649546828,
     "source_value_text": "0.8712235649546828",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-11",
     "source_row_id": "R8XGt5ScHpmTbD5DnXR59V",
     "source_model_name": "DeepSeek-R1-Distill-Qwen-14B",
     "p": 0.8712235649546828,
     "p_star": 0.8709433962264151,
     "y": 1.9093258905653854,
     "v": 0.0067094367924432725,
     "family_factor": 1.0,
     "w": 4.68562120679666
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5055555555555555,
     "source_value_text": "0.5055555555555555",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "EceR3NeHzSxacdmAmfRxgT",
     "source_model_name": "DeepSeek-R1-Distill-Qwen-14B",
     "p": 0.5050606161717273,
     "p_star": 0.5049506027766897,
     "y": 0.019803058247165616,
     "v": 0.08524315224530174,
     "family_factor": 1.0,
     "w": 2.6991551047344116
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.44696969696969696,
     "source_value_text": "0.44696969696969696",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-10",
     "source_row_id": "8UqaLobhmNJLuPGTTpeaCw",
     "source_model_name": "DeepSeek-R1-Distill-Qwen-14B",
     "p": 0.2626262626262626,
     "p_star": 0.2638190954773869,
     "y": -1.0262122588595441,
     "v": 0.05827029788024425,
     "family_factor": 1.0,
     "w": 3.6478750398667965
    }
   ]
  },
  {
   "slug": "gemini-2-0-pro",
   "name": "Gemini 2.0 Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.7464340193142813,
   "se": 0.21497265903783883,
   "si_iq": 88.80348971028577,
   "si_iq_low": 83.49951013865041,
   "si_iq_high": 94.10746928192115,
   "si_iq_display": 89,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8345921450151057,
     "source_value_text": "0.8345921450151057",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-06",
     "source_row_id": "fvDt6HaHV5d3gSEuavixsv",
     "source_model_name": "gemini-2.0-pro-exp-02-05",
     "p": 0.8345921450151057,
     "p_star": 0.8343396226415094,
     "y": 1.6167007677822747,
     "v": 0.005456255685746046,
     "family_factor": 1.0,
     "w": 4.74130241727881
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.35600000000000004,
     "source_value_text": "35.6",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-02-25",
     "source_row_id": "2025-02-25-20-23-07--gemini-pro",
     "source_model_name": "Gemini 2.0 Pro exp-02-05",
     "p": 0.35600000000000004,
     "p_star": 0.35663716814159296,
     "y": -0.5899899155868362,
     "v": 0.019199197217567007,
     "family_factor": 1.0,
     "w": 1.4277072574283876
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6565656565656566,
     "source_value_text": "0.6565656565656566",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-07",
     "source_row_id": "g5YE7G6DXb45EH4HxEdiht",
     "source_model_name": "gemini-2.0-pro-exp-02-05",
     "p": 0.5420875420875421,
     "p_star": 0.5418760469011725,
     "y": 0.1678974920789193,
     "v": 0.03253030190005575,
     "family_factor": 1.0,
     "w": 4.35636424962662
    }
   ]
  },
  {
   "slug": "gemini-2-0-flash-thinking-jan-2025",
   "name": "Gemini 2.0 Flash Thinking (Jan 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.7579319826958612,
   "se": 0.24701178089070672,
   "si_iq": 88.63102025956208,
   "si_iq_low": 82.53654552188405,
   "si_iq_high": 94.72549499724012,
   "si_iq_display": 89,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5777777777777777,
     "source_value_text": "0.5777777777777777",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-07",
     "source_row_id": "cXz2gsCmGYSvQ6Ey4LDiN7",
     "source_model_name": "gemini-2.0-flash-thinking-exp-01-21",
     "p": 0.5773551329106884,
     "p_star": 0.575673499586543,
     "y": 0.3050374519432639,
     "v": 0.08721174326270069,
     "family_factor": 1.0,
     "w": 2.6707726304240764
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.182,
     "source_value_text": "18.2",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-01-21",
     "source_row_id": "2025-01-21-22-51-49--gemini-2.0-flash-thinking-exp-01-21-polyglot-diff",
     "source_model_name": "gemini-2.0-flash-thinking-exp-01-21",
     "p": 0.182,
     "p_star": 0.18340707964601768,
     "y": -1.4934325478947037,
     "v": 0.029413312269044218,
     "family_factor": 1.0,
     "w": 1.3988583968696964
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5707070707070707,
     "source_value_text": "0.5707070707070707",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-06",
     "source_row_id": "ag9w2w4xa47ghZaWt5oZey",
     "source_model_name": "gemini-2.0-flash-thinking-exp-01-21",
     "p": 0.4276094276094276,
     "p_star": 0.4279731993299833,
     "y": -0.2901252693670853,
     "v": 0.03633030721137383,
     "family_factor": 1.0,
     "w": 4.234937051043763
    }
   ]
  },
  {
   "slug": "gpt-4-5",
   "name": "GPT-4.5",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.8549238379578424,
   "se": 0.1836807133648332,
   "si_iq": 87.17614243063237,
   "si_iq_low": 82.64422308911738,
   "si_iq_high": 91.70806177214736,
   "si_iq_display": 87,
   "domains": {
    "math": {
     "si_iq": 85.94969650620484,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.7862537764350453,
     "source_value_text": "0.7862537764350453",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-28",
     "source_row_id": "japqZFi3FS7um32EHG6wwW",
     "source_model_name": "gpt-4.5-preview-2025-02-27",
     "p": 0.7862537764350453,
     "p_star": 0.7860377358490566,
     "y": 1.3012051375332196,
     "v": 0.004484103699978239,
     "family_factor": 1.0,
     "w": 4.78541694185107
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.37777777777777777,
     "source_value_text": "0.37777777777777777",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-28",
     "source_row_id": "9DCJMt7YsTMDenTdX4Db6V",
     "source_model_name": "gpt-4.5-preview-2025-02-27",
     "p": 0.3771549327104883,
     "p_star": 0.3798254776515646,
     "y": -0.49028904820170705,
     "v": 0.09051944474207214,
     "family_factor": 1.0,
     "w": 2.624404037482404
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6868686868686869,
     "source_value_text": "0.6868686868686869",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-28",
     "source_row_id": "dodibSv7pk8GtqeMy4YLQg",
     "source_model_name": "gpt-4.5-preview-2025-02-27",
     "p": 0.5824915824915825,
     "p_star": 0.5820770519262982,
     "y": 0.33130574981327376,
     "v": 0.032323449237899225,
     "family_factor": 1.0,
     "w": 4.363174271187792
    }
   ]
  },
  {
   "slug": "gemini-2-0-flash-feb-2025",
   "name": "Gemini 2.0 Flash (Feb 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.8844823105502617,
   "se": 0.18533939296019458,
   "si_iq": 86.73276534174607,
   "si_iq_low": 82.15992171372386,
   "si_iq_high": 91.30560896976829,
   "si_iq_display": 87,
   "domains": {
    "math": {
     "si_iq": 86.29821158463727,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8216578549848943,
     "source_value_text": "0.8216578549848943",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-06",
     "source_row_id": "SqwGZz2UfTmbvPiw2rq3LH",
     "source_model_name": "gemini-2.0-flash-001",
     "p": 0.8216578549848943,
     "p_star": 0.8214150943396227,
     "y": 1.525964427619293,
     "v": 0.005141014167214375,
     "family_factor": 1.0,
     "w": 4.755518138761806
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.3111111111111111,
     "source_value_text": "0.3111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "ZnGSRrKbiEnuju4kk4sgVb",
     "source_model_name": "gemini-2.0-flash-001",
     "p": 0.3104215326437549,
     "p_star": 0.31454280367323845,
     "y": -0.7789658879269081,
     "v": 0.09895019645670787,
     "family_factor": 1.0,
     "w": 2.5131917882212367
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6414141414141414,
     "source_value_text": "0.6414141414141414",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-06",
     "source_row_id": "fbszwTApm3f28z5VA6oXBK",
     "source_model_name": "gemini-2.0-flash-001",
     "p": 0.521885521885522,
     "p_star": 0.5217755443886097,
     "y": 0.08715730913144296,
     "v": 0.03283834275421609,
     "family_factor": 1.0,
     "w": 4.346262210285679
    }
   ]
  },
  {
   "slug": "mistral-medium-3",
   "name": "Mistral Medium 3",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.9614581074953251,
   "se": 0.18112493344431776,
   "si_iq": 85.57812838757012,
   "si_iq_low": 81.10926731843583,
   "si_iq_high": 90.04698945670442,
   "si_iq_display": 86,
   "domains": {
    "math": {
     "si_iq": 86.15749629692522,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8162764350453172,
     "source_value_text": "0.8162764350453172",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-07",
     "source_row_id": "LNUnvvrDra89Vhdc9bzdCy",
     "source_model_name": "mistral-medium-2505",
     "p": 0.8162764350453172,
     "p_star": 0.8160377358490566,
     "y": 1.4897299483681323,
     "v": 0.0050236253149547935,
     "family_factor": 1.0,
     "w": 4.760833560073294
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.32222222222222224,
     "source_value_text": "0.32222222222222224",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-07",
     "source_row_id": "QWw65xeTn8x42SymMsVREN",
     "source_model_name": "mistral-medium-2505",
     "p": 0.32154376598821044,
     "p_star": 0.3254232493362928,
     "y": -0.7289588174340552,
     "v": 0.09717414817999273,
     "family_factor": 1.0,
     "w": 2.535829390491745
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5953282828282829,
     "source_value_text": "0.5953282828282829",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-05-07",
     "source_row_id": "FNMbfvEEm9PRnrJnrqk2PH",
     "source_model_name": "mistral-medium-2505",
     "p": 0.4604377104377105,
     "p_star": 0.46063651591289784,
     "y": -0.15778044787783702,
     "v": 0.03468684359119141,
     "family_factor": 1.0,
     "w": 4.286612216869746
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.37689999999999996,
     "source_value_text": "37.69%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "48",
     "source_model_name": "Mistral-Medium-2505",
     "p": 0.37689999999999996,
     "p_star": 0.3781188118811881,
     "y": -0.49754059522886457,
     "v": 0.04168900676316587,
     "family_factor": 1.0,
     "w": 4.990555000279459
    }
   ]
  },
  {
   "slug": "qwen3-4b-instruct-2507",
   "name": "qwen3-4b-instruct-2507",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.9703137842909241,
   "se": 0.25484757772858985,
   "si_iq": 85.44529323563614,
   "si_iq_low": 79.15748737137841,
   "si_iq_high": 91.73309909989386,
   "si_iq_display": 85,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.5222222222222223,
     "source_value_text": "0.5222222222222223",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "KH7KfZvFc9kZbqiJFdfYTc",
     "source_model_name": "qwen3-4b-instruct-2507",
     "p": 0.5217439661884107,
     "p_star": 0.5212712712712713,
     "y": 0.08513647182071898,
     "v": 0.08538404959227923,
     "family_factor": 1.0,
     "w": 2.6971036672230713
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4583333333333333,
     "source_value_text": "0.4583333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "VhQBa9AViRt2UKSNpEAyjN",
     "source_model_name": "qwen3-4b-instruct-2507",
     "p": 0.27777777777777773,
     "p_star": 0.27889447236180903,
     "y": -0.9499520144472872,
     "v": 0.05457496294674936,
     "family_factor": 1.0,
     "w": 3.735082695045002
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.3568,
     "source_value_text": "35.68%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "54",
     "source_model_name": "Qwen3-4B-Instruct-2507 (FC)",
     "p": 0.3568,
     "p_star": 0.3582178217821782,
     "y": -0.5831077177462523,
     "v": 0.04264051199997817,
     "family_factor": 1.0,
     "w": 4.957264743880446
    }
   ]
  },
  {
   "slug": "qwen3-235b-a22b",
   "name": "Qwen3-235B-A22B",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.9717209688433927,
   "se": 0.21356012240072758,
   "si_iq": 85.4241854673491,
   "si_iq_low": 80.15505714377922,
   "si_iq_high": 90.693313790919,
   "si_iq_display": 85,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.6885699899295065,
     "source_value_text": "0.6885699899295065",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-06-03",
     "source_row_id": "BTDXT8mHQu4je5jysTDuXV",
     "source_model_name": "qwen3-235b-a22b",
     "p": 0.6885699899295065,
     "p_star": 0.6884276729559747,
     "y": 0.7927787616545582,
     "v": 0.003515920375733745,
     "family_factor": 1.0,
     "w": 4.830174896625952
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.596,
     "source_value_text": "59.6",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-05-09",
     "source_row_id": "2025-05-09-17-02-02--qwen3-235b-a22b.unthink_16k_diff",
     "source_model_name": "Qwen3 235B A22B diff, no think, Alibaba API",
     "p": 0.596,
     "p_star": 0.595575221238938,
     "y": 0.3870619387505229,
     "v": 0.018289054854159013,
     "family_factor": 1.0,
     "w": 1.430335718070315
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.7070707070707071,
     "source_value_text": "0.7070707070707071",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-06-03",
     "source_row_id": "agebmxGseTvmvN4AHN8i4m",
     "source_model_name": "qwen3-235b-a22b",
     "p": 0.6094276094276094,
     "p_star": 0.6088777219430486,
     "y": 0.442597219864622,
     "v": 0.032488862881412575,
     "family_factor": 1.0,
     "w": 4.357726805357197
    }
   ]
  },
  {
   "slug": "deepseek-v3-mar-2025",
   "name": "DeepSeek-V3 (Mar 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": -0.9745014781715385,
   "se": 0.17722345175445134,
   "si_iq": 85.38247782742692,
   "si_iq_low": 81.00987727474518,
   "si_iq_high": 89.75507838010867,
   "si_iq_display": 85,
   "domains": {
    "math": {
     "si_iq": 84.6479118728895,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.75547583081571,
     "source_value_text": "0.75547583081571",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-01",
     "source_row_id": "YFyn28VJ6m2hfop3KGRkBs",
     "source_model_name": "DeepSeek-V3-0324",
     "p": 0.75547583081571,
     "p_star": 0.7552830188679246,
     "y": 1.1269901746761302,
     "v": 0.00408020892580372,
     "family_factor": 1.0,
     "w": 4.803987282120446
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.37777777777777777,
     "source_value_text": "0.37777777777777777",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-01",
     "source_row_id": "VpsMexBEhXkPYJBe7v6Fk9",
     "source_model_name": "DeepSeek-V3-0324",
     "p": 0.3771549327104883,
     "p_star": 0.3798254776515646,
     "y": -0.49028904820170705,
     "v": 0.09051944474207214,
     "family_factor": 1.0,
     "w": 2.624404037482404
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.6761363636363636,
     "source_value_text": "0.6761363636363636",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-01",
     "source_row_id": "VjfLwKbT6kTprYsMGcz2YT",
     "source_model_name": "DeepSeek-V3-0324",
     "p": 0.5681818181818182,
     "p_star": 0.5678391959798995,
     "y": 0.2730405224588329,
     "v": 0.03233485166655436,
     "family_factor": 0.5,
     "w": 2.1813991624987117
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.646465,
     "source_value_text": "0.646465",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-29",
     "source_row_id": "deepseek/deepseek-chat-v3-0324",
     "source_model_name": "deepseek/deepseek-chat-v3-0324",
     "p": 0.52862,
     "p_star": 0.5284761809045226,
     "y": 0.11402811655321712,
     "v": 0.03272019249036344,
     "family_factor": 0.5,
     "w": 1.5406723600447993
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.4337431393442623,
     "source_value_text": "0.4337431393442623",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-22",
     "source_row_id": "deepseek/deepseek-chat-v3-0324",
     "source_model_name": "deepseek/deepseek-chat-v3-0324",
     "p": 0.4337431393442623,
     "p_star": 0.4350422934747669,
     "y": -0.2613076198957801,
     "v": 0.07821359265370513,
     "family_factor": 1.0,
     "w": 3.9677488717740994
    }
   ]
  },
  {
   "slug": "qwen3-coder-480b-a35b",
   "name": "Qwen3-Coder-480B-A35B",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.0274730468744366,
   "se": 0.525898368567751,
   "si_iq": 84.58790429688345,
   "si_iq_low": 71.61251376990135,
   "si_iq_high": 97.56329482386555,
   "si_iq_display": 85,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.6035354999999999,
     "source_value_text": "0.603535",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3-coder-480b-a35b-07-25",
     "source_model_name": "qwen/qwen3-coder-480b-a35b-07-25",
     "p": 0.4713806666666665,
     "p_star": 0.47152448241206013,
     "y": -0.11402545465302352,
     "v": 0.03424875875124444,
     "family_factor": 1.0,
     "w": 3.056410438599784
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.43333342857142854,
     "source_value_text": "0.433333",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-03",
     "source_row_id": "qwen/qwen3-coder-480b-a35b-07-25",
     "source_model_name": "qwen/qwen3-coder-480b-a35b-07-25",
     "p": 0.43333342857142854,
     "p_star": 0.4346406162464986,
     "y": -0.26294208630049704,
     "v": 0.07823025383954364,
     "family_factor": 1.0,
     "w": 3.9673779616738827
    }
   ]
  },
  {
   "slug": "o1-preview",
   "name": "o1-preview",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.0552033716568756,
   "se": 0.18634279284471597,
   "si_iq": 84.17194942514686,
   "si_iq_low": 79.57434910241983,
   "si_iq_high": 88.7695497478739,
   "si_iq_display": 84,
   "domains": {
    "math": {
     "si_iq": 85.87098715658092,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.8164652567975831,
     "source_value_text": "0.8164652567975831",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "8Uu6XsSJCKwcwhXDt8vgzq",
     "source_model_name": "o1-preview-2024-09-12",
     "p": 0.8164652567975831,
     "p_star": 0.8162264150943396,
     "y": 1.4909873028704688,
     "v": 0.005027620585524135,
     "family_factor": 1.0,
     "w": 4.7606524570634186
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.3111111111111111,
     "source_value_text": "0.3111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-07",
     "source_row_id": "Cprjaj9JQ9MY5NCXqeQR5H",
     "source_model_name": "o1-preview-2024-09-12",
     "p": 0.3104215326437549,
     "p_star": 0.31454280367323845,
     "y": -0.7789658879269081,
     "v": 0.09895019645670787,
     "family_factor": 1.0,
     "w": 2.5131917882212367
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5031565656565656,
     "source_value_text": "0.5031565656565656",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "7CkADTsoNbDd88uqYbqfwj",
     "source_model_name": "o1-preview-2024-09-12",
     "p": 0.33754208754208753,
     "p_star": 0.33835845896147404,
     "y": -0.670618067499917,
     "v": 0.044335564023879524,
     "family_factor": 1.0,
     "w": 4.000055517115008
    }
   ]
  },
  {
   "slug": "magistral-small-1-0",
   "name": "Magistral Small 1.0",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.1470449026394582,
   "se": 0.2699862660892192,
   "si_iq": 82.79432646040813,
   "si_iq_low": 76.13300661457939,
   "si_iq_high": 89.45564630623687,
   "si_iq_display": 83,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.3,
     "source_value_text": "0.3",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "hmZPoiHBpqufv9r7ujiK8V",
     "source_model_name": "magistral-small-2506",
     "p": 0.29929929929929927,
     "p_star": 0.3036623580101841,
     "y": -0.8299182407830691,
     "v": 0.10090560338706679,
     "family_factor": 1.0,
     "w": 2.4887309839571516
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5606060606060606,
     "source_value_text": "0.5606060606060606",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-06",
     "source_row_id": "dwGLob8Vhrwx4Wn376jVmt",
     "source_model_name": "magistral-small-2506",
     "p": 0.4141414141414141,
     "p_star": 0.41457286432160795,
     "y": -0.3450929796651203,
     "v": 0.03716478085576799,
     "family_factor": 1.0,
     "w": 4.209172832760352
    }
   ]
  },
  {
   "slug": "mistral-small-3-2",
   "name": "Mistral Small 3.2",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.3035611752533387,
   "se": 0.2595414080795119,
   "si_iq": 80.44658237119992,
   "si_iq_low": 74.04296652252165,
   "si_iq_high": 86.85019821987818,
   "si_iq_display": 80,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.30277777777777776,
     "source_value_text": "0.30277777777777776",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "HyKzRUkV42yTmGrbYQvZxQ",
     "source_model_name": "mistral-small-3.2-2506",
     "p": 0.3020798576354132,
     "p_star": 0.30638246942594766,
     "y": -0.8170864783453332,
     "v": 0.10039902019227238,
     "family_factor": 1.0,
     "w": 2.495022178852352
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.49053030303030304,
     "source_value_text": "0.49053030303030304",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "V2CVKXcEdLnEXmppjUEB9M",
     "source_model_name": "mistral-small-3.2-2506",
     "p": 0.3207070707070707,
     "p_star": 0.32160804020100503,
     "y": -0.7463916950787575,
     "v": 0.046668836805555565,
     "family_factor": 1.0,
     "w": 3.9364208632474598
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.3715,
     "source_value_text": "37.15%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "51",
     "source_model_name": "Mistral-small-2506 (FC)",
     "p": 0.3715,
     "p_star": 0.37277227722772277,
     "y": -0.5203419525212456,
     "v": 0.04192647982130934,
     "family_factor": 1.0,
     "w": 4.98220474485678
    }
   ]
  },
  {
   "slug": "gemini-1-5-pro-sept-2024",
   "name": "Gemini 1.5 Pro (Sept 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.3257593810164798,
   "se": 0.18768862754457924,
   "si_iq": 80.1136092847528,
   "si_iq_low": 75.48280343818463,
   "si_iq_high": 84.74441513132098,
   "si_iq_display": 80,
   "domains": {
    "math": {
     "si_iq": 79.76896324555454,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.7039274924471299,
     "source_value_text": "0.7039274924471299",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "QyqLmgcJpeDMsnQyaaJVkR",
     "source_model_name": "gemini-1.5-pro-002",
     "p": 0.7039274924471299,
     "p_star": 0.7037735849056603,
     "y": 0.8653326142955073,
     "v": 0.003617424565837331,
     "family_factor": 1.0,
     "w": 4.82544323114599
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.23055555555555557,
     "source_value_text": "0.23055555555555557",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "fhCdyX9uUS4WPtjLiVdBdK",
     "source_model_name": "gemini-1.5-pro-002",
     "p": 0.22978534089645203,
     "p_star": 0.23565957261609438,
     "y": -1.1766250007817343,
     "v": 0.11856752678325475,
     "family_factor": 1.0,
     "w": 2.2876225364247786
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5722853535353535,
     "source_value_text": "0.5722853535353535",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "9TrLEEw8TvsyugyCjwvUvD",
     "source_model_name": "gemini-1.5-pro-002",
     "p": 0.42971380471380466,
     "p_star": 0.43006700167504186,
     "y": -0.28157779272290784,
     "v": 0.03620890059582315,
     "family_factor": 1.0,
     "w": 4.238711763064698
    }
   ]
  },
  {
   "slug": "gemini-2-0-flash-dec-2024",
   "name": "Gemini 2.0 Flash (Dec 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.3655210607643933,
   "se": 0.6325757120685713,
   "si_iq": 79.5171840885341,
   "si_iq_low": 63.90976373405153,
   "si_iq_high": 95.12460444301666,
   "si_iq_display": 80,
   "domains": {},
   "inputs": [
    {
     "benchmark": "aider_polyglot",
     "score": 0.222,
     "source_value_text": "22.2",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2024-12-22",
     "source_row_id": "2024-12-22-20-08-13--gemini-2.0-flash-exp-polyglot-whole",
     "source_model_name": "gemini-2.0-flash-exp",
     "p": 0.222,
     "p_star": 0.22323008849557524,
     "y": -1.2469411558148231,
     "v": 0.025405076894110794,
     "family_factor": 1.0,
     "w": 1.4100392040090426
    }
   ]
  },
  {
   "slug": "magistral-small-1-2",
   "name": "Magistral Small 1.2",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.3944747644664783,
   "se": 0.27523028475056555,
   "si_iq": 79.08287853300283,
   "si_iq_low": 72.29217401110623,
   "si_iq_high": 85.87358305489943,
   "si_iq_display": 79,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.28055555555555556,
     "source_value_text": "0.28055555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "cSTYZ3FKp5Mbs3xopn68NK",
     "source_model_name": "magistral-small-2509",
     "p": 0.27983539094650206,
     "p_star": 0.284621578099839,
     "y": -0.9216511622580784,
     "v": 0.10481366470789738,
     "family_factor": 1.0,
     "w": 2.4412433648560197
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.476010101010101,
     "source_value_text": "0.476010101010101",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "3UbYVQELDHAcQgu7sTTnRf",
     "source_model_name": "magistral-small-2509",
     "p": 0.3013468013468013,
     "p_star": 0.3023450586264656,
     "y": -0.8361556838339621,
     "v": 0.049836790019450815,
     "family_factor": 1.0,
     "w": 3.8531943264046036
    }
   ]
  },
  {
   "slug": "qwen2-5-max",
   "name": "Qwen2.5-Max",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.4867547182501246,
   "se": 0.1852595598515582,
   "si_iq": 77.69867922624813,
   "si_iq_low": 73.12780530534701,
   "si_iq_high": 82.26955314714925,
   "si_iq_display": 78,
   "domains": {
    "math": {
     "si_iq": 77.06600905042654,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.6718277945619335,
     "source_value_text": "0.6718277945619335",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-01",
     "source_row_id": "GFZDNH95TnVegNrEtmUT2Q",
     "source_model_name": "qwen-max-2025-01-25",
     "p": 0.6718277945619335,
     "p_star": 0.6716981132075471,
     "y": 0.7158754316375012,
     "v": 0.003419863102156786,
     "family_factor": 1.0,
     "w": 4.8346612053248075
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.16111111111111112,
     "source_value_text": "0.16111111111111112",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-01",
     "source_row_id": "PZt4Yb9bpXVPDoPi4uTxwK",
     "source_model_name": "qwen-max-2025-01-25",
     "p": 0.16027138249360473,
     "p_star": 0.16765678722200464,
     "y": -1.6023259145519109,
     "v": 0.15330578010909524,
     "family_factor": 1.0,
     "w": 1.9738988971536973
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.218,
     "source_value_text": "21.8",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-01-28",
     "source_row_id": "2025-01-28-16-00-03--qwen-max-2025-01-25-polyglot-diff",
     "source_model_name": "qwen-max-2025-01-25",
     "p": 0.218,
     "p_star": 0.21924778761061944,
     "y": -1.2700552893452821,
     "v": 0.025734586626764713,
     "family_factor": 1.0,
     "w": 1.4091133119698407
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5612373737373737,
     "source_value_text": "0.5612373737373737",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-01",
     "source_row_id": "GBf7rqHkGGzfX87V37F9mH",
     "source_model_name": "qwen-max-2025-01-25",
     "p": 0.41498316498316495,
     "p_star": 0.4154103852596314,
     "y": -0.34164317603744543,
     "v": 0.03710961376193017,
     "family_factor": 1.0,
     "w": 4.210866425399652
    }
   ]
  },
  {
   "slug": "deepseek-v3",
   "name": "DeepSeek-V3",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.5043673596140255,
   "se": 0.18460506170493496,
   "si_iq": 77.43448960578962,
   "si_iq_low": 72.87976399330549,
   "si_iq_high": 81.98921521827376,
   "si_iq_display": 77,
   "domains": {
    "math": {
     "si_iq": 76.2162229316993,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.6485083081570997,
     "source_value_text": "0.6485083081570997",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "exvQCLCiga6gE7zvQNp2Z6",
     "source_model_name": "DeepSeek-V3",
     "p": 0.6485083081570997,
     "p_star": 0.6483962264150943,
     "y": 0.6119970716423466,
     "v": 0.0033079750282551637,
     "family_factor": 1.0,
     "w": 4.839897402531101
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.15833333333333333,
     "source_value_text": "0.15833333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "7saSEhfVvXuz4yTcGy5u2y",
     "source_model_name": "DeepSeek-V3",
     "p": 0.15749082415749083,
     "p_star": 0.16493667580624102,
     "y": -1.6219459420885822,
     "v": 0.15534167051444903,
     "family_factor": 1.0,
     "w": 1.9581606049362261
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5653409090909091,
     "source_value_text": "0.5653409090909091",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "Vwo3nMA8g2gGBCyTdKFMQJ",
     "source_model_name": "DeepSeek-V3",
     "p": 0.4204545454545454,
     "p_star": 0.4208542713567838,
     "y": -0.3192675111715826,
     "v": 0.036760980927589205,
     "family_factor": 0.5,
     "w": 2.1108004098600146
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.661616,
     "source_value_text": "0.661616",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "deepseek/deepseek-chat-v3",
     "source_model_name": "deepseek/deepseek-chat-v3",
     "p": 0.5488213333333333,
     "p_star": 0.548576,
     "y": 0.19491879893297856,
     "v": 0.03245822187730615,
     "family_factor": 0.5,
     "w": 1.5428294656900363
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.4053599698492462,
     "source_value_text": "0.4053599698492462",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-02",
     "source_row_id": "deepseek/deepseek-chat-v3",
     "source_model_name": "deepseek/deepseek-chat-v3",
     "p": 0.4053599698492462,
     "p_star": 0.4072156567149473,
     "y": -0.37548774798058804,
     "v": 0.07963582071150929,
     "family_factor": 1.0,
     "w": 3.93633507162329
    }
   ]
  },
  {
   "slug": "glm-4-7-flash-none",
   "name": "glm-4.7-flash_none",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.5338120666641353,
   "se": 0.28050634449225714,
   "si_iq": 76.99281900003797,
   "si_iq_low": 70.07193925858596,
   "si_iq_high": 83.91369874148998,
   "si_iq_display": 77,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.25,
     "source_value_text": "0.25",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "fPE4Zajhq5WfccSxEYXXR7",
     "source_model_name": "glm-4.7-flash_none",
     "p": 0.24924924924924924,
     "p_star": 0.25470035252643947,
     "y": -1.07369858281874,
     "v": 0.11247082204607106,
     "family_factor": 1.0,
     "w": 2.3532642985284005
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4513888888888889,
     "source_value_text": "0.4513888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "GSde7u2Mb6GZGpubJjjPam",
     "source_model_name": "glm-4.7-flash_none",
     "p": 0.26851851851851855,
     "p_star": 0.2696817420435511,
     "y": -0.9962378783645711,
     "v": 0.05676386508194093,
     "family_factor": 1.0,
     "w": 3.6829295379253577
    }
   ]
  },
  {
   "slug": "qwen3-4b",
   "name": "Qwen3-4B",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.5511930119690265,
   "se": 0.481871454480191,
   "si_iq": 76.7321048204646,
   "si_iq_low": 64.8429819796512,
   "si_iq_high": 88.621227661278,
   "si_iq_display": 77,
   "domains": {},
   "inputs": [
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5233585858585859,
     "source_value_text": "0.5233585858585859",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "G3dinPvwrci2Nu3m9pby2i",
     "source_model_name": "qwen3-4b",
     "p": 0.36447811447811446,
     "p_star": 0.3651591289782244,
     "y": -0.5530411422933377,
     "v": 0.041256421696333846,
     "family_factor": 1.0,
     "w": 4.087249714075196
    }
   ]
  },
  {
   "slug": "phi-4",
   "name": "Phi-4",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.6011653290439583,
   "se": 0.1890969220277643,
   "si_iq": 75.98252006434063,
   "si_iq_low": 71.31696763556478,
   "si_iq_high": 80.64807249311647,
   "si_iq_display": 76,
   "domains": {
    "math": {
     "si_iq": 75.66255571180321,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.6493580060422961,
     "source_value_text": "0.6493580060422961",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-31",
     "source_row_id": "PnvmfAHVxH9oXfcdcUeUZ3",
     "source_model_name": "phi-4",
     "p": 0.6493580060422961,
     "p_star": 0.649245283018868,
     "y": 0.6157234180760365,
     "v": 0.003311645991546737,
     "family_factor": 1.0,
     "w": 4.839725426898256
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.1375,
     "source_value_text": "0.1375",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "5mmrBSQb7hVSJ9VYtNm46i",
     "source_model_name": "phi-4",
     "p": 0.13663663663663664,
     "p_star": 0.1445358401880141,
     "y": -1.7781166928242684,
     "v": 0.1731876315457517,
     "family_factor": 1.0,
     "w": 1.8302439139389193
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5606060606060606,
     "source_value_text": "0.5606060606060606",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-31",
     "source_row_id": "RAwuPRwJedy7P2KeQhEmr8",
     "source_model_name": "phi-4",
     "p": 0.4141414141414141,
     "p_star": 0.41457286432160795,
     "y": -0.3450929796651203,
     "v": 0.03716478085576799,
     "family_factor": 1.0,
     "w": 4.209172832760352
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.2879,
     "source_value_text": "28.79%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "70",
     "source_model_name": "Phi-4 (Prompt)",
     "p": 0.2879,
     "p_star": 0.29,
     "y": -0.8953840470548413,
     "v": 0.04761029865987959,
     "family_factor": 1.0,
     "w": 4.790362106209455
    }
   ]
  },
  {
   "slug": "qwen-plus-jan-2025",
   "name": "Qwen Plus (Jan 2025)",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.6036518384967064,
   "se": 0.1915669818381417,
   "si_iq": 75.9452224225494,
   "si_iq_low": 71.21872667738349,
   "si_iq_high": 80.67171816771533,
   "si_iq_display": 76,
   "domains": {
    "math": {
     "si_iq": 76.66504856327174,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.6527567975830816,
     "source_value_text": "0.6527567975830816",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-07",
     "source_row_id": "J3WoEpLKAJZWGGpyBVCCCn",
     "source_model_name": "qwen-plus-2025-01-25",
     "p": 0.6527567975830816,
     "p_star": 0.6526415094339623,
     "y": 0.6306706277040909,
     "v": 0.003326623240288699,
     "family_factor": 1.0,
     "w": 4.839023906135375
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.17777777777777778,
     "source_value_text": "0.17777777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-07",
     "source_row_id": "AULNJG2C75JBP6uaiAgj3P",
     "source_model_name": "qwen-plus-2025-01-25",
     "p": 0.17695473251028807,
     "p_star": 0.18397745571658614,
     "y": -1.4896287555577956,
     "v": 0.1424251310976641,
     "family_factor": 1.0,
     "w": 2.06249243936087
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4810606060606061,
     "source_value_text": "0.4810606060606061",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-07",
     "source_row_id": "QtraMoKiQRRpZc9txpFAYF",
     "source_model_name": "qwen-plus-2025-01-25",
     "p": 0.3080808080808081,
     "p_star": 0.3090452261306533,
     "y": -0.8045867422941536,
     "v": 0.04866944279198888,
     "family_factor": 1.0,
     "w": 3.8834494725148496
    }
   ]
  },
  {
   "slug": "claude-3-5-sonnet-october-2024",
   "name": "Claude 3.5 Sonnet (October 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.6220353790428605,
   "se": 0.1921543881469583,
   "si_iq": 75.66946931435709,
   "si_iq_low": 70.92848060494094,
   "si_iq_high": 80.41045802377324,
   "si_iq_display": 76,
   "domains": {
    "math": {
     "si_iq": 71.79520327474592,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.5694864048338368,
     "source_value_text": "0.5694864048338368",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "AjroyuZECXLtMTwnzaMHtX",
     "source_model_name": "claude-3-5-sonnet-20241022",
     "p": 0.5694864048338368,
     "p_star": 0.569433962264151,
     "y": 0.2795421089057735,
     "v": 0.0030759062336469063,
     "family_factor": 1.0,
     "w": 4.8507941212432995
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.08472222222222223,
     "source_value_text": "0.08472222222222223",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "geVVaRWxuprKUqnW2VzvCa",
     "source_model_name": "claude-3-5-sonnet-20241022",
     "p": 0.0838060282504727,
     "p_star": 0.09285372328850591,
     "y": -2.2792783253950524,
     "v": 0.2551978553765335,
     "family_factor": 1.0,
     "w": 1.40766615685212
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.516,
     "source_value_text": "51.6",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-01-17",
     "source_row_id": "2025-01-17-19-44-33--sonnet-baseline-jan-17",
     "source_model_name": "claude-3-5-sonnet-20241022",
     "p": 0.516,
     "p_star": 0.5159292035398231,
     "y": 0.06373838392851144,
     "v": 0.01763870292034205,
     "family_factor": 1.0,
     "w": 1.4322198491172928
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.553030303030303,
     "source_value_text": "0.553030303030303",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "JCCVcVLz3J4TQXSU67hMJZ",
     "source_model_name": "claude-3-5-sonnet-20241022",
     "p": 0.404040404040404,
     "p_star": 0.40452261306532655,
     "y": -0.3866557761506685,
     "v": 0.03785992394612843,
     "family_factor": 1.0,
     "w": 4.1879485543256
    }
   ]
  },
  {
   "slug": "grok-2-dec-2024",
   "name": "Grok-2 (Dec 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.6497097709092134,
   "se": 0.19596196236329183,
   "si_iq": 75.2543534363618,
   "si_iq_low": 70.41942117174514,
   "si_iq_high": 80.08928570097845,
   "si_iq_display": 75,
   "domains": {
    "math": {
     "si_iq": 74.63392307238652,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.6351963746223565,
     "source_value_text": "0.6351963746223565",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-17",
     "source_row_id": "Kpck3pLw3veM5Mt7WZAb8G",
     "source_model_name": "grok-2-1212",
     "p": 0.6351963746223565,
     "p_star": 0.6350943396226414,
     "y": 0.5541346987375112,
     "v": 0.0032541486401210227,
     "family_factor": 1.0,
     "w": 4.842420441068041
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.11527777777777778,
     "source_value_text": "0.11527777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "PpSVDb67Ucbxpcd8JQv5ii",
     "source_model_name": "grok-2-1212",
     "p": 0.11439216994772551,
     "p_star": 0.12277494886190539,
     "y": -1.9664105787984925,
     "v": 0.19906851143624602,
     "family_factor": 1.0,
     "w": 1.6718577211582757
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5378787878787878,
     "source_value_text": "0.5378787878787878",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "83DRJD4FvjwqU9eStRaNiU",
     "source_model_name": "grok-2-1212",
     "p": 0.3838383838383838,
     "p_star": 0.3844221105527638,
     "y": -0.47082028915229146,
     "v": 0.039448982207262,
     "family_factor": 1.0,
     "w": 4.140225766090672
    }
   ]
  },
  {
   "slug": "qwen2-5-coder-32b-instruct",
   "name": "Qwen2.5-Coder-32B-Instruct",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.6956367443222158,
   "se": 0.6361673901882096,
   "si_iq": 74.56544883516676,
   "si_iq_low": 58.869411688857205,
   "si_iq_high": 90.26148598147633,
   "si_iq_display": 75,
   "domains": {},
   "inputs": [
    {
     "benchmark": "aider_polyglot",
     "score": 0.16399999999999998,
     "source_value_text": "16.4",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2024-12-26",
     "source_row_id": "2024-12-26-00-55-20--Qwen2.5-Coder-32B-Instruct",
     "source_model_name": "Qwen2.5-Coder-32B-Instruct",
     "p": 0.16399999999999998,
     "p_star": 0.1654867256637168,
     "y": -1.617957665778871,
     "v": 0.031898424076079866,
     "family_factor": 1.0,
     "w": 1.3920148922271909
    }
   ]
  },
  {
   "slug": "gemini-1-5-flash-sep-2024",
   "name": "Gemini 1.5 Flash (Sep 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.70001842426559,
   "se": 0.1927336591211062,
   "si_iq": 74.49972363601614,
   "si_iq_low": 69.74444268391633,
   "si_iq_high": 79.25500458811597,
   "si_iq_display": 74,
   "domains": {
    "math": {
     "si_iq": 75.12695420619859,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.6186744712990937,
     "source_value_text": "0.6186744712990937",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "kDnfjYKQpnLGEjuhBc9AvM",
     "source_model_name": "gemini-1.5-flash-002",
     "p": 0.6186744712990937,
     "p_star": 0.6185849056603774,
     "y": 0.48354619062284865,
     "v": 0.003196384633076085,
     "family_factor": 1.0,
     "w": 4.845130977967827
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.1625,
     "source_value_text": "0.1625",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "QdGZ2m52PWt3EkLPbcoRwz",
     "source_model_name": "gemini-1.5-flash-002",
     "p": 0.16166166166166165,
     "p_star": 0.16901684292988642,
     "y": -1.5926111541188968,
     "v": 0.15231376835457963,
     "family_factor": 1.0,
     "w": 1.9816595949585434
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.47316919191919193,
     "source_value_text": "0.47316919191919193",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "PCLvrs4TEBtqQqcYeU8pAG",
     "source_model_name": "gemini-1.5-flash-002",
     "p": 0.2975589225589226,
     "p_star": 0.29857621440536014,
     "y": -0.8540870238448709,
     "v": 0.05052694624245057,
     "family_factor": 1.0,
     "w": 3.8355276819321102
    }
   ]
  },
  {
   "slug": "llama-4-scout",
   "name": "Llama 4 Scout",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.779338148495812,
   "se": 0.19611421239581334,
   "si_iq": 73.30992777256282,
   "si_iq_low": 68.47123907182127,
   "si_iq_high": 78.14861647330437,
   "si_iq_display": 73,
   "domains": {
    "math": {
     "si_iq": 73.234380319731,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.6227341389728097,
     "source_value_text": "0.6227341389728097",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-08",
     "source_row_id": "c6rTyTFCeoHMBzC2QwjxFL",
     "source_model_name": "Llama-4-Scout-17B-16E-Instruct",
     "p": 0.6227341389728097,
     "p_star": 0.6226415094339623,
     "y": 0.5007752879124896,
     "v": 0.0032096969696969705,
     "family_factor": 1.0,
     "w": 4.844506036548127
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.07777777777777778,
     "source_value_text": "0.07777777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-08",
     "source_row_id": "T3X5DeC47iqCaoRYXu5k8L",
     "source_model_name": "Llama-4-Scout-17B-16E-Instruct",
     "p": 0.07685463241018797,
     "p_star": 0.08605344474909693,
     "y": -2.3628035424732663,
     "v": 0.2735460733487512,
     "family_factor": 1.0,
     "w": 1.338522971256583
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5183080808080808,
     "source_value_text": "0.5183080808080808",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-08",
     "source_row_id": "MsXAXDEKP3xBKtiA7aTBBG",
     "source_model_name": "Llama-4-Scout-17B-16E-Instruct",
     "p": 0.3577441077441077,
     "p_star": 0.35845896147403683,
     "y": -0.5820589741587947,
     "v": 0.04195960881803671,
     "family_factor": 1.0,
     "w": 4.067003804791201
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.2813,
     "source_value_text": "28.13%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "72",
     "source_model_name": "Llama-4-Scout-17B-16E-Instruct (FC)",
     "p": 0.2813,
     "p_star": 0.28346534653465344,
     "y": -0.9273367297680127,
     "v": 0.04826364071657801,
     "family_factor": 1.0,
     "w": 4.769252783548318
    }
   ]
  },
  {
   "slug": "gemma-3-12b",
   "name": "Gemma 3 12B",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.8244573502813854,
   "se": 0.2690247868134136,
   "si_iq": 72.63313974577922,
   "si_iq_low": 65.99554229544137,
   "si_iq_high": 79.27073719611707,
   "si_iq_display": 73,
   "domains": {
    "agentic": {
     "si_iq": 75.3403906580784,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.16666666666666666,
     "source_value_text": "0.16666666666666666",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "CAyLyhDHZiMQBZDB3qd8tG",
     "source_model_name": "gemma-3-12b-it",
     "p": 0.16583249916583248,
     "p_star": 0.17309701005353179,
     "y": -1.5638351954819258,
     "v": 0.14943659565512635,
     "family_factor": 1.0,
     "w": 2.004517415284585
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.39457070707070707,
     "source_value_text": "0.39457070707070707",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "KfQKr2ibCFMx5xBELoiM3Y",
     "source_model_name": "gemma-3-12b-it",
     "p": 0.19276094276094277,
     "p_star": 0.19430485762144056,
     "y": -1.4222770789993964,
     "v": 0.08672757409380473,
     "family_factor": 0.5,
     "w": 1.5459695012681611
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.37878799999999996,
     "source_value_text": "0.37878799999999996",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-07",
     "source_row_id": "google/gemma-3-12b-it",
     "source_model_name": "google/gemma-3-12b-it",
     "p": 0.17171733333333328,
     "p_star": 0.17336699497487432,
     "y": -1.5619501241034168,
     "v": 0.10196817318668498,
     "family_factor": 0.5,
     "w": 1.1249235346991495
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.3043,
     "source_value_text": "30.43%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "66",
     "source_model_name": "Gemma-3-12b-it (Prompt)",
     "p": 0.3043,
     "p_star": 0.30623762376237623,
     "y": -0.8177681556854642,
     "v": 0.04614110198147887,
     "family_factor": 1.0,
     "w": 4.838520933530133
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.48,
     "source_value_text": "0.48",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-08",
     "source_row_id": "google/gemma-3-12b-it",
     "source_model_name": "google/gemma-3-12b-it",
     "p": 0.48,
     "p_star": 0.4803921568627451,
     "y": -0.07847161544149509,
     "v": 0.07701193685021179,
     "family_factor": 1.0,
     "w": 3.994684165197876
    }
   ]
  },
  {
   "slug": "deepseek-r1-distill-qwen-1-5b",
   "name": "DeepSeek-R1-Distill-Qwen-1.5B",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.8261472794611333,
   "se": 0.30670958891600747,
   "si_iq": 72.607790808083,
   "si_iq_low": 65.04040339558024,
   "si_iq_high": 80.17517822058576,
   "si_iq_display": 73,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.21388888888888888,
     "source_value_text": "0.21388888888888888",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "Gs234P3jzGiLm68KjyzYZL",
     "source_model_name": "DeepSeek-R1-Distill-Qwen-1.5B",
     "p": 0.21310199087976864,
     "p_star": 0.21933890412151277,
     "y": -1.2695230784620894,
     "v": 0.1247659658736406,
     "family_factor": 1.0,
     "w": 2.2245360771438634
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.33585858585858586,
     "source_value_text": "0.33585858585858586",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "ESnXA8LqMqhjcsoWQaMLVQ",
     "source_model_name": "DeepSeek-R1-Distill-Qwen-1.5B",
     "p": 0.11447811447811447,
     "p_star": 0.11641541038525961,
     "y": -2.026822112779475,
     "v": 0.18778457543556348,
     "family_factor": 1.0,
     "w": 2.006189068040923
    }
   ]
  },
  {
   "slug": "qwen2-5-72b",
   "name": "Qwen2.5-72B",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.8466060547705894,
   "se": 0.19378464511977747,
   "si_iq": 72.30090917844116,
   "si_iq_low": 67.51969744848347,
   "si_iq_high": 77.08212090839885,
   "si_iq_display": 72,
   "domains": {
    "math": {
     "si_iq": 73.51343087880436,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.631703172205438,
     "source_value_text": "0.631703172205438",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "ni4DJboYYpdRssVeAuro2V",
     "source_model_name": "qwen2.5-72b-instruct",
     "p": 0.631703172205438,
     "p_star": 0.6316037735849057,
     "y": 0.5391031958514868,
     "v": 0.003241129170296407,
     "family_factor": 1.0,
     "w": 4.8430311060938624
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.08055555555555556,
     "source_value_text": "0.08055555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "67YbVQfJh7sd77KH3zFgTn",
     "source_model_name": "qwen2.5-72b-instruct",
     "p": 0.07963519074630186,
     "p_star": 0.08877355616486052,
     "y": -2.328702617888719,
     "v": 0.26586218661689354,
     "family_factor": 1.0,
     "w": 1.3666348102914683
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4914772727272727,
     "source_value_text": "0.4914772727272727",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "WtALgW6VSFdihDZWXRm2AZ",
     "source_model_name": "qwen2.5-72b-instruct",
     "p": 0.32196969696969696,
     "p_star": 0.3228643216080402,
     "y": -0.7406394860137774,
     "v": 0.04648126112926057,
     "family_factor": 0.5,
     "w": 1.9707308113634763
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.461279,
     "source_value_text": "0.461279",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-01",
     "source_row_id": "qwen/qwen-2.5-72b-instruct",
     "source_model_name": "qwen/qwen-2.5-72b-instruct",
     "p": 0.2817053333333333,
     "p_star": 0.2828022914572864,
     "y": -0.9306035099831633,
     "v": 0.05370696565823475,
     "family_factor": 0.5,
     "w": 1.3854875495220595
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.25,
     "source_value_text": "0.25",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-09-01",
     "source_row_id": "qwen/qwen-2.5-72b-instruct",
     "source_model_name": "qwen/qwen-2.5-72b-instruct",
     "p": 0.25,
     "p_star": 0.2549019607843137,
     "y": -1.0726368022648491,
     "v": 0.10121457489878541,
     "family_factor": 1.0,
     "w": 3.5141926549914935
    }
   ]
  },
  {
   "slug": "mistral-large-2-nov-2024",
   "name": "Mistral Large 2 (Nov 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.9281580488053331,
   "se": 0.1958462815158396,
   "si_iq": 71.07762926792,
   "si_iq_low": 66.24555117487319,
   "si_iq_high": 75.90970736096682,
   "si_iq_display": 71,
   "domains": {
    "math": {
     "si_iq": 69.03686954861949,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.5028323262839879,
     "source_value_text": "0.5028323262839879",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "MMqL6fQSwsBKAdBSfxrYpU",
     "source_model_name": "mistral-large-2411",
     "p": 0.5028323262839879,
     "p_star": 0.5028301886792453,
     "y": 0.011320875624482514,
     "v": 0.003016686187880708,
     "family_factor": 1.0,
     "w": 4.853582642797357
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.07777777777777778,
     "source_value_text": "0.07777777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "beRGgJXTJggTi8PPEZNoZ5",
     "source_model_name": "mistral-large-2411",
     "p": 0.07685463241018797,
     "p_star": 0.08605344474909693,
     "y": -2.3628035424732663,
     "v": 0.2735460733487512,
     "family_factor": 1.0,
     "w": 1.338522971256583
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5132575757575758,
     "source_value_text": "0.5132575757575758",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "n9gpXfUzo8SbWqvrG2q4xM",
     "source_model_name": "mistral-large-2411",
     "p": 0.35101010101010105,
     "p_star": 0.3517587939698493,
     "y": -0.6113171623123128,
     "v": 0.042705268153773124,
     "family_factor": 1.0,
     "w": 4.0457530171030385
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.3837,
     "source_value_text": "38.37%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "46",
     "source_model_name": "mistral-large-2411 (FC)",
     "p": 0.3837,
     "p_star": 0.3848514851485148,
     "y": -0.469006219211471,
     "v": 0.04140798580335488,
     "family_factor": 1.0,
     "w": 5.000472760922187
    }
   ]
  },
  {
   "slug": "yi-lightning",
   "name": "Yi-Lightning",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.941603352335805,
   "se": 0.6399432179880511,
   "si_iq": 70.87594971496293,
   "si_iq_low": 55.08675228675516,
   "si_iq_high": 86.6651471431707,
   "si_iq_display": 71,
   "domains": {},
   "inputs": [
    {
     "benchmark": "aider_polyglot",
     "score": 0.129,
     "source_value_text": "12.9",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2024-12-23",
     "source_row_id": "2024-12-23-01-11-56--yi-test",
     "source_model_name": "yi-lightning",
     "p": 0.129,
     "p_star": 0.130641592920354,
     "y": -1.8952978346688125,
     "v": 0.03878692178261675,
     "family_factor": 1.0,
     "w": 1.3733906977062784
    }
   ]
  },
  {
   "slug": "claude-3-5-sonnet",
   "name": "Claude 3.5 Sonnet",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.9432294550444138,
   "se": 0.20272982455092453,
   "si_iq": 70.85155817433379,
   "si_iq_low": 65.84964373185551,
   "si_iq_high": 75.85347261681208,
   "si_iq_display": 71,
   "domains": {
    "math": {
     "si_iq": 69.15359428158996,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.5168051359516617,
     "source_value_text": "0.5168051359516617",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "H42HJG29bwqzaMewTMsmky",
     "source_model_name": "claude-3-5-sonnet-20240620",
     "p": 0.5168051359516617,
     "p_star": 0.5167924528301887,
     "y": 0.06719508306355301,
     "v": 0.0030199959256286095,
     "family_factor": 1.0,
     "w": 4.853426711072247
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.06527777777777778,
     "source_value_text": "0.06527777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "2xNPhKLsiWLHQBLLDGU4VJ",
     "source_model_name": "claude-3-5-sonnet-20240620",
     "p": 0.06434211989767545,
     "p_star": 0.07381294337816077,
     "y": -2.529542118480823,
     "v": 0.31529395771968294,
     "family_factor": 1.0,
     "w": 1.2039664693062844
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5404040404040404,
     "source_value_text": "0.5404040404040404",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "78Wpvp8WDByAcQRBas72cs",
     "source_model_name": "claude-3-5-sonnet-20240620",
     "p": 0.3872053872053873,
     "p_star": 0.3877721943048577,
     "y": -0.45668640566354396,
     "v": 0.03916440053801142,
     "family_factor": 1.0,
     "w": 4.14869224426349
    }
   ]
  },
  {
   "slug": "qwen2-5-32b",
   "name": "Qwen2.5-32B",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.9607700375210493,
   "se": 0.20289948886530712,
   "si_iq": 70.58844943718427,
   "si_iq_low": 65.58234889931342,
   "si_iq_high": 75.5945499750551,
   "si_iq_display": 71,
   "domains": {
    "math": {
     "si_iq": 70.79669161352598,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.5607061933534743,
     "source_value_text": "0.5607061933534743",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-30",
     "source_row_id": "Nk4mmCXFH3mEyCYnQPdPx5",
     "source_model_name": "qwen2.5-32b-instruct",
     "p": 0.5607061933534743,
     "p_star": 0.5606603773584905,
     "y": 0.2438425923842832,
     "v": 0.00306165316624893,
     "family_factor": 1.0,
     "w": 4.851464969162188
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.07361111111111111,
     "source_value_text": "0.07361111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "NRCNnCCL5aQKsZf6cKC69Z",
     "source_model_name": "qwen2.5-32b-instruct",
     "p": 0.07268379490601713,
     "p_star": 0.08197327762545155,
     "y": -2.4158331880007586,
     "v": 0.2860489857015964,
     "family_factor": 1.0,
     "w": 1.2951724224616512
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.46085858585858586,
     "source_value_text": "0.46085858585858586",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-30",
     "source_row_id": "d6JihAFVqUy3u9suNt4P3L",
     "source_model_name": "qwen2.5-32b-instruct",
     "p": 0.28114478114478114,
     "p_star": 0.2822445561139028,
     "y": -0.9333549882454182,
     "v": 0.0538287638335576,
     "family_factor": 1.0,
     "w": 3.7532009931141204
    }
   ]
  },
  {
   "slug": "gpt-4o-may-2024",
   "name": "GPT-4o (May 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.9779781823659663,
   "se": 0.195568890537361,
   "si_iq": 70.3303272645105,
   "si_iq_low": 65.5050931863714,
   "si_iq_high": 75.1555613426496,
   "si_iq_display": 70,
   "domains": {
    "math": {
     "si_iq": 68.82563674588097,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.5104796072507553,
     "source_value_text": "0.5104796072507553",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "Uqsvq9TAGoqD2xpKfhHBmS",
     "source_model_name": "gpt-4o-2024-05-13",
     "p": 0.5104796072507553,
     "p_star": 0.5104716981132076,
     "y": 0.04189291827499569,
     "v": 0.0030179132684008533,
     "family_factor": 1.0,
     "w": 4.853524830165311
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.0625,
     "source_value_text": "0.0625",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "9cCn5aW522cTRxJSE69crm",
     "source_model_name": "gpt-4o-2024-05-13",
     "p": 0.06156156156156156,
     "p_star": 0.07109283196239717,
     "y": -2.570022291612731,
     "v": 0.32656604235377523,
     "family_factor": 1.0,
     "w": 1.1721514381243734
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4889520202020202,
     "source_value_text": "0.4889520202020202",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "Y59q8WbEDp2HH8oovyJCj9",
     "source_model_name": "gpt-4o-2024-05-13",
     "p": 0.3186026936026936,
     "p_star": 0.3195142378559464,
     "y": -0.7560050634793809,
     "v": 0.046986311799230386,
     "family_factor": 0.5,
     "w": 1.9639593038371919
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.542088,
     "source_value_text": "0.542088",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "openai/gpt-4o-2024-05-13",
     "source_model_name": "openai/gpt-4o-2024-05-13",
     "p": 0.38945066666666667,
     "p_star": 0.3900061909547739,
     "y": -0.4472861947689602,
     "v": 0.03897918947291984,
     "family_factor": 0.5,
     "w": 1.4908704983982826
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.44,
     "source_value_text": "0.44",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "openai/gpt-4o-2024-05-13",
     "source_model_name": "openai/gpt-4o-2024-05-13",
     "p": 0.44,
     "p_star": 0.4411764705882353,
     "y": -0.2363887780642304,
     "v": 0.07797270955165692,
     "family_factor": 1.0,
     "w": 3.973119153874029
    }
   ]
  },
  {
   "slug": "llama-3-1-405b",
   "name": "Llama 3.1-405B",
   "tier": "insufficient",
   "rank": null,
   "theta": -1.9780041594251618,
   "se": 0.1983708457336206,
   "si_iq": 70.32993760862257,
   "si_iq_low": 65.43557142229764,
   "si_iq_high": 75.2243037949475,
   "si_iq_display": 70,
   "domains": {
    "math": {
     "si_iq": 69.34950018191248,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.49773413897280966,
     "source_value_text": "0.49773413897280966",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "ZR7amdUBRr5Cke8Aoz4snr",
     "source_model_name": "Llama-3.1-405B-Instruct",
     "p": 0.49773413897280966,
     "p_star": 0.4977358490566038,
     "y": -0.009056665677797055,
     "v": 0.00301665139164121,
     "family_factor": 1.0,
     "w": 4.853584282206342
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.09722222222222222,
     "source_value_text": "0.09722222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "2fQJP3brRApfBdQq7Zy3bm",
     "source_model_name": "Llama-3.1-405B-Instruct",
     "p": 0.09631854076298521,
     "p_star": 0.10509422465944206,
     "y": -2.1418611083197012,
     "v": 0.22827464677771483,
     "family_factor": 1.0,
     "w": 1.5231148823337728
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.5091540404040404,
     "source_value_text": "0.5091540404040404",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "S5QYXSvQBRSbUbXSnAGbMm",
     "source_model_name": "Llama-3.1-405B-Instruct",
     "p": 0.3455387205387206,
     "p_star": 0.34631490787269686,
     "y": -0.6352772254917405,
     "v": 0.04334432858611544,
     "family_factor": 1.0,
     "w": 4.02771616348098
    }
   ]
  },
  {
   "slug": "qwen-turbo",
   "name": "Qwen-Turbo",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.035799743444162,
   "se": 0.2066806805683288,
   "si_iq": 69.46300384833756,
   "si_iq_low": 64.3636106860045,
   "si_iq_high": 74.56239701067064,
   "si_iq_display": 69,
   "domains": {
    "math": {
     "si_iq": 70.47089712459575,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.5623111782477341,
     "source_value_text": "0.5623111782477341",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-07",
     "source_row_id": "jWV936hYKg6rYcPEynzEEt",
     "source_model_name": "qwen-turbo-2024-11-01",
     "p": 0.5623111782477341,
     "p_star": 0.5622641509433962,
     "y": 0.25035611483909437,
     "v": 0.0030641055311270544,
     "family_factor": 1.0,
     "w": 4.851349530695648
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.06111111111111111,
     "source_value_text": "0.06111111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-07",
     "source_row_id": "G5gxbTH33S7LXA29o5fgmv",
     "source_model_name": "qwen-turbo-2024-11-01",
     "p": 0.06017128239350461,
     "p_star": 0.06973277625451538,
     "y": -2.5908014274457947,
     "v": 0.3325386039345715,
     "family_factor": 1.0,
     "w": 1.1559661853341374
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.41792929292929293,
     "source_value_text": "0.41792929292929293",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-07",
     "source_row_id": "9Ke5At9bYuf56SmKJJ7Sz7",
     "source_model_name": "qwen-turbo-2024-11-01",
     "p": 0.2239057239057239,
     "p_star": 0.22529313232830822,
     "y": -1.235082357910586,
     "v": 0.07103088605665964,
     "family_factor": 1.0,
     "w": 3.3757076426439108
    }
   ]
  },
  {
   "slug": "gpt-4-turbo-apr-2024",
   "name": "GPT-4 Turbo (Apr 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.107066677915254,
   "se": 0.18742078264102574,
   "si_iq": 68.39399983127119,
   "si_iq_low": 63.76980247111787,
   "si_iq_high": 73.01819719142452,
   "si_iq_display": 68,
   "domains": {
    "math": {
     "si_iq": 68.10039160218562,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "frontiermath_t13",
     "score": 0.007017543859649123,
     "source_value_text": "0.007017543859649123",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "bC2dbN4x2GWWmnnfseKxgQ",
     "source_model_name": "gpt-4-turbo-2024-04-09",
     "p": 0.007017543859649123,
     "p_star": 0.008741258741258742,
     "y": -4.730921391293651,
     "v": 0.4021164021164021,
     "family_factor": 1.0,
     "w": 0.9957850368809273
    },
    {
     "benchmark": "math_level_5",
     "score": 0.46733383685800606,
     "source_value_text": "0.46733383685800606",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-27",
     "source_row_id": "AZAJomaSEfZtqYqXUre9fS",
     "source_model_name": "gpt-4-turbo-2024-04-09",
     "p": 0.46733383685800606,
     "p_star": 0.46735849056603773,
     "y": -0.13075199876412977,
     "v": 0.0030295008802913833,
     "family_factor": 1.0,
     "w": 4.852978959695664
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.06666666666666667,
     "source_value_text": "0.06666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-27",
     "source_row_id": "MZABVPEY8VCPAyCZ4iir68",
     "source_model_name": "gpt-4-turbo-2024-04-09",
     "p": 0.0657323990657324,
     "p_star": 0.07517299908604257,
     "y": -2.5098145822085716,
     "v": 0.30996978174058354,
     "family_factor": 1.0,
     "w": 1.219602083541818
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4659090909090909,
     "source_value_text": "0.4659090909090909",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-27",
     "source_row_id": "TaCoN7eyPQEfDWXqs2MpcF",
     "source_model_name": "gpt-4-turbo-2024-04-09",
     "p": 0.28787878787878785,
     "p_star": 0.2889447236180904,
     "y": -0.9005147692799877,
     "v": 0.052409573366642856,
     "family_factor": 1.0,
     "w": 3.788149631524313
    }
   ]
  },
  {
   "slug": "mistral-large-2-jul-2024",
   "name": "Mistral Large 2 (Jul 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.1213248765211383,
   "se": 0.2004556310507329,
   "si_iq": 68.18012685218292,
   "si_iq_low": 63.23432315383809,
   "si_iq_high": 73.12593055052776,
   "si_iq_display": 68,
   "domains": {
    "math": {
     "si_iq": 67.20209861421915,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.4481684290030212,
     "source_value_text": "0.4481684290030212",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "div9uE9eovqykqx883kSpE",
     "source_model_name": "mistral-large-2407",
     "p": 0.4481684290030212,
     "p_star": 0.4482075471698113,
     "y": -0.20791558425610454,
     "v": 0.0030493080993395883,
     "family_factor": 1.0,
     "w": 4.852046163357057
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.08472222222222223,
     "source_value_text": "0.08472222222222223",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "bHLfPfZj8HgD9Gef75NtrM",
     "source_model_name": "mistral-large-2407",
     "p": 0.0838060282504727,
     "p_star": 0.09285372328850591,
     "y": -2.2792783253950524,
     "v": 0.2551978553765335,
     "family_factor": 1.0,
     "w": 1.40766615685212
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.49021464646464646,
     "source_value_text": "0.49021464646464646",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "ZQPNnicTuhuscJvni85PFY",
     "source_model_name": "mistral-large-2407",
     "p": 0.3202861952861953,
     "p_star": 0.3211892797319933,
     "y": -0.74831172036842,
     "v": 0.046731843931692836,
     "family_factor": 1.0,
     "w": 3.9347305514568203
    }
   ]
  },
  {
   "slug": "mistral-small-3-1",
   "name": "Mistral Small 3.1",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.1497335340093753,
   "se": 0.2052467194837669,
   "si_iq": 67.75399698985937,
   "si_iq_low": 62.68998367691309,
   "si_iq_high": 72.81801030280565,
   "si_iq_display": 68,
   "domains": {
    "math": {
     "si_iq": 67.0373994475714,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.4677114803625378,
     "source_value_text": "0.4677114803625378",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-18",
     "source_row_id": "Kas7Y5PBsT7Li5Wm6Y8mj8",
     "source_model_name": "mistral-small-2503",
     "p": 0.4677114803625378,
     "p_star": 0.46773584905660376,
     "y": -0.129236178966806,
     "v": 0.003029202836617376,
     "family_factor": 1.0,
     "w": 4.852992998430694
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.058333333333333334,
     "source_value_text": "0.058333333333333334",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-18",
     "source_row_id": "JxqtHWrwCtYoQYBB3jVqB9",
     "source_model_name": "mistral-small-2503",
     "p": 0.05739072405739072,
     "p_star": 0.06701266483875179,
     "y": -2.6335099974655636,
     "v": 0.3452260095095115,
     "family_factor": 1.0,
     "w": 1.1230251362691746
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.47474747474747475,
     "source_value_text": "0.47474747474747475",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-18",
     "source_row_id": "S8bBDAbucsFceirHxeEDvu",
     "source_model_name": "mistral-small-2503",
     "p": 0.2996632996632997,
     "p_star": 0.30067001675041877,
     "y": -0.8441093363625766,
     "v": 0.050140446599604246,
     "family_factor": 1.0,
     "w": 3.845401304348776
    }
   ]
  },
  {
   "slug": "openhands-lm-32b-v0-1",
   "name": "openhands-lm-32b-v0.1",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.172010137751339,
   "se": 0.6445995521379786,
   "si_iq": 67.41984793372991,
   "si_iq_low": 51.515765657744474,
   "si_iq_high": 83.32393020971536,
   "si_iq_display": 67,
   "domains": {},
   "inputs": [
    {
     "benchmark": "aider_polyglot",
     "score": 0.102,
     "source_value_text": "10.2",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2025-04-19",
     "source_row_id": "2025-04-19-14-43-04--o4-mini-patch",
     "source_model_name": "openhands-lm-32b-v0.1",
     "p": 0.102,
     "p_star": 0.10376106194690266,
     "y": -2.1561162747564113,
     "v": 0.04737044052930678,
     "family_factor": 1.0,
     "w": 1.3508696850281172
    }
   ]
  },
  {
   "slug": "mistral-small-3",
   "name": "Mistral Small 3",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.1786478213340135,
   "se": 0.2037606802142141,
   "si_iq": 67.32028267998979,
   "si_iq_low": 62.29293413159373,
   "si_iq_high": 72.34763122838586,
   "si_iq_display": 67,
   "domains": {
    "math": {
     "si_iq": 66.57514671976456,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.4481684290030212,
     "source_value_text": "0.4481684290030212",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-30",
     "source_row_id": "NbsnvBsMoMizozbPZY8LLb",
     "source_model_name": "mistral-small-2501",
     "p": 0.4481684290030212,
     "p_star": 0.4482075471698113,
     "y": -0.20791558425610454,
     "v": 0.0030493080993395883,
     "family_factor": 1.0,
     "w": 4.852046163357057
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.06666666666666667,
     "source_value_text": "0.06666666666666667",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "LEBmfabfasGXFwRwhN9j35",
     "source_model_name": "mistral-small-3-2501",
     "p": 0.0657323990657324,
     "p_star": 0.07517299908604257,
     "y": -2.5098145822085716,
     "v": 0.30996978174058354,
     "family_factor": 1.0,
     "w": 1.219602083541818
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.47285353535353536,
     "source_value_text": "0.47285353535353536",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "YJPwhEJa6qQWB23HQjByxt",
     "source_model_name": "mistral-small-3-2501",
     "p": 0.29713804713804715,
     "p_star": 0.2981574539363484,
     "y": -0.8560873696300526,
     "v": 0.050605185635356785,
     "family_factor": 1.0,
     "w": 3.833535125327612
    }
   ]
  },
  {
   "slug": "claude-3-5-haiku",
   "name": "Claude 3.5 Haiku",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.1792027835129337,
   "se": 0.2039563414676336,
   "si_iq": 67.311958247306,
   "si_iq_low": 62.279782185979954,
   "si_iq_high": 72.34413430863204,
   "si_iq_display": 67,
   "domains": {
    "math": {
     "si_iq": 66.46292191745663,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.46355740181268884,
     "source_value_text": "0.46355740181268884",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-12",
     "source_row_id": "GSvi9Zf5aK3t5TfCPqNRHy",
     "source_model_name": "claude-3-5-haiku-20241022",
     "p": 0.46355740181268884,
     "p_star": 0.46358490566037736,
     "y": -0.14591873912982073,
     "v": 0.003032675561694204,
     "family_factor": 1.0,
     "w": 4.852829427889684
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.043055555555555555,
     "source_value_text": "0.043055555555555555",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "cqhrR5KnwpcuAVpHkZGQFd",
     "source_model_name": "claude-3-5-haiku-20241022",
     "p": 0.04209765320876432,
     "p_star": 0.052052052052052045,
     "y": -2.902055374604651,
     "v": 0.4392856638070697,
     "family_factor": 1.0,
     "w": 0.9271524046648416
    },
    {
     "benchmark": "aider_polyglot",
     "score": 0.28,
     "source_value_text": "28.0",
     "source_url": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_snapshot": "https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml@sha256:85a50b25953512d1",
     "source_sha256": "85a50b25953512d18ba4bb0c23c0b8e626fcf9a5b52d287644b8a0b44b9535de",
     "verify_url": "https://aider.chat/docs/leaderboards/",
     "retrieved_at": "2026-10-18T12:17:28Z",
     "eval_date": "2024-12-21",
     "source_row_id": "2024-12-21-21-46-27--polyglot-haiku-diff",
     "source_model_name": "claude-3-5-haiku-20241022",
     "p": 0.28,
     "p_star": 0.2809734513274337,
     "y": -0.939638095871146,
     "v": 0.02180496668685645,
     "family_factor": 1.0,
     "w": 1.4202350249545832
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3813131313131313,
     "source_value_text": "0.3813131313131313",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-12",
     "source_row_id": "JpLxrpvthx7A75sbaHZ9Et",
     "source_model_name": "claude-3-5-haiku-20241022",
     "p": 0.1750841750841751,
     "p_star": 0.1767169179229481,
     "y": -1.5387509866710998,
     "v": 0.0991896950889681,
     "family_factor": 1.0,
     "w": 2.898494668269622
    }
   ]
  },
  {
   "slug": "gemini-1-5-pro-may-2024",
   "name": "Gemini 1.5 Pro (May 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.2810420575663373,
   "se": 0.20394972807291112,
   "si_iq": 65.78436913650495,
   "si_iq_low": 60.75235624621034,
   "si_iq_high": 70.81638202679954,
   "si_iq_display": 66,
   "domains": {
    "math": {
     "si_iq": 65.09619089658676,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.4074773413897281,
     "source_value_text": "0.4074773413897281",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "PxLmyq7PFfARAuqxg5oPtE",
     "source_model_name": "gemini-1.5-pro-001",
     "p": 0.4074773413897281,
     "p_star": 0.4075471698113208,
     "y": -0.3741145782240883,
     "v": 0.0031233781552252892,
     "family_factor": 1.0,
     "w": 4.848561101706547
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.06805555555555555,
     "source_value_text": "0.06805555555555555",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "3S6fjGAMKWKK3zcdxkmh9H",
     "source_model_name": "gemini-1.5-pro-001",
     "p": 0.06712267823378934,
     "p_star": 0.07653305479392436,
     "y": -2.4904122697252604,
     "v": 0.3048385598509223,
     "family_factor": 1.0,
     "w": 1.235060218038815
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4586489898989899,
     "source_value_text": "0.4586489898989899",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "PKdqpKZ9tqDWyWJ7GksBWz",
     "source_model_name": "gemini-1.5-pro-001",
     "p": 0.27819865319865317,
     "p_star": 0.27931323283082077,
     "y": -0.9478707502959157,
     "v": 0.05448029748279147,
     "family_factor": 1.0,
     "w": 3.737371552213256
    }
   ]
  },
  {
   "slug": "claude-3-opus",
   "name": "Claude 3 Opus",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.3066798415433167,
   "se": 0.20278934783066105,
   "si_iq": 65.39980237685025,
   "si_iq_low": 60.39641932780044,
   "si_iq_high": 70.40318542590006,
   "si_iq_display": 65,
   "domains": {
    "math": {
     "si_iq": 63.20782464428968,
     "n": 2
    },
    "knowledge": {
     "si_iq": 70.66748864327062,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "chess_puzzles",
     "score": 0.03,
     "source_value_text": "0.03",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#chess_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/chess-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-10-13",
     "source_row_id": "WAbi8sZpyNAZoNN3Gmg22y",
     "source_model_name": "claude-3-opus-20240229",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 22.969328441965256,
     "family_factor": 1.0,
     "w": 0.03065138124698309
    },
    {
     "benchmark": "math_level_5",
     "score": 0.37481117824773413,
     "source_value_text": "0.37481117824773413",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "6SNzvpd6kXXxqpJoaHsSDd",
     "source_model_name": "claude-3-opus-20240229",
     "p": 0.37481117824773413,
     "p_star": 0.3749056603773585,
     "y": -0.5112281597480789,
     "v": 0.003218019450606425,
     "family_factor": 1.0,
     "w": 4.84411542346313
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.04722222222222222,
     "source_value_text": "0.04722222222222222",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "mYb9MGQD39RS8VdDyMqujr",
     "source_model_name": "claude-3-opus-20240229",
     "p": 0.04626849071293516,
     "p_star": 0.05613221917569744,
     "y": -2.8222761291204934,
     "v": 0.40855447042846404,
     "family_factor": 1.0,
     "w": 0.983178851183322
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4715909090909091,
     "source_value_text": "0.4715909090909091",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "hTnDa4gn8RYduCEYqoNywe",
     "source_model_name": "claude-3-opus-20240229",
     "p": 0.29545454545454547,
     "p_star": 0.2964824120603015,
     "y": -0.8641049787035847,
     "v": 0.050921328025608406,
     "family_factor": 1.0,
     "w": 3.8255048291892892
    },
    {
     "benchmark": "simpleqa_verified",
     "score": 0.126,
     "source_value_text": "0.126",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#simpleqa_verified.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/simple-qa-verified",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-31",
     "source_row_id": "NxVp4VF8uQbL5S6hx6HFRB",
     "source_model_name": "claude-3-opus-20240229",
     "p": 0.126,
     "p_star": 0.12637362637362637,
     "y": -1.9334099862910819,
     "v": 0.009039609308085705,
     "family_factor": 1.0,
     "w": 1.6667856819907798
    }
   ]
  },
  {
   "slug": "qwen3-1-7b",
   "name": "Qwen3-1.7B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.358800870617911,
   "se": 0.32324535865240533,
   "si_iq": 64.61798694073133,
   "si_iq_low": 56.64261562331868,
   "si_iq_high": 72.59335825814398,
   "si_iq_display": 65,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.08055555555555556,
     "source_value_text": "0.08055555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "bbqokudairnKtbyjBjuWCx",
     "source_model_name": "qwen3-1.7b_none",
     "p": 0.07963519074630186,
     "p_star": 0.08877355616486052,
     "y": -2.328702617888719,
     "v": 0.26586218661689354,
     "family_factor": 1.0,
     "w": 1.3666348102914683
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.380050505050505,
     "source_value_text": "0.380050505050505",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "F3CtjUceBrMi9iYmjULx7J",
     "source_model_name": "qwen3-1.7b",
     "p": 0.17340067340067336,
     "p_star": 0.17504187604690116,
     "y": -1.5503073892072778,
     "v": 0.10056053596697886,
     "family_factor": 1.0,
     "w": 2.8786833182609923
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.2841,
     "source_value_text": "28.41%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "71",
     "source_model_name": "Qwen3-1.7B (FC)",
     "p": 0.2841,
     "p_star": 0.28623762376237627,
     "y": -0.9137277823882325,
     "v": 0.04798183829842199,
     "family_factor": 1.0,
     "w": 4.778334891073507
    }
   ]
  },
  {
   "slug": "qwen3-0-6b",
   "name": "Qwen3-0.6B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.3876099150615193,
   "se": 0.7642362549598668,
   "si_iq": 64.18585127407721,
   "si_iq_low": 45.32999536034086,
   "si_iq_high": 83.04170718781356,
   "si_iq_display": 64,
   "domains": {},
   "inputs": [
    {
     "benchmark": "bfcl_overall",
     "score": 0.23929999999999998,
     "source_value_text": "23.93%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "92",
     "source_model_name": "Qwen3-0.6B (FC)",
     "p": 0.23929999999999998,
     "p_star": 0.24188118811881187,
     "y": -1.142393469855383,
     "v": 0.05345863752857298,
     "family_factor": 1.0,
     "w": 4.607800463853909
    }
   ]
  },
  {
   "slug": "qwen2-72b",
   "name": "Qwen2-72B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.420030415365081,
   "se": 0.2296907360590802,
   "si_iq": 63.699543769523785,
   "si_iq_low": 58.032427879977945,
   "si_iq_high": 69.36665965906963,
   "si_iq_display": 64,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.39067220543806647,
     "source_value_text": "0.39067220543806647",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "9mWoY9fM2ifKvDg3xaug6h",
     "source_model_name": "qwen2-72b-instruct",
     "p": 0.39067220543806647,
     "p_star": 0.39075471698113207,
     "y": -0.444140909362691,
     "v": 0.00316781509434583,
     "family_factor": 1.0,
     "w": 4.846472706073648
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4078282828282828,
     "source_value_text": "0.4078282828282828",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "Pex6SpYJX8ZPySncfNNy7H",
     "source_model_name": "qwen2-72b-instruct",
     "p": 0.21043771043771042,
     "p_star": 0.211892797319933,
     "y": -1.3135536508578596,
     "v": 0.07704030860830226,
     "family_factor": 1.0,
     "w": 3.2611232646854473
    }
   ]
  },
  {
   "slug": "llama-3-1-70b",
   "name": "Llama 3.1-70B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.455914672419969,
   "se": 0.21139995456671873,
   "si_iq": 63.16127991370047,
   "si_iq_low": 57.94544900066718,
   "si_iq_high": 68.37711082673374,
   "si_iq_display": 63,
   "domains": {
    "math": {
     "si_iq": 62.34139362320302,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.36678625377643503,
     "source_value_text": "0.36678625377643503",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "6JiXiQ67iyiC7cFFRiogvs",
     "source_model_name": "Llama-3.1-70B-Instruct",
     "p": 0.36678625377643503,
     "p_star": 0.3668867924528302,
     "y": -0.5455959160024921,
     "v": 0.0032467046059364776,
     "family_factor": 1.0,
     "w": 4.842769577085862
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.03611111111111111,
     "source_value_text": "0.03611111111111111",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "X2tQXGELXtEbc2VX6gARd7",
     "source_model_name": "Llama-3.1-70B-Instruct",
     "p": 0.03514625736847959,
     "p_star": 0.045251773512643076,
     "y": -3.0492058055088695,
     "v": 0.5031234617569382,
     "family_factor": 1.0,
     "w": 0.8290176584135315
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.44191919191919193,
     "source_value_text": "0.44191919191919193",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "MEwMcmSV32JHrsNoAq4BFL",
     "source_model_name": "Llama-3.1-70B-Instruct",
     "p": 0.2558922558922559,
     "p_star": 0.2571189279731993,
     "y": -1.0609972347223824,
     "v": 0.06011134385882739,
     "family_factor": 1.0,
     "w": 3.6059298190556963
    }
   ]
  },
  {
   "slug": "gemma-3-4b",
   "name": "Gemma 3 4B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.471529321901024,
   "se": 0.38830867309479,
   "si_iq": 62.92706017148464,
   "si_iq_low": 53.346394058864774,
   "si_iq_high": 72.5077262841045,
   "si_iq_display": 63,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.075,
     "source_value_text": "0.075",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "KAPGpH2CLMafAt8MnAQJT3",
     "source_model_name": "gemma-3-4b-it",
     "p": 0.07407407407407407,
     "p_star": 0.08333333333333333,
     "y": -2.3978952727983707,
     "v": 0.2817424745591098,
     "family_factor": 1.0,
     "w": 1.3097835145996544
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.23232323232323232,
     "source_value_text": "0.23232323232323232",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "McJyXLHBzx5VjAqXjmrrsb",
     "source_model_name": "gemma-3-4b-it",
     "p": 0.0,
     "p_star": 0.002512562814070352,
     "y": -5.983936280687191,
     "v": 266.65994962216627,
     "family_factor": 0.5,
     "w": 0.0010821532055456109
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.271044,
     "source_value_text": "0.271044",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-15",
     "source_row_id": "google/gemma-3-4b-it",
     "source_model_name": "google/gemma-3-4b-it",
     "p": 0.028058666666666676,
     "p_star": 0.030430231155778906,
     "y": -3.4614158756394944,
     "v": 2.0257631453718603,
     "family_factor": 0.5,
     "w": 0.13239473269671628
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.1962,
     "source_value_text": "19.62%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "101",
     "source_model_name": "Gemma-3-4b-it (Prompt)",
     "p": 0.1962,
     "p_star": 0.19920792079207922,
     "y": -1.3912522294806775,
     "v": 0.06145127258211364,
     "family_factor": 1.0,
     "w": 4.379691592873107
    }
   ]
  },
  {
   "slug": "llama-3-2-3b",
   "name": "Llama 3.2 3B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.603777483665251,
   "se": 0.7704324366358136,
   "si_iq": 60.94333774502124,
   "si_iq_low": 41.93460461806877,
   "si_iq_high": 79.9520708719737,
   "si_iq_display": 61,
   "domains": {},
   "inputs": [
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.17340049999999999,
     "source_value_text": "0.1734",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-10-13",
     "source_row_id": "meta-llama/llama-3.2-3b-instruct",
     "source_model_name": "meta-llama/llama-3.2-3b-instruct",
     "p": 0.0,
     "p_star": 0.002512562814070352,
     "y": -5.983936280687191,
     "v": 266.65994962216627,
     "family_factor": 1.0,
     "w": 0.0021638631144260422
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.2195,
     "source_value_text": "21.95%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "98",
     "source_model_name": "Llama-3.2-3B-Instruct (FC)",
     "p": 0.2195,
     "p_star": 0.22227722772277228,
     "y": -1.252444750513367,
     "v": 0.05670710355709484,
     "family_factor": 1.0,
     "w": 4.512282884029692
    }
   ]
  },
  {
   "slug": "wizardlm-2-8x22b",
   "name": "WizardLM-2 8x22B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.7524526166795,
   "se": 0.22879424045400312,
   "si_iq": 58.7132107498075,
   "si_iq_low": 53.068213925991564,
   "si_iq_high": 64.35820757362345,
   "si_iq_display": 59,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.25736404833836857,
     "source_value_text": "0.25736404833836857",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "4bAYQuh4heJoTNhapVZLNB",
     "source_model_name": "WizardLM-2-8x22B",
     "p": 0.25736404833836857,
     "p_star": 0.25754716981132075,
     "y": -1.0587564532324434,
     "v": 0.003943942546229713,
     "family_factor": 1.0,
     "w": 4.810285118612101
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.43434343434343436,
     "source_value_text": "0.43434343434343436",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "MQJA3RUjsQzSubGJiukZ7A",
     "source_model_name": "WizardLM-2-8x22B",
     "p": 0.2457912457912458,
     "p_star": 0.24706867671691796,
     "y": -1.1143076781318004,
     "v": 0.06313892770511073,
     "family_factor": 1.0,
     "w": 3.5390098323635044
    }
   ]
  },
  {
   "slug": "gemini-1-5-flash-may-2024",
   "name": "Gemini 1.5 Flash (May 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.8111530307025294,
   "se": 0.21301637985589625,
   "si_iq": 57.83270453946206,
   "si_iq_low": 52.576991872389705,
   "si_iq_high": 63.088417206534416,
   "si_iq_display": 58,
   "domains": {
    "math": {
     "si_iq": 57.08355687925986,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.2512273413897281,
     "source_value_text": "0.2512273413897281",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "CPpd4hqQHtZ5pUejBELwKb",
     "source_model_name": "gemini-1.5-flash-001",
     "p": 0.2512273413897281,
     "p_star": 0.25141509433962267,
     "y": -1.0910792963605642,
     "v": 0.004007041262793026,
     "family_factor": 1.0,
     "w": 4.807366827565621
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.03888888888888889,
     "source_value_text": "0.03888888888888889",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "U9GVBhYjRzU55YVjna5mMT",
     "source_model_name": "gemini-1.5-flash-001",
     "p": 0.03792681570459348,
     "p_star": 0.04797188492840667,
     "y": -2.987979458351033,
     "v": 0.47536719430633745,
     "family_factor": 1.0,
     "w": 0.8690102684821993
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.40372474747474746,
     "source_value_text": "0.40372474747474746",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "Hc2ycMP6DyCZxCPjKbZFQU",
     "source_model_name": "gemini-1.5-flash-001",
     "p": 0.20496632996632994,
     "p_star": 0.20644891122278056,
     "y": -1.3464649434738367,
     "v": 0.0797953431781908,
     "family_factor": 1.0,
     "w": 3.2111525192141825
    }
   ]
  },
  {
   "slug": "gemma-2-27b",
   "name": "Gemma 2 27B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.856704052746315,
   "se": 0.22351907972114,
   "si_iq": 57.149439208805276,
   "si_iq_low": 51.634595423470735,
   "si_iq_high": 62.66428299413982,
   "si_iq_display": 57,
   "domains": {
    "math": {
     "si_iq": 57.3748522588567,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.2788897280966767,
     "source_value_text": "0.2788897280966767",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "PM3GCQcVK7t2MujNp4F4kH",
     "source_model_name": "gemma-2-27b-it",
     "p": 0.2788897280966767,
     "p_star": 0.27905660377358493,
     "y": -0.9491459847361,
     "v": 0.003748545235672262,
     "family_factor": 1.0,
     "w": 4.819344684440771
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.013888888888888888,
     "source_value_text": "0.013888888888888888",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-07",
     "source_row_id": "jD6rJdvfNPErKEz9qkpssj",
     "source_model_name": "gemma-2-27b-it",
     "p": 0.012901790679568455,
     "p_star": 0.023490882186534355,
     "y": -3.7273717337123635,
     "v": 0.9665939523974955,
     "family_factor": 1.0,
     "w": 0.46878195669129513
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3648989898989899,
     "source_value_text": "0.3648989898989899",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "ZUJxsJDpHnLXxNiDcvj22W",
     "source_model_name": "gemma-2-27b-it",
     "p": 0.1531986531986532,
     "p_star": 0.15494137353433834,
     "y": -1.6963591952752841,
     "v": 0.12033767676014484,
     "family_factor": 1.0,
     "w": 2.6202975255027208
    }
   ]
  },
  {
   "slug": "gpt-4-jun-2023",
   "name": "GPT-4 (Jun 2023)",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.8671979343579923,
   "se": 0.2273451135876993,
   "si_iq": 56.99203098463011,
   "si_iq_low": 51.38278819265239,
   "si_iq_high": 62.60127377660784,
   "si_iq_display": 57,
   "domains": {
    "math": {
     "si_iq": 54.79048682172554,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.12,
     "source_value_text": "0.12",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "CvujZuqfj5r7qsa52Smyx9",
     "source_model_name": "gpt-4-0613",
     "p": 0.03062348534919585,
     "p_star": 0.03527077757346124,
     "y": -3.30879267312414,
     "v": 1.1176837657418708,
     "family_factor": 1.0,
     "w": 0.5806982084184594
    },
    {
     "benchmark": "math_level_5",
     "score": 0.22970166163141995,
     "source_value_text": "0.22970166163141995",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "WsSrH8oHBm7m7vq9yTRqSC",
     "source_model_name": "gpt-4-0613",
     "p": 0.22970166163141995,
     "p_star": 0.2299056603773585,
     "y": -1.2088439738261498,
     "v": 0.0042595393377777594,
     "family_factor": 1.0,
     "w": 4.7957242394876785
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.011111111111111112,
     "source_value_text": "0.011111111111111112",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-23",
     "source_row_id": "hGVxg4EhSSJSCdH88m9soq",
     "source_model_name": "gpt-4-0613",
     "p": 0.010121232343454568,
     "p_star": 0.02077077077077077,
     "y": -3.8532190144138143,
     "v": 1.095975963508547,
     "family_factor": 1.0,
     "w": 0.41806860276120145
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.30650252525252525,
     "source_value_text": "0.30650252525252525",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "fu7pWqbSC4MUBdwv3GFNa5",
     "source_model_name": "gpt-4-0613",
     "p": 0.07533670033670033,
     "p_star": 0.07747068676716917,
     "y": -2.4772195217240185,
     "v": 0.3709699536491013,
     "family_factor": 1.0,
     "w": 1.2258749517167369
    }
   ]
  },
  {
   "slug": "gemini-1-5-flash-8b",
   "name": "Gemini 1.5 Flash 8B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.868508911591862,
   "se": 0.41657676469839117,
   "si_iq": 56.97236632612207,
   "si_iq_low": 46.694246960303964,
   "si_iq_high": 67.25048569194018,
   "si_iq_display": 57,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.04583333333333333,
     "source_value_text": "0.04583333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "jGY5Ee5P9dyStA4Fw5Pa6q",
     "source_model_name": "gemini-1.5-flash-8b-001",
     "p": 0.044878211544878206,
     "p_star": 0.05477216346781564,
     "y": -2.8482438963142154,
     "v": 0.41827878948399044,
     "family_factor": 1.0,
     "w": 0.9647317431180443
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.32954545454545453,
     "source_value_text": "0.32954545454545453",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-12",
     "source_row_id": "gFT36W4KU3wggLQ9nNCctg",
     "source_model_name": "gemini-1.5-flash-8b-001",
     "p": 0.10606060606060604,
     "p_star": 0.10804020100502511,
     "y": -2.1109176737818536,
     "v": 0.2119577388615088,
     "family_factor": 1.0,
     "w": 1.8507323180911246
    }
   ]
  },
  {
   "slug": "llama-3-70b",
   "name": "Llama 3-70B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.8721159113509627,
   "se": 0.21208129698497355,
   "si_iq": 56.91826132973556,
   "si_iq_low": 51.68561978467174,
   "si_iq_high": 62.150902874799385,
   "si_iq_display": 57,
   "domains": {
    "math": {
     "si_iq": 55.95149564448461,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.225547583081571,
     "source_value_text": "0.225547583081571",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "dekbZbU3BtiQZNKG8Txaax",
     "source_model_name": "Meta-Llama-3-70B-Instruct",
     "p": 0.225547583081571,
     "p_star": 0.2257547169811321,
     "y": -1.2324396397213384,
     "v": 0.004314602860349102,
     "family_factor": 1.0,
     "w": 4.793192767741
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.043055555555555555,
     "source_value_text": "0.043055555555555555",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "6RD3A6J432TZzxrKYRxph2",
     "source_model_name": "Meta-Llama-3-70B-Instruct",
     "p": 0.04209765320876432,
     "p_star": 0.052052052052052045,
     "y": -2.902055374604651,
     "v": 0.4392856638070697,
     "family_factor": 1.0,
     "w": 0.9271524046648416
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.40561868686868685,
     "source_value_text": "0.40561868686868685",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "jrvutCoFFG4KxYtU7REdpe",
     "source_model_name": "Meta-Llama-3-70B-Instruct",
     "p": 0.20749158249158248,
     "p_star": 0.2089614740368509,
     "y": -1.331196771749991,
     "v": 0.07849905012382898,
     "family_factor": 1.0,
     "w": 3.234472501613338
    }
   ]
  },
  {
   "slug": "mistral-large",
   "name": "Mistral Large",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.9094899088159822,
   "se": 0.21986636926797995,
   "si_iq": 56.35765136776027,
   "si_iq_low": 50.93293021342156,
   "si_iq_high": 61.782372522098974,
   "si_iq_display": 56,
   "domains": {
    "math": {
     "si_iq": 55.78900801807882,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.24461858006042297,
     "source_value_text": "0.24461858006042297",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "gypQecfFNK2x4pNGDtGMDv",
     "source_model_name": "mistral-large-2402",
     "p": 0.24461858006042297,
     "p_star": 0.24481132075471698,
     "y": -1.126479829830826,
     "v": 0.004079146102086967,
     "family_factor": 1.0,
     "w": 4.804036338937394
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.019444444444444445,
     "source_value_text": "0.019444444444444445",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "ZVHvk3GTPUNTgjc5w3vkhW",
     "source_model_name": "mistral-large-2402",
     "p": 0.01846290735179624,
     "p_star": 0.028931105018061537,
     "y": -3.5134801038543024,
     "v": 0.783166385224738,
     "family_factor": 1.0,
     "w": 0.5661447359919227
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.38762626262626265,
     "source_value_text": "0.38762626262626265",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "dDeREdDJ5bVyci3APZxzWb",
     "source_model_name": "mistral-large-2402",
     "p": 0.18350168350168353,
     "p_star": 0.18509212730318259,
     "y": -1.4822213806682523,
     "v": 0.09284551989105407,
     "family_factor": 1.0,
     "w": 2.9938484934251695
    }
   ]
  },
  {
   "slug": "granite-4-0-1b",
   "name": "granite-4.0-1b",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.969513034359778,
   "se": 0.745821645534117,
   "si_iq": 55.45730448460333,
   "si_iq_low": 37.055788730452704,
   "si_iq_high": 73.85882023875395,
   "si_iq_display": 55,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.008333333333333333,
     "source_value_text": "0.008333333333333333",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "PiFfhBoFbnaoqX5z2gVvra",
     "source_model_name": "granite-4.0-1b",
     "p": 0.007340674007340674,
     "p_star": 0.01805065935500718,
     "y": -3.9963575056108858,
     "v": 1.2663520482998976,
     "family_factor": 1.0,
     "w": 0.36593790057411035
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.2398989898989899,
     "source_value_text": "0.2398989898989899",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "oWiE4CniV7k5adL5wDh5r8",
     "source_model_name": "granite-4.0-1b",
     "p": 0.0,
     "p_star": 0.002512562814070352,
     "y": -5.983936280687191,
     "v": 266.65994962216627,
     "family_factor": 1.0,
     "w": 0.0021643064110912218
    }
   ]
  },
  {
   "slug": "hermes-2-theta-llama-3-70b",
   "name": "Hermes 2 Theta Llama-3 70B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.976723990354797,
   "se": 0.2192225772692882,
   "si_iq": 55.349140144678046,
   "si_iq_low": 49.94030314800258,
   "si_iq_high": 60.75797714135351,
   "si_iq_display": 55,
   "domains": {
    "math": {
     "si_iq": 55.003077743593806,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.22686933534743203,
     "source_value_text": "0.22686933534743203",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "ZAVTwsDqrvbWbqSgeNdXFd",
     "source_model_name": "Hermes-2-Theta-Llama-3-70B",
     "p": 0.22686933534743203,
     "p_star": 0.2270754716981132,
     "y": -1.2248989723587427,
     "v": 0.004296837344960594,
     "family_factor": 1.0,
     "w": 4.7940092214518035
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.025,
     "source_value_text": "0.025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-04-01",
     "source_row_id": "63MnE4e4AXvbQ585MaWTFv",
     "source_model_name": "Hermes-2-Theta-Llama-3-70B",
     "p": 0.024024024024024024,
     "p_star": 0.03437132784958872,
     "y": -3.3355566388664633,
     "v": 0.6594133434652547,
     "family_factor": 1.0,
     "w": 0.6584029689529368
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3746843434343434,
     "source_value_text": "0.3746843434343434",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "DHdeZNynu4VtRp2VGkCGvd",
     "source_model_name": "Hermes-2-Theta-Llama-3-70B",
     "p": 0.16624579124579122,
     "p_star": 0.16792294807370184,
     "y": -1.6004198152452476,
     "v": 0.10681573185012537,
     "family_factor": 1.0,
     "w": 2.7916167886494168
    }
   ]
  },
  {
   "slug": "mixtral-8x22b",
   "name": "Mixtral 8x22B",
   "tier": "insufficient",
   "rank": null,
   "theta": -2.991098797140626,
   "se": 0.23749136640315036,
   "si_iq": 55.13351804289061,
   "si_iq_low": 49.273938682985296,
   "si_iq_high": 60.993097402795925,
   "si_iq_display": 55,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.24244712990936557,
     "source_value_text": "0.24244712990936557",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "cGMb2vs9NhfkwZJsQXzLmQ",
     "source_model_name": "open-mixtral-8x22b",
     "p": 0.24244712990936557,
     "p_star": 0.24264150943396226,
     "y": -1.1382516245587189,
     "v": 0.004103832542555178,
     "family_factor": 1.0,
     "w": 4.802897144018322
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.34059343434343436,
     "source_value_text": "0.34059343434343436",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "ifAM3DJBdm5eU9Y2DjaEvW",
     "source_model_name": "open-mixtral-8x22b",
     "p": 0.12079124579124582,
     "p_star": 0.12269681742043555,
     "y": -1.9671362233391703,
     "v": 0.17263795945653695,
     "family_factor": 1.0,
     "w": 2.117644477461933
    }
   ]
  },
  {
   "slug": "llama-3-1-8b",
   "name": "Llama 3.1-8B",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.024580292581884,
   "se": 0.23575995417371826,
   "si_iq": 54.63129561127174,
   "si_iq_low": 48.81443505633489,
   "si_iq_high": 60.4481561662086,
   "si_iq_display": 55,
   "domains": {
    "math": {
     "si_iq": 54.682053787158736,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.22875755287009064,
     "source_value_text": "0.22875755287009064",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "gyxR3YTcmh4UcKZkET5pPX",
     "source_model_name": "Llama-3.1-8B-Instruct",
     "p": 0.22875755287009064,
     "p_star": 0.2289622641509434,
     "y": -1.2141801117895283,
     "v": 0.004271856779064555,
     "family_factor": 1.0,
     "w": 4.795157729466929
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.016666666666666666,
     "source_value_text": "0.016666666666666666",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "6YAzFq89fwWiJ3uJdptCMr",
     "source_model_name": "Llama-3.1-8B-Instruct",
     "p": 0.01568234901568235,
     "p_star": 0.02621099360229795,
     "y": -3.6150157284012976,
     "v": 0.8650184894595339,
     "family_factor": 1.0,
     "w": 0.5181247877230093
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.26957070707070707,
     "source_value_text": "0.26957070707070707",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:df0a77c60270c77e",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "fxwRTtt8bLV4DNutwtMEox",
     "source_model_name": "Llama-3.1-8B-Instruct",
     "p": 0.026094276094276097,
     "p_star": 0.028475711892797323,
     "y": -3.529814759484249,
     "v": 2.2963369526309503,
     "family_factor": 0.5,
     "w": 0.12046516842210986
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.26941151269035535,
     "source_value_text": "0.26941151269035535",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-10-17",
     "source_row_id": "meta-llama/llama-3.1-8b-instruct",
     "source_model_name": "meta-llama/llama-3.1-8b-instruct",
     "p": 0.0258820169204738,
     "p_star": 0.028264519348009106,
     "y": -3.5374763433947036,
     "v": 2.3289148549128202,
     "family_factor": 0.5,
     "w": 0.11623421272741893
    }
   ]
  },
  {
   "slug": "mistral-7b-v0-3",
   "name": "Mistral 7B v0.3",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.0437360048806674,
   "se": 0.8444206460076561,
   "si_iq": 54.34395992678999,
   "si_iq_low": 33.50972976776583,
   "si_iq_high": 75.17819008581415,
   "si_iq_display": 54,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.002777777777777778,
     "source_value_text": "0.002777777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "j6Mo25oV9Y9jdGxCMHZfpU",
     "source_model_name": "Mistral-7B-Instruct-v0.3",
     "p": 0.0017795573351128907,
     "p_star": 0.012610436523480002,
     "y": -4.360539889442886,
     "v": 1.8435379036714543,
     "family_factor": 1.0,
     "w": 0.2572627984540314
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.1518308080808081,
     "source_value_text": "0.1518308080808081",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "YbQkMPC2GtNLhxqTEhhVsa",
     "source_model_name": "Mistral-7B-Instruct-v0.3",
     "p": 0.0,
     "p_star": 0.002512562814070352,
     "y": -5.983936280687191,
     "v": 266.65994962216627,
     "family_factor": 1.0,
     "w": 0.0021643064110912218
    }
   ]
  },
  {
   "slug": "granite-4-0-micro",
   "name": "granite-4.0-micro",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.059480596580597,
   "se": 0.5301081045951217,
   "si_iq": 54.107791051291045,
   "si_iq_low": 41.02853450715548,
   "si_iq_high": 67.1870475954266,
   "si_iq_display": 54,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.027777777777777776,
     "source_value_text": "0.027777777777777776",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "gVnaLSupMCiWmiScxfMLx3",
     "source_model_name": "granite-4.0-micro",
     "p": 0.026804582360137913,
     "p_star": 0.037091439265352306,
     "y": -3.2565722593592503,
     "v": 0.6115095255466259,
     "family_factor": 1.0,
     "w": 0.7027312805346758
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.2828282828282828,
     "source_value_text": "0.2828282828282828",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "SadaSwnSdMpYRstc8zvgjJ",
     "source_model_name": "granite-4.0-micro",
     "p": 0.04377104377104376,
     "p_star": 0.04606365159128977,
     "y": -3.0305727782147116,
     "v": 0.9371665735493658,
     "family_factor": 1.0,
     "w": 0.556661084066595
    }
   ]
  },
  {
   "slug": "claude-3-sonnet",
   "name": "Claude 3 Sonnet",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.0719286323996595,
   "se": 0.21759615861589293,
   "si_iq": 53.92107051400511,
   "si_iq_low": 48.552361835745316,
   "si_iq_high": 59.289779192264895,
   "si_iq_display": 54,
   "domains": {
    "math": {
     "si_iq": 52.30664437147375,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.18174093655589124,
     "source_value_text": "0.18174093655589124",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "FD2ztfjFUeqGyrtF8yuCUB",
     "source_model_name": "claude-3-sonnet-20240229",
     "p": 0.18174093655589124,
     "p_star": 0.1819811320754717,
     "y": -1.5029823904714315,
     "v": 0.00506601586155122,
     "family_factor": 1.0,
     "w": 4.758912726441113
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.025,
     "source_value_text": "0.025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "AeRCEiG87bMFpxbxbmjCyn",
     "source_model_name": "claude-3-sonnet-20240229",
     "p": 0.024024024024024024,
     "p_star": 0.03437132784958872,
     "y": -3.3355566388664633,
     "v": 0.6594133434652547,
     "family_factor": 1.0,
     "w": 0.6584029689529368
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.4059343434343434,
     "source_value_text": "0.4059343434343434",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "QLejPZXhjX6SQCQgzjNvCG",
     "source_model_name": "claude-3-sonnet-20240229",
     "p": 0.2079124579124579,
     "p_star": 0.20938023450586263,
     "y": -1.3286652482832544,
     "v": 0.07828718644067797,
     "family_factor": 1.0,
     "w": 3.2383161163504552
    }
   ]
  },
  {
   "slug": "gemma-2-9b",
   "name": "Gemma 2 9B",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.1394179821765946,
   "se": 0.24135337427319772,
   "si_iq": 52.90873026735108,
   "si_iq_low": 46.953864321049586,
   "si_iq_high": 58.86359621365258,
   "si_iq_display": 53,
   "domains": {
    "math": {
     "si_iq": 53.09690271407798,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.2100641993957704,
     "source_value_text": "0.2100641993957704",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "Hdcqs42VnPNVBquXttexhq",
     "source_model_name": "gemma-2-9b-it",
     "p": 0.2100641993957704,
     "p_star": 0.21028301886792453,
     "y": -1.3232202972741876,
     "v": 0.004541303724393199,
     "family_factor": 1.0,
     "w": 4.7827985895237335
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.005555555555555556,
     "source_value_text": "0.005555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-07",
     "source_row_id": "WNE7cveVN8rsi7DmsFsFVy",
     "source_model_name": "gemma-2-9b-it",
     "p": 0.0045601156712267825,
     "p_star": 0.015330547939243593,
     "y": -4.162458568004531,
     "v": 1.5007847472225642,
     "family_factor": 1.0,
     "w": 0.3123468041955817
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.2746212121212121,
     "source_value_text": "0.2746212121212121",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "fQjoHKyUEPAuwdrBGfL8SG",
     "source_model_name": "gemma-2-9b-it",
     "p": 0.0328282828282828,
     "p_star": 0.035175879396984897,
     "y": -3.311585222972469,
     "v": 1.5433673469387776,
     "family_factor": 1.0,
     "w": 0.3513214925835657
    }
   ]
  },
  {
   "slug": "granite-4-0-350m",
   "name": "granite-4.0-350m",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.1666275336725027,
   "se": 0.6246895891454843,
   "si_iq": 52.50058699491246,
   "si_iq_low": 37.08773945294786,
   "si_iq_high": 67.91343453687705,
   "si_iq_display": 53,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.002777777777777778,
     "source_value_text": "0.002777777777777778",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "aQYiADNH3qVzZkWUmQn6nZ",
     "source_model_name": "granite-4.0-350m",
     "p": 0.0017795573351128907,
     "p_star": 0.012610436523480002,
     "y": -4.360539889442886,
     "v": 1.8435379036714543,
     "family_factor": 1.0,
     "w": 0.2572627984540314
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.11237373737373738,
     "source_value_text": "0.11237373737373738",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "F6xZSehzKjpybEh8JkGwni",
     "source_model_name": "granite-4.0-350m",
     "p": 0.0,
     "p_star": 0.002512562814070352,
     "y": -5.983936280687191,
     "v": 266.65994962216627,
     "family_factor": 1.0,
     "w": 0.0021643064110912218
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.1898,
     "source_value_text": "18.98%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "103",
     "source_model_name": "Granite-4.0-350m (FC)",
     "p": 0.1898,
     "p_star": 0.19287128712871288,
     "y": -1.4314600907000803,
     "v": 0.06297191150481708,
     "family_factor": 1.0,
     "w": 4.338826087620914
    }
   ]
  },
  {
   "slug": "gpt-4-mar-2023",
   "name": "GPT-4 (Mar 2023)",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.1698886618996522,
   "se": 0.5052186973537629,
   "si_iq": 52.45167007150522,
   "si_iq_low": 39.98650514324832,
   "si_iq_high": 64.9168349997621,
   "si_iq_display": 52,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.005555555555555556,
     "source_value_text": "0.005555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-22",
     "source_row_id": "cLTgetxaaTCZoA9vwY4SdL",
     "source_model_name": "gpt-4-0314",
     "p": 0.0045601156712267825,
     "p_star": 0.015330547939243593,
     "y": -4.162458568004531,
     "v": 1.5007847472225642,
     "family_factor": 1.0,
     "w": 0.3123468041955817
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3573232323232323,
     "source_value_text": "0.3573232323232323",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-10-23",
     "source_row_id": "FkbLkW5ed8rnZGFJMevDFn",
     "source_model_name": "gpt-4-0314",
     "p": 0.14309764309764308,
     "p_star": 0.14489112227805695,
     "y": -1.7752462236668867,
     "v": 0.1331943647631749,
     "family_factor": 1.0,
     "w": 2.4758328520329607
    }
   ]
  },
  {
   "slug": "claude-2-1",
   "name": "Claude 2.1",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.2124523724809078,
   "se": 0.48396113739509267,
   "si_iq": 51.81321441278639,
   "si_iq_low": 39.87253322245336,
   "si_iq_high": 63.7538956031194,
   "si_iq_display": 52,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.019444444444444445,
     "source_value_text": "0.019444444444444445",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-07",
     "source_row_id": "2vg9qw9pd8zSyRMu9YNiVm",
     "source_model_name": "claude-2.1",
     "p": 0.01846290735179624,
     "p_star": 0.028931105018061537,
     "y": -3.5134801038543024,
     "v": 0.783166385224738,
     "family_factor": 1.0,
     "w": 0.5661447359919227
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.32954545454545453,
     "source_value_text": "0.32954545454545453",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "eMAisrJd7fAUHPfcPWXeXo",
     "source_model_name": "claude-2.1",
     "p": 0.10606060606060604,
     "p_star": 0.10804020100502511,
     "y": -2.1109176737818536,
     "v": 0.2119577388615088,
     "family_factor": 1.0,
     "w": 1.8507323180911246
    }
   ]
  },
  {
   "slug": "eurus-2-7b-prime",
   "name": "Eurus-2-7B-PRIME",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.259030488513632,
   "se": 0.6493266575716684,
   "si_iq": 51.11454267229552,
   "si_iq_low": 35.093829422094686,
   "si_iq_high": 67.13525592249636,
   "si_iq_display": 51,
   "domains": {},
   "inputs": [
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3390151515151515,
     "source_value_text": "0.3390151515151515",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "RJm4u2vXF6PUmThJGzAfHE",
     "source_model_name": "Eurus-2-7B-PRIME",
     "p": 0.11868686868686866,
     "p_star": 0.12060301507537687,
     "y": -1.9867321435755685,
     "v": 0.17744047619047626,
     "family_factor": 1.0,
     "w": 2.0809878829405086
    }
   ]
  },
  {
   "slug": "phi-3-medium-14b",
   "name": "phi-3-medium 14B",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.2835657776047196,
   "se": 0.25056168864639344,
   "si_iq": 50.74651333592921,
   "si_iq_low": 44.56445239867758,
   "si_iq_high": 56.92857427318083,
   "si_iq_display": 51,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.17560422960725075,
     "source_value_text": "0.17560422960725075",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-31",
     "source_row_id": "njA86GC9DzSXyiZWtUxXiD",
     "source_model_name": "Phi-3-medium-128k-instruct",
     "p": 0.17560422960725075,
     "p_star": 0.1758490566037736,
     "y": -1.5447277027391497,
     "v": 0.005203666147872157,
     "family_factor": 1.0,
     "w": 4.752686083175182
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.2758838383838384,
     "source_value_text": "0.2758838383838384",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-31",
     "source_row_id": "bDS2AGEf3AywbVcdDyAKZK",
     "source_model_name": "Phi-3-medium-128k-instruct",
     "p": 0.03451178451178453,
     "p_star": 0.03685092127303184,
     "y": -3.263327587439034,
     "v": 1.4150988142292478,
     "family_factor": 1.0,
     "w": 0.3810644320801822
    }
   ]
  },
  {
   "slug": "qwen2-5-7b",
   "name": "Qwen2.5-7B",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.2873574273749364,
   "se": 0.38876819974748655,
   "si_iq": 50.68963858937595,
   "si_iq_low": 41.09763466296417,
   "si_iq_high": 60.28164251578774,
   "si_iq_display": 51,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.025,
     "source_value_text": "0.025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "U8HHNLLLVHJ7sHCfwdiDBX",
     "source_model_name": "qwen2.5-7b-instruct",
     "p": 0.024024024024024024,
     "p_star": 0.03437132784958872,
     "y": -3.3355566388664633,
     "v": 0.6594133434652547,
     "family_factor": 1.0,
     "w": 0.6584029689529368
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3547979797979798,
     "source_value_text": "0.3547979797979798",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:1bcfa0042412d122",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "6jkd5nJzspGZJtvZynZZTD",
     "source_model_name": "qwen2.5-7b-instruct",
     "p": 0.1397306397306397,
     "p_star": 0.14154103852596311,
     "y": -1.8025491766494355,
     "v": 0.13805542437623886,
     "family_factor": 0.5,
     "w": 1.212638339795069
    },
    {
     "benchmark": "or_gpqa_diamond",
     "score": 0.3417510000000001,
     "source_value_text": "0.3417510000000001",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T13:21:32Z",
     "eval_date": "2026-08-01",
     "source_row_id": "qwen/qwen-2.5-7b-instruct",
     "source_model_name": "qwen/qwen-2.5-7b-instruct",
     "p": 0.12233466666666677,
     "p_star": 0.1242324824120604,
     "y": -1.9529459964187186,
     "v": 0.1692596540686339,
     "family_factor": 0.5,
     "w": 0.8912228330422307
    },
    {
     "benchmark": "or_tau2_airline",
     "score": 0.166667,
     "source_value_text": "0.166667",
     "source_url": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_snapshot": "https://openrouter.ai/api/v1/datasets/exports/benchmark-leaderboard/2026-10-18.csv",
     "source_sha256": "aa7b4c661b02ff153e48bf6cff39c6f09461b4b3bd56a680df9ef8a112128ee2",
     "verify_url": "https://openrouter.ai/benchmarks/tau2-bench-airline",
     "retrieved_at": "2026-10-18T12:17:25Z",
     "eval_date": "2026-08-01",
     "source_row_id": "qwen/qwen-2.5-7b-instruct",
     "source_model_name": "qwen/qwen-2.5-7b-instruct",
     "p": 0.166667,
     "p_star": 0.17320294117647062,
     "y": -1.5630952931277302,
     "v": 0.13423799800442854,
     "family_factor": 1.0,
     "w": 3.0187535208236316
    }
   ]
  },
  {
   "slug": "claude-3-haiku",
   "name": "Claude 3 Haiku",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.3216095679386584,
   "se": 0.22394942143185648,
   "si_iq": 50.175856480920125,
   "si_iq_low": 44.650394956322,
   "si_iq_high": 55.701318005518246,
   "si_iq_display": 50,
   "domains": {
    "math": {
     "si_iq": 49.322889337346055,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.1487915407854985,
     "source_value_text": "0.1487915407854985",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "QSnWVKUVj9six4jYj4HJD9",
     "source_model_name": "claude-3-haiku-20240307",
     "p": 0.1487915407854985,
     "p_star": 0.1490566037735849,
     "y": -1.742019487035657,
     "v": 0.005945718375480647,
     "family_factor": 1.0,
     "w": 4.719397892305165
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.018055555555555554,
     "source_value_text": "0.018055555555555554",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "ThMd6DNDTtyWxhPcb9Kq4y",
     "source_model_name": "claude-3-haiku-20240307",
     "p": 0.01707262818373929,
     "p_star": 0.02757104931017974,
     "y": -3.5630307302414406,
     "v": 0.8220037270315164,
     "family_factor": 1.0,
     "w": 0.5422971570947985
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3630050505050505,
     "source_value_text": "0.3630050505050505",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "T3FWdCCWBryVjxwTcoY5bK",
     "source_model_name": "claude-3-haiku-20240307",
     "p": 0.15067340067340065,
     "p_star": 0.15242881072026798,
     "y": -1.7156771627706155,
     "v": 0.12333104067456675,
     "family_factor": 1.0,
     "w": 2.585176997544772
    }
   ]
  },
  {
   "slug": "gpt-3-5-turbo-nov-2023",
   "name": "GPT-3.5 Turbo (Nov 2023)",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.3820375158758527,
   "se": 0.25023755250754254,
   "si_iq": 49.26943726186221,
   "si_iq_low": 43.09537367397859,
   "si_iq_high": 55.44350084974583,
   "si_iq_display": 49,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.15889350453172205,
     "source_value_text": "0.15889350453172205",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "cJWh887zSiTtnxm9XAJVkr",
     "source_model_name": "gpt-3.5-turbo-1106",
     "p": 0.15889350453172205,
     "p_star": 0.1591509433962264,
     "y": -1.664559081584749,
     "v": 0.005635454789168909,
     "family_factor": 1.0,
     "w": 4.733259311449155
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.2803030303030303,
     "source_value_text": "0.2803030303030303",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "enhRcQmfN6RFB2zu7R3Uxr",
     "source_model_name": "gpt-3.5-turbo-1106",
     "p": 0.040404040404040366,
     "p_star": 0.04271356783919594,
     "y": -3.109586031070486,
     "v": 1.0765332534125294,
     "family_factor": 1.0,
     "w": 0.4907215903290655
    }
   ]
  },
  {
   "slug": "ministral-3b",
   "name": "Ministral 3B",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.413775258299227,
   "se": 0.2543817085718334,
   "si_iq": 48.79337112551159,
   "si_iq_low": 42.51705956244337,
   "si_iq_high": 55.06968268857981,
   "si_iq_display": 49,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.14444864048338368,
     "source_value_text": "0.14444864048338368",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "YNhHxRT9Ee2uEWWJh9RXuP",
     "source_model_name": "ministral-3b-2410",
     "p": 0.14444864048338368,
     "p_star": 0.14471698113207548,
     "y": -1.776652449573593,
     "v": 0.006092939765779617,
     "family_factor": 1.0,
     "w": 4.7128489520965795
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.25252525252525254,
     "source_value_text": "0.25252525252525254",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "bJV4D8SEo9zMJPEYTTXJNZ",
     "source_model_name": "ministral-3b-2410",
     "p": 0.0033670033670033885,
     "p_star": 0.0058626465661641754,
     "y": -5.133274245554351,
     "v": 49.63361587263345,
     "family_factor": 1.0,
     "w": 0.011608853670889433
    }
   ]
  },
  {
   "slug": "claude-2",
   "name": "Claude 2",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.4883854140703554,
   "se": 0.22432394807279454,
   "si_iq": 47.67421878894467,
   "si_iq_low": 42.13951663969474,
   "si_iq_high": 53.208920938194595,
   "si_iq_display": 48,
   "domains": {
    "math": {
     "si_iq": 46.99274366533458,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.1172583081570997,
     "source_value_text": "0.1172583081570997",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "Gs4vxvDD5wmrSvyTkqx2YV",
     "source_model_name": "claude-2.0",
     "p": 0.1172583081570997,
     "p_star": 0.11754716981132075,
     "y": -2.015865638938433,
     "v": 0.007270303671771049,
     "family_factor": 1.0,
     "w": 4.661122257376237
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.025,
     "source_value_text": "0.025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-03-07",
     "source_row_id": "7LLTmqs4LC5GLVfJEqJWSC",
     "source_model_name": "claude-2.0",
     "p": 0.024024024024024024,
     "p_star": 0.03437132784958872,
     "y": -3.3355566388664633,
     "v": 0.6594133434652547,
     "family_factor": 1.0,
     "w": 0.6584029689529368
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3465909090909091,
     "source_value_text": "0.3465909090909091",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "mTa4f52zsEuxdrPy7WfQvX",
     "source_model_name": "claude-2.0",
     "p": 0.1287878787878788,
     "p_star": 0.1306532663316583,
     "y": -1.895195056476297,
     "v": 0.15632588842904532,
     "family_factor": 1.0,
     "w": 2.252407170918456
    }
   ]
  },
  {
   "slug": "gpt-3-5-turbo-jan-2024",
   "name": "GPT-3.5 Turbo (Jan 2024)",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.516959318033359,
   "se": 0.22988614513148378,
   "si_iq": 47.24561022949961,
   "si_iq_low": 41.57367304903809,
   "si_iq_high": 52.91754740996114,
   "si_iq_display": 47,
   "domains": {
    "math": {
     "si_iq": 47.14450537970277,
     "n": 3
    }
   },
   "inputs": [
    {
     "benchmark": "mystery_game_puzzles",
     "score": 0.03,
     "source_value_text": "0.03",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#mystery_game_puzzles.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/mystery-game-puzzles",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "UfmijCsx59sZ8xpcbcWDms",
     "source_model_name": "gpt-3.5-turbo-0125",
     "p": 0.0,
     "p_star": 0.0049504950495049506,
     "y": -5.303304908059076,
     "v": 42.81785608200461,
     "family_factor": 1.0,
     "w": 0.016475817893499955
    },
    {
     "benchmark": "frontiermath_t13",
     "score": 0.0,
     "source_value_text": "0.0",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#frontiermath_tiers_1_3_v2.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-27",
     "source_row_id": "FNaBAvmeTiRRFDW63KemZ7",
     "source_model_name": "gpt-3.5-turbo-0125",
     "p": 0.0,
     "p_star": 0.0017482517482517483,
     "y": -6.3473892096560105,
     "v": 1.9964973730297724,
     "family_factor": 1.0,
     "w": 0.2384930248099574
    },
    {
     "benchmark": "math_level_5",
     "score": 0.1163141993957704,
     "source_value_text": "0.1163141993957704",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "9tSgxGV3nzhTBpq7GcX7yx",
     "source_model_name": "gpt-3.5-turbo-0125",
     "p": 0.1163141993957704,
     "p_star": 0.11660377358490566,
     "y": -2.0249921905931654,
     "v": 0.007321297982081067,
     "family_factor": 1.0,
     "w": 4.658907499268995
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.022222222222222223,
     "source_value_text": "0.022222222222222223",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-07",
     "source_row_id": "7ZVhkukwaRXU2Sx2ttibPF",
     "source_model_name": "gpt-3.5-turbo-0125",
     "p": 0.02124346568791013,
     "p_star": 0.03165121643382513,
     "y": -3.4208157542008952,
     "v": 0.7158085929380985,
     "family_factor": 1.0,
     "w": 0.6128888618337203
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.27178030303030304,
     "source_value_text": "0.27178030303030304",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "eZaQhpbhbzbo3sbKGS5Efa",
     "source_model_name": "gpt-3.5-turbo-0125",
     "p": 0.02904040404040405,
     "p_star": 0.03140703517587941,
     "y": -3.4288125486951286,
     "v": 1.9087439688715941,
     "family_factor": 1.0,
     "w": 0.28741854518868853
    }
   ]
  },
  {
   "slug": "ministral-8b",
   "name": "Ministral 8B",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.525188068219838,
   "se": 0.24499174747118954,
   "si_iq": 47.12217897670243,
   "si_iq_low": 41.077544139777785,
   "si_iq_high": 53.16681381362707,
   "si_iq_display": 47,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.14935800604229607,
     "source_value_text": "0.14935800604229607",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "hqdiKcvEPSRyvenUVB9qxM",
     "source_model_name": "ministral-8b-2410",
     "p": 0.14935800604229607,
     "p_star": 0.14962264150943397,
     "y": -1.7375638010558003,
     "v": 0.005927167799228382,
     "family_factor": 1.0,
     "w": 4.720224380469484
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.27146464646464646,
     "source_value_text": "0.27146464646464646",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "DGEzZA6nvTne4MEGSuo3Tm",
     "source_model_name": "ministral-8b-2410",
     "p": 0.028619528619528618,
     "p_star": 0.030988274706867668,
     "y": -3.442667814549452,
     "v": 1.9575828017978039,
     "family_factor": 1.0,
     "w": 0.280596371958965
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.111,
     "source_value_text": "11.10%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "105",
     "source_model_name": "Ministral-8B-Instruct-2410 (FC)",
     "p": 0.111,
     "p_star": 0.11485148514851484,
     "y": -2.0421155840671497,
     "v": 0.09642829591915453,
     "family_factor": 1.0,
     "w": 3.5998213896717646
    }
   ]
  },
  {
   "slug": "mistral-nemo",
   "name": "Mistral NeMo",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.546023264774889,
   "se": 0.23970421300265493,
   "si_iq": 46.80965102837666,
   "si_iq_low": 40.89547452476263,
   "si_iq_high": 52.72382753199069,
   "si_iq_display": 47,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.1082892749244713,
     "source_value_text": "0.1082892749244713",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "9qCrggpoq8FjQWVQhHaGBT",
     "source_model_name": "open-mistral-nemo-2407",
     "p": 0.1082892749244713,
     "p_star": 0.10858490566037736,
     "y": -2.1052777860607432,
     "v": 0.007791243659431366,
     "family_factor": 1.0,
     "w": 4.638595706157359
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.2989267676767677,
     "source_value_text": "0.2989267676767677",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "XCSWtbDquA7FUiWfd7kh9q",
     "source_model_name": "open-mistral-nemo-2407",
     "p": 0.06523569023569024,
     "p_star": 0.06742043551088778,
     "y": -2.6270063022729047,
     "v": 0.47268046167080796,
     "family_factor": 1.0,
     "w": 1.008154298655822
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.2763,
     "source_value_text": "27.63%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "78",
     "source_model_name": "Open-Mistral-Nemo-2407 (FC)",
     "p": 0.2763,
     "p_star": 0.2785148514851485,
     "y": -0.9518404091804255,
     "v": 0.04878445957380628,
     "family_factor": 1.0,
     "w": 4.752558050834461
    }
   ]
  },
  {
   "slug": "gemini-1-0-pro",
   "name": "Gemini 1.0 Pro",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.5909153220572536,
   "se": 0.23071912410952347,
   "si_iq": 46.1362701691412,
   "si_iq_low": 40.4437810566205,
   "si_iq_high": 51.82875928166189,
   "si_iq_display": 46,
   "domains": {
    "math": {
     "si_iq": 45.43209810224546,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.11244335347432025,
     "source_value_text": "0.11244335347432025",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "iUdecHq9vU5utytzgTXzqY",
     "source_model_name": "gemini-1.0-pro-001",
     "p": 0.11244335347432025,
     "p_star": 0.11273584905660378,
     "y": -2.0630952773695195,
     "v": 0.007539477576914265,
     "family_factor": 1.0,
     "w": 4.64945535598674
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.011111111111111112,
     "source_value_text": "0.011111111111111112",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-02-25",
     "source_row_id": "NpJvYQDcmwbGgS5MzZUPUg",
     "source_model_name": "gemini-1.0-pro-001",
     "p": 0.010121232343454568,
     "p_star": 0.02077077077077077,
     "y": -3.8532190144138143,
     "v": 1.095975963508547,
     "family_factor": 1.0,
     "w": 0.41806860276120145
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.33964646464646464,
     "source_value_text": "0.33964646464646464",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "ibpS8bs4z3wD3Hb6F3kpdV",
     "source_model_name": "gemini-1.0-pro-001",
     "p": 0.11952861952861953,
     "p_star": 0.12144053601340034,
     "y": -1.9788588659757227,
     "v": 0.17549147650953462,
     "family_factor": 1.0,
     "w": 2.095710097839067
    }
   ]
  },
  {
   "slug": "dbrx",
   "name": "DBRX",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.615514892165521,
   "se": 0.24250996157798008,
   "si_iq": 45.76727661751718,
   "si_iq_low": 39.78387441239637,
   "si_iq_high": 51.75067882263799,
   "si_iq_display": 46,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.11650302114803625,
     "source_value_text": "0.11650302114803625",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "PMbefrjykQmTBpABMa7FJi",
     "source_model_name": "dbrx-instruct",
     "p": 0.11650302114803625,
     "p_star": 0.11679245283018867,
     "y": -2.0231617686154744,
     "v": 0.007311031879122247,
     "family_factor": 1.0,
     "w": 4.6593532020380914
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.32891414141414144,
     "source_value_text": "0.32891414141414144",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "TTa3hu7PgRxHgizVreZsdJ",
     "source_model_name": "dbrx-instruct",
     "p": 0.10521885521885525,
     "p_star": 0.1072026800670017,
     "y": -2.1196383408061723,
     "v": 0.21467243931754215,
     "family_factor": 1.0,
     "w": 1.8347659249782924
    }
   ]
  },
  {
   "slug": "mixtral-8x7b",
   "name": "Mixtral 8x7B",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.7781309092556485,
   "se": 0.24797860867802735,
   "si_iq": 43.328036361165275,
   "si_iq_low": 37.20970726518796,
   "si_iq_high": 49.44636545714259,
   "si_iq_display": 43,
   "domains": {},
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.09950906344410876,
     "source_value_text": "0.09950906344410876",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "GN3Hez798byishFw3U6cpp",
     "source_model_name": "open-mixtral-8x7b",
     "p": 0.09950906344410876,
     "p_star": 0.09981132075471698,
     "y": -2.1993227736578076,
     "v": 0.00839349583316659,
     "family_factor": 1.0,
     "w": 4.612822901934752
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.3058712121212121,
     "source_value_text": "0.3058712121212121",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "Sn2qbB2HiySe7NcG28jnyM",
     "source_model_name": "Mixtral-8x7B-Instruct-v0.1",
     "p": 0.07449494949494946,
     "p_star": 0.0766331658291457,
     "y": -2.4889966350395256,
     "v": 0.3780067899237096,
     "family_factor": 1.0,
     "w": 1.2078285944050535
    }
   ]
  },
  {
   "slug": "llama-3-2-1b",
   "name": "Llama 3.2 1B",
   "tier": "insufficient",
   "rank": null,
   "theta": -3.8603256551956524,
   "se": 0.6279904349517637,
   "si_iq": 42.09511517206521,
   "si_iq_low": 26.600826488682998,
   "si_iq_high": 57.589403855447436,
   "si_iq_display": 42,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.005555555555555556,
     "source_value_text": "0.005555555555555556",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "8qwT2CF9U5zV99PFirnVsp",
     "source_model_name": "Llama-3.2-1B-Instruct",
     "p": 0.0045601156712267825,
     "p_star": 0.015330547939243593,
     "y": -4.162458568004531,
     "v": 1.5007847472225642,
     "family_factor": 1.0,
     "w": 0.3123468041955817
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.23926767676767677,
     "source_value_text": "0.23926767676767677",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "FGEsLTxzZ7fE9aq7DhdqZb",
     "source_model_name": "Llama-3.2-1B-Instruct",
     "p": 0.0,
     "p_star": 0.002512562814070352,
     "y": -5.983936280687191,
     "v": 266.65994962216627,
     "family_factor": 1.0,
     "w": 0.0021643064110912218
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.1082,
     "source_value_text": "10.82%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "107",
     "source_model_name": "Llama-3.2-1B-Instruct (FC)",
     "p": 0.1082,
     "p_star": 0.11207920792079208,
     "y": -2.0696767059888677,
     "v": 0.09850493155089317,
     "family_factor": 1.0,
     "w": 3.5621622881709505
    }
   ]
  },
  {
   "slug": "llama-3-8b",
   "name": "Llama 3-8B",
   "tier": "insufficient",
   "rank": null,
   "theta": -4.016806809987739,
   "se": 0.24453462260359846,
   "si_iq": 39.74789785018392,
   "si_iq_low": 33.71454156826363,
   "si_iq_high": 45.7812541321042,
   "si_iq_display": 40,
   "domains": {
    "math": {
     "si_iq": 39.28434983661369,
     "n": 2
    }
   },
   "inputs": [
    {
     "benchmark": "math_level_5",
     "score": 0.0612726586102719,
     "source_value_text": "0.0612726586102719",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#math_level_5.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/math-level-5",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "BURdKU7mhUX4YMPUDoFsed",
     "source_model_name": "Meta-Llama-3-8B-Instruct",
     "p": 0.0612726586102719,
     "p_star": 0.06160377358490566,
     "y": -2.723449147875983,
     "v": 0.013045557996431622,
     "family_factor": 1.0,
     "w": 4.422995550305329
    },
    {
     "benchmark": "otis_mock_aime",
     "score": 0.019444444444444445,
     "source_value_text": "0.019444444444444445",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-30",
     "source_row_id": "CAcNPzYBEu39HFWPmuUEeP",
     "source_model_name": "Meta-Llama-3-8B-Instruct",
     "p": 0.01846290735179624,
     "p_star": 0.028931105018061537,
     "y": -3.5134801038543024,
     "v": 0.783166385224738,
     "family_factor": 1.0,
     "w": 0.5661447359919227
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.26073232323232326,
     "source_value_text": "0.26073232323232326",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2025-01-27",
     "source_row_id": "iT3BBFWjsZk2rKHKeJDsM8",
     "source_model_name": "Meta-Llama-3-8B-Instruct",
     "p": 0.014309764309764347,
     "p_star": 0.01675041876046905,
     "y": -4.072439726834048,
     "v": 6.344770017035748,
     "family_factor": 1.0,
     "w": 0.08958430908527226
    }
   ]
  },
  {
   "slug": "gemma-3-1b",
   "name": "Gemma 3 1B",
   "tier": "insufficient",
   "rank": null,
   "theta": -4.020269071843249,
   "se": 0.6030175184421547,
   "si_iq": 39.69596392235126,
   "si_iq_low": 24.817827263156488,
   "si_iq_high": 54.57410058154604,
   "si_iq_display": 40,
   "domains": {},
   "inputs": [
    {
     "benchmark": "otis_mock_aime",
     "score": 0.011111111111111112,
     "source_value_text": "0.011111111111111112",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#otis_mock_aime_2024_2025.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/otis-mock-aime-2024-2025",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "3CGChL5vNDM6Df5C8Z8owN",
     "source_model_name": "gemma-3-1b-it",
     "p": 0.010121232343454568,
     "p_star": 0.02077077077077077,
     "y": -3.8532190144138143,
     "v": 1.095975963508547,
     "family_factor": 1.0,
     "w": 0.41806860276120145
    },
    {
     "benchmark": "gpqa_diamond",
     "score": 0.1994949494949495,
     "source_value_text": "0.1994949494949495",
     "source_url": "https://epoch.ai/data/benchmark_data.zip",
     "source_snapshot": "https://epoch.ai/data/benchmark_data.zip#gpqa_diamond.csv@sha256:0555162213a0a049",
     "source_sha256": "df0a77c60270c77e61dff74400a599b8b1181464af0ec9f3a803f587232b71ec",
     "verify_url": "https://epoch.ai/benchmarks/gpqa-diamond",
     "retrieved_at": "2026-10-18T12:17:21Z",
     "eval_date": "2026-08-28",
     "source_row_id": "Pc6CyTEYKbcdDUDKzGZnS9",
     "source_model_name": "gemma-3-1b-it",
     "p": 0.0,
     "p_star": 0.002512562814070352,
     "y": -5.983936280687191,
     "v": 266.65994962216627,
     "family_factor": 1.0,
     "w": 0.0021643064110912218
    },
    {
     "benchmark": "bfcl_overall",
     "score": 0.0717,
     "source_value_text": "7.17%",
     "source_url": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_snapshot": "https://raw.githubusercontent.com/ShishirPatil/gorilla/gh-pages/data_overall.csv@sha256:ede5081a24bc5ac7",
     "source_sha256": "ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6",
     "verify_url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
     "retrieved_at": "2026-10-18T12:17:30Z",
     "eval_date": "",
     "source_row_id": "109",
     "source_model_name": "Gemma-3-1b-it (Prompt)",
     "p": 0.0717,
     "p_star": 0.07594059405940594,
     "y": -2.4988249841984906,
     "v": 0.13969580679287624,
     "family_factor": 1.0,
     "w": 2.9500173183987575
    }
   ]
  }
 ]
}
