{"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); LiteLLM, model_prices_and_context_window.json (MIT); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.","method_version":"1.0.0","calibration_id":"a75ecba7e64a","note":"Every point = the closed form of /data/index.json applied to that day's inputs with the current parameters (methodology §5, §11); points rounded to 6 decimals.","models":{"ai-co-mathematician":{"points":[["2026-10-18",137.43537]],"inputs":{"frontiermath_t4":[["2026-10-18",0.756]]}},"claude-2":{"points":[["2026-10-18",47.674219]],"inputs":{"gpqa_diamond":[["2026-10-18",0.3465909090909091]],"math_level_5":[["2026-10-18",0.1172583081570997]],"otis_mock_aime":[["2026-10-18",0.025]]}},"claude-2-1":{"points":[["2026-10-18",51.813214]],"inputs":{"gpqa_diamond":[["2026-10-18",0.32954545454545453]],"otis_mock_aime":[["2026-10-18",0.019444444444444445]]}},"claude-3-5-haiku":{"points":[["2026-10-18",67.311958]],"inputs":{"aider_polyglot":[["2026-10-18",0.28]],"gpqa_diamond":[["2026-10-18",0.3813131313131313]],"math_level_5":[["2026-10-18",0.46355740181268884]],"otis_mock_aime":[["2026-10-18",0.043055555555555555]]}},"claude-3-5-sonnet":{"points":[["2026-10-18",70.851558]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5404040404040404]],"math_level_5":[["2026-10-18",0.5168051359516617]],"otis_mock_aime":[["2026-10-18",0.06527777777777778]]}},"claude-3-5-sonnet-october-2024":{"points":[["2026-10-18",75.669469]],"inputs":{"aider_polyglot":[["2026-10-18",0.516]],"gpqa_diamond":[["2026-10-18",0.553030303030303]],"math_level_5":[["2026-10-18",0.5694864048338368]],"otis_mock_aime":[["2026-10-18",0.08472222222222223]]}},"claude-3-7-sonnet":{"points":[["2026-10-18",99.031257]],"inputs":{"aider_polyglot":[["2026-10-18",0.649]],"gpqa_diamond":[["2026-10-18",0.7973484848484849]],"math_level_5":[["2026-10-18",0.9116314199395771]],"otis_mock_aime":[["2026-10-18",0.5777777777777777]],"swe_bench_verified":[["2026-10-18",0.609504132231405]]}},"claude-3-haiku":{"points":[["2026-10-18",50.175856]],"inputs":{"gpqa_diamond":[["2026-10-18",0.3630050505050505]],"math_level_5":[["2026-10-18",0.1487915407854985]],"otis_mock_aime":[["2026-10-18",0.018055555555555554]]}},"claude-3-opus":{"points":[["2026-10-18",65.399802]],"inputs":{"chess_puzzles":[["2026-10-18",0.03]],"gpqa_diamond":[["2026-10-18",0.4715909090909091]],"math_level_5":[["2026-10-18",0.37481117824773413]],"otis_mock_aime":[["2026-10-18",0.04722222222222222]],"simpleqa_verified":[["2026-10-18",0.126]]}},"claude-3-sonnet":{"points":[["2026-10-18",53.921071]],"inputs":{"gpqa_diamond":[["2026-10-18",0.4059343434343434]],"math_level_5":[["2026-10-18",0.18174093655589124]],"otis_mock_aime":[["2026-10-18",0.025]]}},"claude-fable-5":{"points":[["2026-10-18",137.727359]],"inputs":{"chess_puzzles":[["2026-10-18",0.47]],"frontiermath_t13":[["2026-10-18",0.8701754385964913]],"frontiermath_t4":[["2026-10-18",0.902]],"gpqa_diamond":[["2026-10-18",0.8585858585858586]],"mystery_game_puzzles":[["2026-10-18",0.52]],"or_gpqa_diamond":[["2026-10-18",0.8615317499999998]],"or_tau2_airline":[["2026-10-18",0.7957576363636364]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.707]]}},"claude-fable-5-1":{"points":[["2026-10-18",139.757466]],"inputs":{"chess_puzzles":[["2026-10-18",0.48]],"frontiermath_t13":[["2026-10-18",0.9017543859649123]],"frontiermath_t4":[["2026-10-18",0.8780487804878049]],"mystery_game_puzzles":[["2026-10-18",0.58]],"or_gpqa_diamond":[["2026-10-18",0.8894498333333334]],"or_tau2_airline":[["2026-10-18",0.7906666]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.708]]}},"claude-haiku-4-5":{"points":[["2026-10-18",103.693542]],"inputs":{"bfcl_overall":[["2026-10-18",0.687]],"chess_puzzles":[["2026-10-18",0.08]],"gpqa_diamond":[["2026-10-18",0.7121212121212122]],"math_level_5":[["2026-10-18",0.9636087945413192]],"or_gpqa_diamond":[["2026-10-18",0.7310605833333333]],"or_tau2_airline":[["2026-10-18",0.6657576363636364]],"otis_mock_aime":[["2026-10-18",0.6666666666666666]],"simpleqa_verified":[["2026-10-18",0.132]]}},"claude-haiku-5-5":{"points":[["2026-10-18",129.403595]],"inputs":{"chess_puzzles":[["2026-10-18",0.55]],"frontiermath_t13":[["2026-10-18",0.7508771929824561]],"frontiermath_t4":[["2026-10-18",0.4634146341463415]],"gpqa_diamond":[["2026-10-18",0.8964646464646465]],"mystery_game_puzzles":[["2026-10-18",0.3]],"or_gpqa_diamond":[["2026-10-18",0.8692479999999999]],"or_tau2_airline":[["2026-10-18",0.7577776666666667]],"otis_mock_aime":[["2026-10-18",0.9888888888888889]],"simpleqa_verified":[["2026-10-18",0.238]]}},"claude-opus-4":{"points":[["2026-10-18",97.787873]],"inputs":{"aider_polyglot":[["2026-10-18",0.72]],"gpqa_diamond":[["2026-10-18",0.7626262626262627]],"math_level_5":[["2026-10-18",0.850453172205438]],"otis_mock_aime":[["2026-10-18",0.6444444444444445]],"swe_bench_verified":[["2026-10-18",0.7066115702479339]]}},"claude-opus-4-1":{"points":[["2026-10-18",105.415185]],"inputs":{"frontiermath_t13":[["2026-10-18",0.12631578947368421]],"frontiermath_t4":[["2026-10-18",0.024390243902439025]],"gpqa_diamond":[["2026-10-18",0.7727272727272727]],"mystery_game_puzzles":[["2026-10-18",0.21]],"otis_mock_aime":[["2026-10-18",0.6888888888888889]],"swe_bench_verified":[["2026-10-18",0.7334710743801653]]}},"claude-opus-4-5":{"points":[["2026-10-18",114.576853]],"inputs":{"bfcl_overall":[["2026-10-18",0.7746999999999999]],"chess_puzzles":[["2026-10-18",0.14]],"frontiermath_t13":[["2026-10-18",0.34385964912280703]],"frontiermath_t4":[["2026-10-18",0.04878048780487805]],"gpqa_diamond":[["2026-10-18",0.860479797979798]],"mystery_game_puzzles":[["2026-10-18",0.22]],"or_gpqa_diamond":[["2026-10-18",0.8610461538461541]],"or_tau2_airline":[["2026-10-18",0.7700000714285714]],"otis_mock_aime":[["2026-10-18",0.8611111111111112]],"simpleqa_verified":[["2026-10-18",0.457]],"swe_bench_verified":[["2026-10-18",0.7665289256198347]]}},"claude-opus-4-6":{"points":[["2026-10-18",122.954624]],"inputs":{"chess_puzzles":[["2026-10-18",0.21]],"frontiermath_t13":[["2026-10-18",0.6596491228070176]],"frontiermath_t4":[["2026-10-18",0.2682926829268293]],"gpqa_diamond":[["2026-10-18",0.9053030303030303]],"mystery_game_puzzles":[["2026-10-18",0.25]],"or_gpqa_diamond":[["2026-10-18",0.856643153846154]],"or_tau2_airline":[["2026-10-18",0.7638095]],"otis_mock_aime":[["2026-10-18",0.9444444444444444]],"simpleqa_verified":[["2026-10-18",0.47]],"swe_bench_verified":[["2026-10-18",0.7871900826446281]]}},"claude-opus-4-7":{"points":[["2026-10-18",126.949033]],"inputs":{"chess_puzzles":[["2026-10-18",0.41]],"frontiermath_t13":[["2026-10-18",0.7017543859649122]],"frontiermath_t4":[["2026-10-18",0.3170731707317073]],"gpqa_diamond":[["2026-10-18",0.9015151515151515]],"mystery_game_puzzles":[["2026-10-18",0.28]],"or_gpqa_diamond":[["2026-10-18",0.892375117408907]],"or_tau2_airline":[["2026-10-18",0.7757142142857143]],"otis_mock_aime":[["2026-10-18",0.978]],"simpleqa_verified":[["2026-10-18",0.517]],"swe_bench_verified":[["2026-10-18",0.8347107438016529]]}},"claude-opus-4-8":{"points":[["2026-10-18",132.025966]],"inputs":{"chess_puzzles":[["2026-10-18",0.52]],"frontiermath_t13":[["2026-10-18",0.8]],"frontiermath_t4":[["2026-10-18",0.5609756097560976]],"gpqa_diamond":[["2026-10-18",0.9103535353535354]],"mystery_game_puzzles":[["2026-10-18",0.36]],"or_gpqa_diamond":[["2026-10-18",0.8959834999999999]],"or_tau2_airline":[["2026-10-18",0.7776190714285715]],"otis_mock_aime":[["2026-10-18",0.9833333333333333]],"simpleqa_verified":[["2026-10-18",0.53]]}},"claude-opus-5":{"points":[["2026-10-18",136.440631]],"inputs":{"chess_puzzles":[["2026-10-18",0.43]],"frontiermath_t13":[["2026-10-18",0.856140350877193]],"frontiermath_t4":[["2026-10-18",0.7317073170731707]],"gpqa_diamond":[["2026-10-18",0.9387626262626263]],"mystery_game_puzzles":[["2026-10-18",0.59]],"or_gpqa_diamond":[["2026-10-18",0.8957629166666667]],"or_tau2_airline":[["2026-10-18",0.7727272727272727]],"otis_mock_aime":[["2026-10-18",0.9888888888888889]],"simpleqa_verified":[["2026-10-18",0.599]]}},"claude-opus-5-5":{"points":[["2026-10-18",144.424014]],"inputs":{"chess_puzzles":[["2026-10-18",0.67]],"frontiermath_t13":[["2026-10-18",0.9122807017543859]],"frontiermath_t4":[["2026-10-18",0.95]],"gpqa_diamond":[["2026-10-18",0.9059343434343434]],"mystery_game_puzzles":[["2026-10-18",0.71]],"or_gpqa_diamond":[["2026-10-18",0.9020199999999999]],"or_tau2_airline":[["2026-10-18",0.756]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.722]]}},"claude-sonnet-4":{"points":[["2026-10-18",97.098505]],"inputs":{"aider_polyglot":[["2026-10-18",0.613]],"gpqa_diamond":[["2026-10-18",0.7918781725888325]],"math_level_5":[["2026-10-18",0.8436555891238671]],"or_gpqa_diamond":[["2026-10-18",0.7672559999999999]],"or_tau2_airline":[["2026-10-18",0.64]],"otis_mock_aime":[["2026-10-18",0.7111111111111111]]}},"claude-sonnet-4-5":{"points":[["2026-10-18",109.902895]],"inputs":{"bfcl_overall":[["2026-10-18",0.7323999999999999]],"chess_puzzles":[["2026-10-18",0.1]],"frontiermath_t13":[["2026-10-18",0.23859649122807017]],"frontiermath_t4":[["2026-10-18",0.024390243902439025]],"gpqa_diamond":[["2026-10-18",0.8232323232323232]],"math_level_5":[["2026-10-18",0.9773413897280967]],"mystery_game_puzzles":[["2026-10-18",0.17]],"or_gpqa_diamond":[["2026-10-18",0.8111110666666667]],"or_tau2_airline":[["2026-10-18",0.7528572857142857]],"otis_mock_aime":[["2026-10-18",0.7777777777777778]],"simpleqa_verified":[["2026-10-18",0.307]],"swe_bench_verified":[["2026-10-18",0.7128099173553719]]}},"claude-sonnet-4-6":{"points":[["2026-10-18",113.280038]],"inputs":{"chess_puzzles":[["2026-10-18",0.23]],"gpqa_diamond":[["2026-10-18",0.8737373737373737]],"mystery_game_puzzles":[["2026-10-18",0.16]],"or_gpqa_diamond":[["2026-10-18",0.6459467692307692]],"or_tau2_airline":[["2026-10-18",0.7490475714285715]],"otis_mock_aime":[["2026-10-18",0.857936507936508]],"simpleqa_verified":[["2026-10-18",0.355]],"swe_bench_verified":[["2026-10-18",0.7520661157024794]]}},"claude-sonnet-5":{"points":[["2026-10-18",126.098541]],"inputs":{"chess_puzzles":[["2026-10-18",0.45]],"frontiermath_t13":[["2026-10-18",0.656140350877193]],"frontiermath_t4":[["2026-10-18",0.2926829268292683]],"gpqa_diamond":[["2026-10-18",0.9053030303030303]],"mystery_game_puzzles":[["2026-10-18",0.35]],"or_gpqa_diamond":[["2026-10-18",0.8576035833333334]],"or_tau2_airline":[["2026-10-18",0.76]],"otis_mock_aime":[["2026-10-18",0.9472222222222222]],"simpleqa_verified":[["2026-10-18",0.337]]}},"claude-sonnet-5-5":{"points":[["2026-10-18",140.29239]],"inputs":{"chess_puzzles":[["2026-10-18",0.59]],"frontiermath_t13":[["2026-10-18",0.887719298245614]],"frontiermath_t4":[["2026-10-18",0.8048780487804879]],"gpqa_diamond":[["2026-10-18",0.9558080808080808]],"mystery_game_puzzles":[["2026-10-18",0.65]],"or_gpqa_diamond":[["2026-10-18",0.92929275]],"or_tau2_airline":[["2026-10-18",0.775]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.465]]}},"cohere-command-a":{"points":[["2026-10-18",93.488523]],"inputs":{"bfcl_overall":[["2026-10-18",0.46490000000000004]]}},"dbrx":{"points":[["2026-10-18",45.767277]],"inputs":{"gpqa_diamond":[["2026-10-18",0.32891414141414144]],"math_level_5":[["2026-10-18",0.11650302114803625]]}},"deepseek-r1":{"points":[["2026-10-18",97.795446]],"inputs":{"aider_polyglot":[["2026-10-18",0.569]],"gpqa_diamond":[["2026-10-18",0.7171717171717171]],"math_level_5":[["2026-10-18",0.9305135951661632]],"otis_mock_aime":[["2026-10-18",0.5333333333333333]]}},"deepseek-r1-0528-qwen3-8b":{"points":[["2026-10-18",90.484082]],"inputs":{"gpqa_diamond":[["2026-10-18",0.0928030303030303]],"otis_mock_aime":[["2026-10-18",0.4388888888888889]]}},"deepseek-r1-distill-llama-70b":{"points":[["2026-10-18",92.196907]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5574494949494949]],"math_level_5":[["2026-10-18",0.8989803625377644]],"otis_mock_aime":[["2026-10-18",0.5138888888888888]]}},"deepseek-r1-distill-qwen-1-5b":{"points":[["2026-10-18",72.607791]],"inputs":{"gpqa_diamond":[["2026-10-18",0.33585858585858586]],"otis_mock_aime":[["2026-10-18",0.21388888888888888]]}},"deepseek-r1-distill-qwen-14b":{"points":[["2026-10-18",88.857618]],"inputs":{"gpqa_diamond":[["2026-10-18",0.44696969696969696]],"math_level_5":[["2026-10-18",0.8712235649546828]],"otis_mock_aime":[["2026-10-18",0.5055555555555555]]}},"deepseek-r1-distill-qwen-32b":{"points":[["2026-10-18",93.237004]],"inputs":{"gpqa_diamond":[["2026-10-18",0.6414141414141414]],"otis_mock_aime":[["2026-10-18",0.5555555555555556]]}},"deepseek-r1-may-2025":{"points":[["2026-10-18",104.257512]],"inputs":{"gpqa_diamond":[["2026-10-18",0.7632575757575758]],"math_level_5":[["2026-10-18",0.9663897280966768]],"or_gpqa_diamond":[["2026-10-18",0.7851099187817259]],"or_tau2_airline":[["2026-10-18",0.47874697986577186]],"otis_mock_aime":[["2026-10-18",0.6638888888888889]]}},"deepseek-v3":{"points":[["2026-10-18",77.43449]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5653409090909091]],"math_level_5":[["2026-10-18",0.6485083081570997]],"or_gpqa_diamond":[["2026-10-18",0.661616]],"or_tau2_airline":[["2026-10-18",0.4053599698492462]],"otis_mock_aime":[["2026-10-18",0.15833333333333333]]}},"deepseek-v3-1":{"points":[["2026-10-18",99.741525]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.7707982259154932]],"or_tau2_airline":[["2026-10-18",0.47222181249999995]]}},"deepseek-v3-1-terminus":{"points":[["2026-10-18",102.337572]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.7942762]],"or_tau2_airline":[["2026-10-18",0.48266679999999995]]}},"deepseek-v3-2":{"points":[["2026-10-18",114.200294]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.802714625]],"or_tau2_airline":[["2026-10-18",0.7193332]]}},"deepseek-v3-2-exp":{"points":[["2026-10-18",111.747369]],"inputs":{"aider_polyglot":[["2026-10-18",0.742]],"bfcl_overall":[["2026-10-18",0.5672999999999999]],"or_gpqa_diamond":[["2026-10-18",0.8265989999999999]],"or_tau2_airline":[["2026-10-18",0.693333]]}},"deepseek-v3-mar-2025":{"points":[["2026-10-18",85.382478]],"inputs":{"gpqa_diamond":[["2026-10-18",0.6761363636363636]],"math_level_5":[["2026-10-18",0.75547583081571]],"or_gpqa_diamond":[["2026-10-18",0.646465]],"or_tau2_airline":[["2026-10-18",0.4337431393442623]],"otis_mock_aime":[["2026-10-18",0.37777777777777777]]}},"deepseek-v4-1-flash":{"points":[["2026-10-18",127.71231]],"inputs":{"chess_puzzles":[["2026-10-18",0.48]],"frontiermath_t13":[["2026-10-18",0.6736842105263158]],"frontiermath_t4":[["2026-10-18",0.2682926829268293]],"gpqa_diamond":[["2026-10-18",0.8983585858585859]],"mystery_game_puzzles":[["2026-10-18",0.43]],"or_gpqa_diamond":[["2026-10-18",0.8838381666666666]],"or_tau2_airline":[["2026-10-18",0.745]],"otis_mock_aime":[["2026-10-18",0.9833333333333333]],"simpleqa_verified":[["2026-10-18",0.429]]}},"deepseek-v4-flash":{"points":[["2026-10-18",129.306466]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.8989900000000001]],"or_tau2_airline":[["2026-10-18",0.7755553333333334]]}},"deepseek-v4-flash-0731":{"points":[["2026-10-18",123.614079]],"inputs":{"chess_puzzles":[["2026-10-18",0.32]],"frontiermath_t13":[["2026-10-18",0.5754385964912281]],"frontiermath_t4":[["2026-10-18",0.24390243902439024]],"gpqa_diamond":[["2026-10-18",0.9103535353535354]],"mystery_game_puzzles":[["2026-10-18",0.34]],"or_gpqa_diamond":[["2026-10-18",0.8996633999999999]],"or_tau2_airline":[["2026-10-18",0.7766665]],"otis_mock_aime":[["2026-10-18",0.9444444444444444]],"simpleqa_verified":[["2026-10-18",0.33633633633633636]]}},"deepseek-v4-pro":{"points":[["2026-10-18",116.556422]],"inputs":{"chess_puzzles":[["2026-10-18",0.19]],"frontiermath_t13":[["2026-10-18",0.45263157894736844]],"frontiermath_t4":[["2026-10-18",0.024390243902439025]],"gpqa_diamond":[["2026-10-18",0.9090909090909091]],"mystery_game_puzzles":[["2026-10-18",0.17]],"or_gpqa_diamond":[["2026-10-18",0.853535]],"or_tau2_airline":[["2026-10-18",0.788889]],"otis_mock_aime":[["2026-10-18",0.9666666666666667]],"simpleqa_verified":[["2026-10-18",0.46993987975951906]],"swe_bench_verified":[["2026-10-18",0.7763975155279503]]}},"deepseek-v4-pro-0813":{"points":[["2026-10-18",127.617246]],"inputs":{"chess_puzzles":[["2026-10-18",0.46]],"frontiermath_t13":[["2026-10-18",0.6456140350877193]],"frontiermath_t4":[["2026-10-18",0.2682926829268293]],"gpqa_diamond":[["2026-10-18",0.9166666666666666]],"mystery_game_puzzles":[["2026-10-18",0.43]],"or_gpqa_diamond":[["2026-10-18",0.892567903763697]],"or_tau2_airline":[["2026-10-18",0.767500125]],"otis_mock_aime":[["2026-10-18",0.9861111111111112]],"simpleqa_verified":[["2026-10-18",0.5290581162324649]]}},"eurus-2-7b-prime":{"points":[["2026-10-18",51.114543]],"inputs":{"gpqa_diamond":[["2026-10-18",0.3390151515151515]]}},"gemini-1-0-pro":{"points":[["2026-10-18",46.13627]],"inputs":{"gpqa_diamond":[["2026-10-18",0.33964646464646464]],"math_level_5":[["2026-10-18",0.11244335347432025]],"otis_mock_aime":[["2026-10-18",0.011111111111111112]]}},"gemini-1-5-flash-8b":{"points":[["2026-10-18",56.972366]],"inputs":{"gpqa_diamond":[["2026-10-18",0.32954545454545453]],"otis_mock_aime":[["2026-10-18",0.04583333333333333]]}},"gemini-1-5-flash-may-2024":{"points":[["2026-10-18",57.832705]],"inputs":{"gpqa_diamond":[["2026-10-18",0.40372474747474746]],"math_level_5":[["2026-10-18",0.2512273413897281]],"otis_mock_aime":[["2026-10-18",0.03888888888888889]]}},"gemini-1-5-flash-sep-2024":{"points":[["2026-10-18",74.499724]],"inputs":{"gpqa_diamond":[["2026-10-18",0.47316919191919193]],"math_level_5":[["2026-10-18",0.6186744712990937]],"otis_mock_aime":[["2026-10-18",0.1625]]}},"gemini-1-5-pro-may-2024":{"points":[["2026-10-18",65.784369]],"inputs":{"gpqa_diamond":[["2026-10-18",0.4586489898989899]],"math_level_5":[["2026-10-18",0.4074773413897281]],"otis_mock_aime":[["2026-10-18",0.06805555555555555]]}},"gemini-1-5-pro-sept-2024":{"points":[["2026-10-18",80.113609]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5722853535353535]],"math_level_5":[["2026-10-18",0.7039274924471299]],"otis_mock_aime":[["2026-10-18",0.23055555555555557]]}},"gemini-2-0-flash-dec-2024":{"points":[["2026-10-18",79.517184]],"inputs":{"aider_polyglot":[["2026-10-18",0.222]]}},"gemini-2-0-flash-feb-2025":{"points":[["2026-10-18",86.732765]],"inputs":{"gpqa_diamond":[["2026-10-18",0.6414141414141414]],"math_level_5":[["2026-10-18",0.8216578549848943]],"otis_mock_aime":[["2026-10-18",0.3111111111111111]]}},"gemini-2-0-flash-thinking-jan-2025":{"points":[["2026-10-18",88.63102]],"inputs":{"aider_polyglot":[["2026-10-18",0.182]],"gpqa_diamond":[["2026-10-18",0.5707070707070707]],"otis_mock_aime":[["2026-10-18",0.5777777777777777]]}},"gemini-2-0-pro":{"points":[["2026-10-18",88.80349]],"inputs":{"aider_polyglot":[["2026-10-18",0.35600000000000004]],"gpqa_diamond":[["2026-10-18",0.6565656565656566]],"math_level_5":[["2026-10-18",0.8345921450151057]]}},"gemini-2-5-flash-apr-2025":{"points":[["2026-10-18",101.194026]],"inputs":{"aider_polyglot":[["2026-10-18",0.47100000000000003]],"otis_mock_aime":[["2026-10-18",0.7305555555555555]]}},"gemini-2-5-flash-jun-2025":{"points":[["2026-10-18",102.122461]],"inputs":{"bfcl_overall":[["2026-10-18",0.5624]],"or_gpqa_diamond":[["2026-10-18",0.738309]],"or_tau2_airline":[["2026-10-18",0.5511113333333334]]}},"gemini-2-5-flash-may-2025":{"points":[["2026-10-18",101.520654]],"inputs":{"aider_polyglot":[["2026-10-18",0.551]],"otis_mock_aime":[["2026-10-18",0.7083333333333334]]}},"gemini-2-5-pro-jun-2025":{"points":[["2026-10-18",108.466271]],"inputs":{"aider_polyglot":[["2026-10-18",0.831]],"frontiermath_t13":[["2026-10-18",0.24561403508771928]],"frontiermath_t4":[["2026-10-18",0.0]],"gpqa_diamond":[["2026-10-18",0.8529040404040404]],"or_gpqa_diamond":[["2026-10-18",0.806210222222222]],"or_tau2_airline":[["2026-10-18",0.5622223333333333]],"otis_mock_aime":[["2026-10-18",0.8472222222222222]],"swe_bench_verified":[["2026-10-18",0.5755693581780539]]}},"gemini-2-5-pro-mar-2025":{"points":[["2026-10-18",107.688294]],"inputs":{"aider_polyglot":[["2026-10-18",0.7290000000000001]],"gpqa_diamond":[["2026-10-18",0.8383838383838383]],"math_level_5":[["2026-10-18",0.9556268882175226]]}},"gemini-2-5-pro-may-2025":{"points":[["2026-10-18",104.015944]],"inputs":{"aider_polyglot":[["2026-10-18",0.769]],"gpqa_diamond":[["2026-10-18",0.6666666666666666]],"math_level_5":[["2026-10-18",0.9590256797583081]]}},"gemini-3-1-flash-lite":{"points":[["2026-10-18",109.298994]],"inputs":{"frontiermath_t13":[["2026-10-18",0.2771929824561403]],"gpqa_diamond":[["2026-10-18",0.8181818181818182]],"otis_mock_aime":[["2026-10-18",0.8]]}},"gemini-3-1-pro":{"points":[["2026-10-18",126.847617]],"inputs":{"chess_puzzles":[["2026-10-18",0.51]],"frontiermath_t13":[["2026-10-18",0.5964912280701754]],"frontiermath_t4":[["2026-10-18",0.2682926829268293]],"gpqa_diamond":[["2026-10-18",0.9444444444444444]],"mystery_game_puzzles":[["2026-10-18",0.34]],"or_gpqa_diamond":[["2026-10-18",0.9483723333333332]],"or_tau2_airline":[["2026-10-18",0.7422223333333333]],"otis_mock_aime":[["2026-10-18",0.956]],"simpleqa_verified":[["2026-10-18",0.735]],"swe_bench_verified":[["2026-10-18",0.756198347107438]]}},"gemini-3-5-flash":{"points":[["2026-10-18",126.321741]],"inputs":{"chess_puzzles":[["2026-10-18",0.45]],"frontiermath_t13":[["2026-10-18",0.6280701754385964]],"frontiermath_t4":[["2026-10-18",0.2682926829268293]],"gpqa_diamond":[["2026-10-18",0.928030303030303]],"mystery_game_puzzles":[["2026-10-18",0.32]],"or_gpqa_diamond":[["2026-10-18",0.9242421666666667]],"or_tau2_airline":[["2026-10-18",0.7333336666666668]],"otis_mock_aime":[["2026-10-18",0.9555555555555556]],"simpleqa_verified":[["2026-10-18",0.662]],"swe_bench_verified":[["2026-10-18",0.7933884297520661]]}},"gemini-3-5-flash-lite":{"points":[["2026-10-18",109.338261]],"inputs":{"chess_puzzles":[["2026-10-18",0.21]],"frontiermath_t13":[["2026-10-18",0.2596491228070175]],"frontiermath_t4":[["2026-10-18",0.0]],"gpqa_diamond":[["2026-10-18",0.8333333333333334]],"mystery_game_puzzles":[["2026-10-18",0.19]],"or_gpqa_diamond":[["2026-10-18",0.8402775531250001]],"or_tau2_airline":[["2026-10-18",0.7349997500000001]],"otis_mock_aime":[["2026-10-18",0.7111111111111111]]}},"gemini-3-6-flash":{"points":[["2026-10-18",124.729886]],"inputs":{"chess_puzzles":[["2026-10-18",0.42]],"frontiermath_t13":[["2026-10-18",0.5894736842105263]],"frontiermath_t4":[["2026-10-18",0.21951219512195122]],"gpqa_diamond":[["2026-10-18",0.9412878787878788]],"mystery_game_puzzles":[["2026-10-18",0.3]],"or_gpqa_diamond":[["2026-10-18",0.930415]],"or_tau2_airline":[["2026-10-18",0.72]],"otis_mock_aime":[["2026-10-18",0.9416666666666667]],"simpleqa_verified":[["2026-10-18",0.662]]}},"gemini-3-7-flash":{"points":[["2026-10-18",131.069064]],"inputs":{"chess_puzzles":[["2026-10-18",0.66]],"frontiermath_t13":[["2026-10-18",0.7157894736842105]],"frontiermath_t4":[["2026-10-18",0.36585365853658536]],"gpqa_diamond":[["2026-10-18",0.9482323232323232]],"mystery_game_puzzles":[["2026-10-18",0.37]],"or_gpqa_diamond":[["2026-10-18",0.9391951653543308]],"or_tau2_airline":[["2026-10-18",0.7831052054794521]],"otis_mock_aime":[["2026-10-18",0.9722222222222222]],"simpleqa_verified":[["2026-10-18",0.692]]}},"gemini-3-8-flash":{"points":[["2026-10-18",129.897635]],"inputs":{"chess_puzzles":[["2026-10-18",0.58]],"frontiermath_t13":[["2026-10-18",0.6842105263157895]],"frontiermath_t4":[["2026-10-18",0.21951219512195122]],"gpqa_diamond":[["2026-10-18",0.9539141414141414]],"mystery_game_puzzles":[["2026-10-18",0.47]],"or_gpqa_diamond":[["2026-10-18",0.9482614885496183]],"or_tau2_airline":[["2026-10-18",0.734694]],"otis_mock_aime":[["2026-10-18",0.9888888888888889]],"simpleqa_verified":[["2026-10-18",0.697]]}},"gemini-3-flash":{"points":[["2026-10-18",122.356064]],"inputs":{"chess_puzzles":[["2026-10-18",0.39]],"frontiermath_t13":[["2026-10-18",0.512280701754386]],"frontiermath_t4":[["2026-10-18",0.17073170731707318]],"gpqa_diamond":[["2026-10-18",0.8939393939393939]],"mystery_game_puzzles":[["2026-10-18",0.26]],"or_gpqa_diamond":[["2026-10-18",0.8855220000000001]],"or_tau2_airline":[["2026-10-18",0.7533333333333333]],"otis_mock_aime":[["2026-10-18",0.9555555555555556]],"simpleqa_verified":[["2026-10-18",0.668]],"swe_bench_verified":[["2026-10-18",0.7541322314049587]]}},"gemini-3-pro":{"points":[["2026-10-18",122.410588]],"inputs":{"bfcl_overall":[["2026-10-18",0.7251000000000001]],"gpqa_diamond":[["2026-10-18",0.9261363636363636]],"otis_mock_aime":[["2026-10-18",0.9138888888888889]],"swe_bench_verified":[["2026-10-18",0.7293388429752066]]}},"gemini-4-argon":{"points":[["2026-10-18",140.155621]],"inputs":{"chess_puzzles":[["2026-10-18",0.59]],"frontiermath_t13":[["2026-10-18",0.8596491228070176]],"frontiermath_t4":[["2026-10-18",0.7804878048780488]],"gpqa_diamond":[["2026-10-18",0.9640151515151515]],"mystery_game_puzzles":[["2026-10-18",0.64]],"or_gpqa_diamond":[["2026-10-18",0.964646]],"or_tau2_airline":[["2026-10-18",0.786667]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.76]]}},"gemma-2-27b":{"points":[["2026-10-18",57.149439]],"inputs":{"gpqa_diamond":[["2026-10-18",0.3648989898989899]],"math_level_5":[["2026-10-18",0.2788897280966767]],"otis_mock_aime":[["2026-10-18",0.013888888888888888]]}},"gemma-2-9b":{"points":[["2026-10-18",52.90873]],"inputs":{"gpqa_diamond":[["2026-10-18",0.2746212121212121]],"math_level_5":[["2026-10-18",0.2100641993957704]],"otis_mock_aime":[["2026-10-18",0.005555555555555556]]}},"gemma-3-12b":{"points":[["2026-10-18",72.63314]],"inputs":{"bfcl_overall":[["2026-10-18",0.3043]],"gpqa_diamond":[["2026-10-18",0.39457070707070707]],"or_gpqa_diamond":[["2026-10-18",0.37878799999999996]],"or_tau2_airline":[["2026-10-18",0.48]],"otis_mock_aime":[["2026-10-18",0.16666666666666666]]}},"gemma-3-1b":{"points":[["2026-10-18",39.695964]],"inputs":{"bfcl_overall":[["2026-10-18",0.0717]],"gpqa_diamond":[["2026-10-18",0.1994949494949495]],"otis_mock_aime":[["2026-10-18",0.011111111111111112]]}},"gemma-3-27b":{"points":[["2026-10-18",76.7834]],"inputs":{"aider_polyglot":[["2026-10-18",0.049]],"bfcl_overall":[["2026-10-18",0.29469999999999996]],"gpqa_diamond":[["2026-10-18",0.4772727272727273]],"math_level_5":[["2026-10-18",0.740370090634441]],"otis_mock_aime":[["2026-10-18",0.225]]}},"gemma-3-4b":{"points":[["2026-10-18",62.92706]],"inputs":{"bfcl_overall":[["2026-10-18",0.1962]],"gpqa_diamond":[["2026-10-18",0.23232323232323232]],"or_gpqa_diamond":[["2026-10-18",0.271044]],"otis_mock_aime":[["2026-10-18",0.075]]}},"gemma-4-26b-a4b":{"points":[["2026-10-18",105.998841]],"inputs":{"gpqa_diamond":[["2026-10-18",0.7323232323232324]],"or_gpqa_diamond":[["2026-10-18",0.7762077565217391]],"or_tau2_airline":[["2026-10-18",0.5733334999999999]],"otis_mock_aime":[["2026-10-18",0.8222222222222222]]}},"gemma-4-31b-it":{"points":[["2026-10-18",103.968449]],"inputs":{"gpqa_diamond":[["2026-10-18",0.7575757575757576]],"or_gpqa_diamond":[["2026-10-18",0.81649825]],"or_tau2_airline":[["2026-10-18",0.756666625]],"otis_mock_aime":[["2026-10-18",0.7333333333333333]],"simpleqa_verified":[["2026-10-18",0.104]]}},"glm-4-5-air":{"points":[["2026-10-18",114.252865]],"inputs":{"or_tau2_airline":[["2026-10-18",0.68]]}},"glm-4-6":{"points":[["2026-10-18",116.824668]],"inputs":{"bfcl_overall":[["2026-10-18",0.7238]],"or_gpqa_diamond":[["2026-10-18",0.7646065075987841]],"or_tau2_airline":[["2026-10-18",0.7344445]]}},"glm-4-7":{"points":[["2026-10-18",112.292477]],"inputs":{"chess_puzzles":[["2026-10-18",0.21]],"gpqa_diamond":[["2026-10-18",0.8333333333333334]],"or_gpqa_diamond":[["2026-10-18",0.8364136921606119]],"or_tau2_airline":[["2026-10-18",0.7037037777777777]],"otis_mock_aime":[["2026-10-18",0.8333333333333334]],"simpleqa_verified":[["2026-10-18",0.322]]}},"glm-4-7-flash":{"points":[["2026-10-18",94.287816]],"inputs":{"gpqa_diamond":[["2026-10-18",0.6054292929292929]],"or_gpqa_diamond":[["2026-10-18",0.49197393750000007]],"or_tau2_airline":[["2026-10-18",0.6833333333333333]],"otis_mock_aime":[["2026-10-18",0.5833333333333334]]}},"glm-4-7-flash-none":{"points":[["2026-10-18",76.992819]],"inputs":{"gpqa_diamond":[["2026-10-18",0.4513888888888889]],"otis_mock_aime":[["2026-10-18",0.25]]}},"glm-5":{"points":[["2026-10-18",111.611039]],"inputs":{"gpqa_diamond":[["2026-10-18",0.8781725888324873]],"or_gpqa_diamond":[["2026-10-18",0.7285024173913045]],"or_tau2_airline":[["2026-10-18",0.7422222222222222]],"otis_mock_aime":[["2026-10-18",0.8]],"swe_bench_verified":[["2026-10-18",0.7207792207792207]]}},"glm-5-1":{"points":[["2026-10-18",115.536029]],"inputs":{"chess_puzzles":[["2026-10-18",0.2]],"frontiermath_t13":[["2026-10-18",0.3684210526315789]],"gpqa_diamond":[["2026-10-18",0.898989898989899]],"or_gpqa_diamond":[["2026-10-18",0.8115756996197718]],"or_tau2_airline":[["2026-10-18",0.7433332500000001]],"otis_mock_aime":[["2026-10-18",0.9333333333333333]],"simpleqa_verified":[["2026-10-18",0.34]],"swe_bench_verified":[["2026-10-18",0.7417]]}},"glm-5-2":{"points":[["2026-10-18",120.828705]],"inputs":{"chess_puzzles":[["2026-10-18",0.22]],"frontiermath_t13":[["2026-10-18",0.592057761732852]],"frontiermath_t4":[["2026-10-18",0.2926829268292683]],"gpqa_diamond":[["2026-10-18",0.9185606060606061]],"mystery_game_puzzles":[["2026-10-18",0.19]],"or_gpqa_diamond":[["2026-10-18",0.8334862727272728]],"or_tau2_airline":[["2026-10-18",0.7169697272727272]],"otis_mock_aime":[["2026-10-18",0.8638888888888889]],"simpleqa_verified":[["2026-10-18",0.342]],"swe_bench_verified":[["2026-10-18",0.787]]}},"glm-5-3":{"points":[["2026-10-18",125.317001]],"inputs":{"chess_puzzles":[["2026-10-18",0.37]],"frontiermath_t13":[["2026-10-18",0.6877192982456141]],"frontiermath_t4":[["2026-10-18",0.2926829268292683]],"gpqa_diamond":[["2026-10-18",0.9090909090909091]],"mystery_game_puzzles":[["2026-10-18",0.33]],"or_gpqa_diamond":[["2026-10-18",0.8639263412162163]],"or_tau2_airline":[["2026-10-18",0.78083325]],"otis_mock_aime":[["2026-10-18",0.9111111111111111]],"simpleqa_verified":[["2026-10-18",0.41]]}},"glm-5-3-flash":{"points":[["2026-10-18",120.48501]],"inputs":{"chess_puzzles":[["2026-10-18",0.21]],"frontiermath_t13":[["2026-10-18",0.5578947368421052]],"frontiermath_t4":[["2026-10-18",0.17073170731707318]],"gpqa_diamond":[["2026-10-18",0.9015151515151515]],"mystery_game_puzzles":[["2026-10-18",0.08]],"or_gpqa_diamond":[["2026-10-18",0.9090909999999999]],"or_tau2_airline":[["2026-10-18",0.762499875]],"otis_mock_aime":[["2026-10-18",0.9388888888888889]]}},"gpt-3-5-turbo-jan-2024":{"points":[["2026-10-18",47.24561]],"inputs":{"frontiermath_t13":[["2026-10-18",0.0]],"gpqa_diamond":[["2026-10-18",0.27178030303030304]],"math_level_5":[["2026-10-18",0.1163141993957704]],"mystery_game_puzzles":[["2026-10-18",0.03]],"otis_mock_aime":[["2026-10-18",0.022222222222222223]]}},"gpt-3-5-turbo-nov-2023":{"points":[["2026-10-18",49.269437]],"inputs":{"gpqa_diamond":[["2026-10-18",0.2803030303030303]],"math_level_5":[["2026-10-18",0.15889350453172205]]}},"gpt-4-1":{"points":[["2026-10-18",90.890771]],"inputs":{"aider_polyglot":[["2026-10-18",0.524]],"bfcl_overall":[["2026-10-18",0.5396]],"chess_puzzles":[["2026-10-18",0.03]],"frontiermath_t13":[["2026-10-18",0.05964912280701754]],"gpqa_diamond":[["2026-10-18",0.6691919191919192]],"math_level_5":[["2026-10-18",0.8300604229607251]],"or_gpqa_diamond":[["2026-10-18",0.6607744999999999]],"or_tau2_airline":[["2026-10-18",0.5083332500000001]],"otis_mock_aime":[["2026-10-18",0.38333333333333336]],"simpleqa_verified":[["2026-10-18",0.311]],"swe_bench_verified":[["2026-10-18",0.48541666666666666]]}},"gpt-4-1-mini":{"points":[["2026-10-18",91.359831]],"inputs":{"aider_polyglot":[["2026-10-18",0.324]],"bfcl_overall":[["2026-10-18",0.5045000000000001]],"chess_puzzles":[["2026-10-18",0.01]],"frontiermath_t13":[["2026-10-18",0.06666666666666667]],"gpqa_diamond":[["2026-10-18",0.6584595959595959]],"math_level_5":[["2026-10-18",0.8729229607250756]],"mystery_game_puzzles":[["2026-10-18",0.07]],"or_gpqa_diamond":[["2026-10-18",0.6473065000000001]],"or_tau2_airline":[["2026-10-18",0.44333325]],"otis_mock_aime":[["2026-10-18",0.44722222222222224]],"simpleqa_verified":[["2026-10-18",0.127]]}},"gpt-4-1-nano":{"points":[["2026-10-18",76.069944]],"inputs":{"aider_polyglot":[["2026-10-18",0.08900000000000001]],"bfcl_overall":[["2026-10-18",0.33049999999999996]],"chess_puzzles":[["2026-10-18",0.0]],"gpqa_diamond":[["2026-10-18",0.48926767676767674]],"math_level_5":[["2026-10-18",0.6999622356495468]],"or_gpqa_diamond":[["2026-10-18",0.4966332500000001]],"or_tau2_airline":[["2026-10-18",0.11833325]],"otis_mock_aime":[["2026-10-18",0.28888888888888886]],"simpleqa_verified":[["2026-10-18",0.06]]}},"gpt-4-5":{"points":[["2026-10-18",87.176142]],"inputs":{"gpqa_diamond":[["2026-10-18",0.6868686868686869]],"math_level_5":[["2026-10-18",0.7862537764350453]],"otis_mock_aime":[["2026-10-18",0.37777777777777777]]}},"gpt-4-jun-2023":{"points":[["2026-10-18",56.992031]],"inputs":{"gpqa_diamond":[["2026-10-18",0.30650252525252525]],"math_level_5":[["2026-10-18",0.22970166163141995]],"mystery_game_puzzles":[["2026-10-18",0.12]],"otis_mock_aime":[["2026-10-18",0.011111111111111112]]}},"gpt-4-mar-2023":{"points":[["2026-10-18",52.45167]],"inputs":{"gpqa_diamond":[["2026-10-18",0.3573232323232323]],"otis_mock_aime":[["2026-10-18",0.005555555555555556]]}},"gpt-4-turbo-apr-2024":{"points":[["2026-10-18",68.394]],"inputs":{"frontiermath_t13":[["2026-10-18",0.007017543859649123]],"gpqa_diamond":[["2026-10-18",0.4659090909090909]],"math_level_5":[["2026-10-18",0.46733383685800606]],"otis_mock_aime":[["2026-10-18",0.06666666666666667]]}},"gpt-4o-aug-2024":{"points":[["2026-10-18",72.716979]],"inputs":{"aider_polyglot":[["2026-10-18",0.231]],"chess_puzzles":[["2026-10-18",0.06]],"frontiermath_t13":[["2026-10-18",0.0035087719298245615]],"gpqa_diamond":[["2026-10-18",0.49210858585858586]],"math_level_5":[["2026-10-18",0.5327605740181269]],"or_gpqa_diamond":[["2026-10-18",0.5280586666666666]],"or_tau2_airline":[["2026-10-18",0.43]],"otis_mock_aime":[["2026-10-18",0.06388888888888888]],"simpleqa_verified":[["2026-10-18",0.26]]}},"gpt-4o-may-2024":{"points":[["2026-10-18",70.330327]],"inputs":{"gpqa_diamond":[["2026-10-18",0.4889520202020202]],"math_level_5":[["2026-10-18",0.5104796072507553]],"or_gpqa_diamond":[["2026-10-18",0.542088]],"or_tau2_airline":[["2026-10-18",0.44]],"otis_mock_aime":[["2026-10-18",0.0625]]}},"gpt-4o-mini":{"points":[["2026-10-18",68.3347]],"inputs":{"aider_polyglot":[["2026-10-18",0.036000000000000004]],"chess_puzzles":[["2026-10-18",0.03]],"frontiermath_t13":[["2026-10-18",0.007017543859649123]],"gpqa_diamond":[["2026-10-18",0.37720959595959597]],"math_level_5":[["2026-10-18",0.5263406344410876]],"mystery_game_puzzles":[["2026-10-18",0.12]],"or_gpqa_diamond":[["2026-10-18",0.4305555]],"or_tau2_airline":[["2026-10-18",0.28000025]],"otis_mock_aime":[["2026-10-18",0.06944444444444445]],"simpleqa_verified":[["2026-10-18",0.083]]}},"gpt-4o-nov-2024":{"points":[["2026-10-18",68.663029]],"inputs":{"aider_polyglot":[["2026-10-18",0.182]],"gpqa_diamond":[["2026-10-18",0.4788510101010101]],"math_level_5":[["2026-10-18",0.49773413897280966]],"otis_mock_aime":[["2026-10-18",0.0625]],"swe_bench_verified":[["2026-10-18",0.30991735537190085]]}},"gpt-5":{"points":[["2026-10-18",120.877122]],"inputs":{"aider_polyglot":[["2026-10-18",0.88]],"chess_puzzles":[["2026-10-18",0.36]],"frontiermath_t13":[["2026-10-18",0.5543859649122806]],"frontiermath_t4":[["2026-10-18",0.21951219512195122]],"gpqa_diamond":[["2026-10-18",0.8617424242424242]],"math_level_5":[["2026-10-18",0.9813066465256798]],"mystery_game_puzzles":[["2026-10-18",0.23]],"or_gpqa_diamond":[["2026-10-18",0.8501685000000001]],"or_tau2_airline":[["2026-10-18",0.7066666666666667]],"otis_mock_aime":[["2026-10-18",0.9138888888888889]],"simpleqa_verified":[["2026-10-18",0.501]],"swe_bench_verified":[["2026-10-18",0.7355371900826446]]}},"gpt-5-1":{"points":[["2026-10-18",120.181966]],"inputs":{"chess_puzzles":[["2026-10-18",0.42]],"gpqa_diamond":[["2026-10-18",0.8762626262626263]],"mystery_game_puzzles":[["2026-10-18",0.19]],"or_gpqa_diamond":[["2026-10-18",0.8692479999999999]],"or_tau2_airline":[["2026-10-18",0.7583332500000001]],"otis_mock_aime":[["2026-10-18",0.8861111111111111]],"simpleqa_verified":[["2026-10-18",0.48]],"swe_bench_verified":[["2026-10-18",0.6797520661157025]]}},"gpt-5-2":{"points":[["2026-10-18",125.057666]],"inputs":{"bfcl_overall":[["2026-10-18",0.5587]],"chess_puzzles":[["2026-10-18",0.48]],"frontiermath_t13":[["2026-10-18",0.674]],"frontiermath_t4":[["2026-10-18",0.317]],"gpqa_diamond":[["2026-10-18",0.914]],"mystery_game_puzzles":[["2026-10-18",0.23]],"or_gpqa_diamond":[["2026-10-18",0.878788]],"or_tau2_airline":[["2026-10-18",0.726667]],"otis_mock_aime":[["2026-10-18",0.9611111111111111]],"simpleqa_verified":[["2026-10-18",0.371]],"swe_bench_verified":[["2026-10-18",0.737603305785124]]}},"gpt-5-2-pro":{"points":[["2026-10-18",131.577476]],"inputs":{"chess_puzzles":[["2026-10-18",0.6]],"frontiermath_t13":[["2026-10-18",0.74]],"frontiermath_t4":[["2026-10-18",0.46]]}},"gpt-5-3-codex":{"points":[["2026-10-18",122.34523]],"inputs":{"or_tau2_airline":[["2026-10-18",0.753333]],"swe_bench_verified":[["2026-10-18",0.7479338842975206]]}},"gpt-5-4":{"points":[["2026-10-18",130.558237]],"inputs":{"chess_puzzles":[["2026-10-18",0.48]],"frontiermath_t13":[["2026-10-18",0.7859649122807018]],"frontiermath_t4":[["2026-10-18",0.49]],"gpqa_diamond":[["2026-10-18",0.933]],"mystery_game_puzzles":[["2026-10-18",0.37]],"or_gpqa_diamond":[["2026-10-18",0.899551]],"or_tau2_airline":[["2026-10-18",0.73166675]],"otis_mock_aime":[["2026-10-18",0.9777777777777777]],"simpleqa_verified":[["2026-10-18",0.451]],"swe_bench_verified":[["2026-10-18",0.768595041322314]]}},"gpt-5-4-mini":{"points":[["2026-10-18",116.63886]],"inputs":{"chess_puzzles":[["2026-10-18",0.23]],"frontiermath_t13":[["2026-10-18",0.512280701754386]],"frontiermath_t4":[["2026-10-18",0.0975609756097561]],"gpqa_diamond":[["2026-10-18",0.8686868686868687]],"mystery_game_puzzles":[["2026-10-18",0.11]],"or_gpqa_diamond":[["2026-10-18",0.84048825]],"or_tau2_airline":[["2026-10-18",0.6216667499999999]],"otis_mock_aime":[["2026-10-18",0.8888888888888888]],"simpleqa_verified":[["2026-10-18",0.294]]}},"gpt-5-4-nano":{"points":[["2026-10-18",118.048443]],"inputs":{"chess_puzzles":[["2026-10-18",0.45]],"frontiermath_t13":[["2026-10-18",0.44912280701754387]],"frontiermath_t4":[["2026-10-18",0.12195121951219512]],"gpqa_diamond":[["2026-10-18",0.7847]],"mystery_game_puzzles":[["2026-10-18",0.09]],"or_gpqa_diamond":[["2026-10-18",0.77567325]],"or_tau2_airline":[["2026-10-18",0.65166675]],"otis_mock_aime":[["2026-10-18",0.8778]],"simpleqa_verified":[["2026-10-18",0.117]]}},"gpt-5-4-pro":{"points":[["2026-10-18",134.573855]],"inputs":{"chess_puzzles":[["2026-10-18",0.59]],"frontiermath_t13":[["2026-10-18",0.8245614035087719]],"frontiermath_t4":[["2026-10-18",0.5853658536585366]],"gpqa_diamond":[["2026-10-18",0.946]],"simpleqa_verified":[["2026-10-18",0.463]]}},"gpt-5-5":{"points":[["2026-10-18",137.899323]],"inputs":{"chess_puzzles":[["2026-10-18",0.63]],"frontiermath_t13":[["2026-10-18",0.8526315789473684]],"frontiermath_t4":[["2026-10-18",0.725]],"gpqa_diamond":[["2026-10-18",0.9400252525252525]],"mystery_game_puzzles":[["2026-10-18",0.56]],"or_gpqa_diamond":[["2026-10-18",0.9360266666666668]],"or_tau2_airline":[["2026-10-18",0.75]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.63]],"swe_bench_verified":[["2026-10-18",0.8057851239669421]]}},"gpt-5-5-instant":{"points":[["2026-10-18",107.424343]],"inputs":{"frontiermath_t13":[["2026-10-18",0.2631578947368421]],"frontiermath_t4":[["2026-10-18",0.024390243902439025]],"gpqa_diamond":[["2026-10-18",0.8251262626262627]],"otis_mock_aime":[["2026-10-18",0.6805555555555556]]}},"gpt-5-5-pro":{"points":[["2026-10-18",138.922723]],"inputs":{"chess_puzzles":[["2026-10-18",0.62]],"frontiermath_t13":[["2026-10-18",0.8771929824561403]],"frontiermath_t4":[["2026-10-18",0.7804878048780488]],"gpqa_diamond":[["2026-10-18",0.9392135642135643]],"otis_mock_aime":[["2026-10-18",1.0]]}},"gpt-5-6-luna":{"points":[["2026-10-18",130.398277]],"inputs":{"chess_puzzles":[["2026-10-18",0.43]],"frontiermath_t13":[["2026-10-18",0.8210526315789474]],"frontiermath_t4":[["2026-10-18",0.6097560975609756]],"gpqa_diamond":[["2026-10-18",0.9160353535353535]],"mystery_game_puzzles":[["2026-10-18",0.21]],"or_gpqa_diamond":[["2026-10-18",0.8724745]],"or_tau2_airline":[["2026-10-18",0.72333325]],"otis_mock_aime":[["2026-10-18",0.9833333333333333]],"simpleqa_verified":[["2026-10-18",0.41]]}},"gpt-5-6-sol":{"points":[["2026-10-18",140.009993]],"inputs":{"chess_puzzles":[["2026-10-18",0.59]],"frontiermath_t13":[["2026-10-18",0.8912280701754386]],"frontiermath_t4":[["2026-10-18",0.8292682926829268]],"gpqa_diamond":[["2026-10-18",0.9349747474747475]],"mystery_game_puzzles":[["2026-10-18",0.58]],"or_gpqa_diamond":[["2026-10-18",0.9234005000000001]],"or_tau2_airline":[["2026-10-18",0.73333325]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.697]]}},"gpt-5-6-terra":{"points":[["2026-10-18",133.778794]],"inputs":{"chess_puzzles":[["2026-10-18",0.47]],"frontiermath_t13":[["2026-10-18",0.8596491228070176]],"frontiermath_t4":[["2026-10-18",0.7073170731707317]],"gpqa_diamond":[["2026-10-18",0.9330808080808081]],"mystery_game_puzzles":[["2026-10-18",0.35]],"or_gpqa_diamond":[["2026-10-18",0.89267675]],"or_tau2_airline":[["2026-10-18",0.715]],"otis_mock_aime":[["2026-10-18",0.9972222222222222]],"simpleqa_verified":[["2026-10-18",0.432]]}},"gpt-5-mini":{"points":[["2026-10-18",114.882385]],"inputs":{"bfcl_overall":[["2026-10-18",0.5546]],"chess_puzzles":[["2026-10-18",0.24]],"frontiermath_t13":[["2026-10-18",0.4666666666666667]],"frontiermath_t4":[["2026-10-18",0.12195121951219512]],"gpqa_diamond":[["2026-10-18",0.75]],"math_level_5":[["2026-10-18",0.9784743202416919]],"mystery_game_puzzles":[["2026-10-18",0.1]],"or_gpqa_diamond":[["2026-10-18",0.8007853333333332]],"or_tau2_airline":[["2026-10-18",0.712121101010101]],"otis_mock_aime":[["2026-10-18",0.8666666666666667]],"simpleqa_verified":[["2026-10-18",0.216]],"swe_bench_verified":[["2026-10-18",0.6466942148760331]]}},"gpt-5-nano":{"points":[["2026-10-18",105.459994]],"inputs":{"bfcl_overall":[["2026-10-18",0.5145000000000001]],"chess_puzzles":[["2026-10-18",0.22]],"frontiermath_t13":[["2026-10-18",0.2]],"frontiermath_t4":[["2026-10-18",0.024390243902439025]],"gpqa_diamond":[["2026-10-18",0.6944444444444444]],"math_level_5":[["2026-10-18",0.952416918429003]],"mystery_game_puzzles":[["2026-10-18",0.09]],"or_gpqa_diamond":[["2026-10-18",0.6843435000000001]],"or_tau2_airline":[["2026-10-18",0.4511785656565656]],"otis_mock_aime":[["2026-10-18",0.8111111111111111]],"simpleqa_verified":[["2026-10-18",0.117]]}},"gpt-5-pro":{"points":[["2026-10-18",123.991681]],"inputs":{"chess_puzzles":[["2026-10-18",0.48]],"frontiermath_t13":[["2026-10-18",0.5578947368421052]],"frontiermath_t4":[["2026-10-18",0.1951219512195122]]}},"gpt-6-1-sol":{"points":[["2026-10-18",147.933918]],"inputs":{"chess_puzzles":[["2026-10-18",0.68]],"frontiermath_t13":[["2026-10-18",0.9368421052631579]],"frontiermath_t4":[["2026-10-18",1.0]],"gpqa_diamond":[["2026-10-18",0.9539141414141414]],"mystery_game_puzzles":[["2026-10-18",0.8]],"or_gpqa_diamond":[["2026-10-18",0.944444]],"or_tau2_airline":[["2026-10-18",0.6822223333333333]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.739]]}},"gpt-6-astra":{"points":[["2026-10-18",149.64338]],"inputs":{"chess_puzzles":[["2026-10-18",0.74]],"frontiermath_t13":[["2026-10-18",0.9368421052631579]],"frontiermath_t4":[["2026-10-18",0.976]],"gpqa_diamond":[["2026-10-18",0.9577020202020202]],"mystery_game_puzzles":[["2026-10-18",0.84]],"or_gpqa_diamond":[["2026-10-18",0.9472503333333333]],"or_tau2_airline":[["2026-10-18",0.6766665000000001]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.756]]}},"gpt-6-luna":{"points":[["2026-10-18",130.205674]],"inputs":{"chess_puzzles":[["2026-10-18",0.36]],"frontiermath_t13":[["2026-10-18",0.7894736842105263]],"frontiermath_t4":[["2026-10-18",0.5609756097560976]],"gpqa_diamond":[["2026-10-18",0.9046717171717171]],"mystery_game_puzzles":[["2026-10-18",0.07]],"or_gpqa_diamond":[["2026-10-18",0.8815936666666665]],"or_tau2_airline":[["2026-10-18",0.68]],"otis_mock_aime":[["2026-10-18",0.9888888888888889]],"simpleqa_verified":[["2026-10-18",0.414]]}},"gpt-6-sol":{"points":[["2026-10-18",140.290228]],"inputs":{"chess_puzzles":[["2026-10-18",0.56]],"frontiermath_t13":[["2026-10-18",0.8982456140350877]],"frontiermath_t4":[["2026-10-18",0.9]],"gpqa_diamond":[["2026-10-18",0.9431818181818182]],"mystery_game_puzzles":[["2026-10-18",0.56]],"or_gpqa_diamond":[["2026-10-18",0.9208749999999999]],"or_tau2_airline":[["2026-10-18",0.7022223333333333]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.607]]}},"gpt-oss-120b":{"points":[["2026-10-18",105.803533]],"inputs":{"aider_polyglot":[["2026-10-18",0.418]],"gpqa_diamond":[["2026-10-18",0.7575757575757576]],"mystery_game_puzzles":[["2026-10-18",0.02]],"or_gpqa_diamond":[["2026-10-18",0.7578456145038168]],"or_tau2_airline":[["2026-10-18",0.633333]],"otis_mock_aime":[["2026-10-18",0.8888888888888888]]}},"gpt-oss-20b":{"points":[["2026-10-18",95.050382]],"inputs":{"gpqa_diamond":[["2026-10-18",0.6079545454545454]],"or_gpqa_diamond":[["2026-10-18",0.6311448]],"or_tau2_airline":[["2026-10-18",0.4672696511627907]],"otis_mock_aime":[["2026-10-18",0.6527777777777778]]}},"granite-4-0-1b":{"points":[["2026-10-18",55.457304]],"inputs":{"gpqa_diamond":[["2026-10-18",0.2398989898989899]],"otis_mock_aime":[["2026-10-18",0.008333333333333333]]}},"granite-4-0-350m":{"points":[["2026-10-18",52.500587]],"inputs":{"bfcl_overall":[["2026-10-18",0.1898]],"gpqa_diamond":[["2026-10-18",0.11237373737373738]],"otis_mock_aime":[["2026-10-18",0.002777777777777778]]}},"granite-4-0-micro":{"points":[["2026-10-18",54.107791]],"inputs":{"gpqa_diamond":[["2026-10-18",0.2828282828282828]],"otis_mock_aime":[["2026-10-18",0.027777777777777776]]}},"grok-2-dec-2024":{"points":[["2026-10-18",75.254353]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5378787878787878]],"math_level_5":[["2026-10-18",0.6351963746223565]],"otis_mock_aime":[["2026-10-18",0.11527777777777778]]}},"grok-3":{"points":[["2026-10-18",95.810051]],"inputs":{"aider_polyglot":[["2026-10-18",0.5329999999999999]],"gpqa_diamond":[["2026-10-18",0.7575757575757576]],"math_level_5":[["2026-10-18",0.8874622356495468]],"otis_mock_aime":[["2026-10-18",0.5555555555555556]]}},"grok-3-mini":{"points":[["2026-10-18",100.014969]],"inputs":{"aider_polyglot":[["2026-10-18",0.493]],"gpqa_diamond":[["2026-10-18",0.7626262626262627]],"math_level_5":[["2026-10-18",0.9093655589123867]],"otis_mock_aime":[["2026-10-18",0.7777777777777778]]}},"grok-4":{"points":[["2026-10-18",113.612472]],"inputs":{"aider_polyglot":[["2026-10-18",0.7959999999999999]],"bfcl_overall":[["2026-10-18",0.6297]],"gpqa_diamond":[["2026-10-18",0.87]],"otis_mock_aime":[["2026-10-18",0.84]]}},"grok-4-3-beta":{"points":[["2026-10-18",117.215737]],"inputs":{"chess_puzzles":[["2026-10-18",0.18]],"frontiermath_t13":[["2026-10-18",0.4280701754385965]],"frontiermath_t4":[["2026-10-18",0.14634146341463414]],"gpqa_diamond":[["2026-10-18",0.8882575757575758]],"otis_mock_aime":[["2026-10-18",0.9333333333333333]],"simpleqa_verified":[["2026-10-18",0.332]]}},"grok-4-5":{"points":[["2026-10-18",124.152844]],"inputs":{"chess_puzzles":[["2026-10-18",0.35]],"frontiermath_t13":[["2026-10-18",0.5719298245614035]],"frontiermath_t4":[["2026-10-18",0.24390243902439024]],"gpqa_diamond":[["2026-10-18",0.9343434343434344]],"otis_mock_aime":[["2026-10-18",0.9777777777777777]],"simpleqa_verified":[["2026-10-18",0.483]]}},"grok-4-6":{"points":[["2026-10-18",126.277642]],"inputs":{"chess_puzzles":[["2026-10-18",0.33]],"frontiermath_t13":[["2026-10-18",0.6596491228070176]],"frontiermath_t4":[["2026-10-18",0.3170731707317073]],"gpqa_diamond":[["2026-10-18",0.9400252525252525]],"mystery_game_puzzles":[["2026-10-18",0.34]],"or_gpqa_diamond":[["2026-10-18",0.9246375695652174]],"or_tau2_airline":[["2026-10-18",0.747619]],"otis_mock_aime":[["2026-10-18",0.9916666666666667]],"simpleqa_verified":[["2026-10-18",0.493]]}},"grok-4-7":{"points":[["2026-10-18",123.383422]],"inputs":{"chess_puzzles":[["2026-10-18",0.41]],"frontiermath_t13":[["2026-10-18",0.5298245614035088]],"frontiermath_t4":[["2026-10-18",0.17073170731707318]],"gpqa_diamond":[["2026-10-18",0.92739898989899]],"mystery_game_puzzles":[["2026-10-18",0.29]],"otis_mock_aime":[["2026-10-18",0.9805555555555555]],"simpleqa_verified":[["2026-10-18",0.56]]}},"hermes-2-theta-llama-3-70b":{"points":[["2026-10-18",55.34914]],"inputs":{"gpqa_diamond":[["2026-10-18",0.3746843434343434]],"math_level_5":[["2026-10-18",0.22686933534743203]],"otis_mock_aime":[["2026-10-18",0.025]]}},"inkling":{"points":[["2026-10-18",113.551686]],"inputs":{"chess_puzzles":[["2026-10-18",0.21]],"frontiermath_t13":[["2026-10-18",0.3333333333333333]],"frontiermath_t4":[["2026-10-18",0.04878048780487805]],"gpqa_diamond":[["2026-10-18",0.8825757575757576]],"or_gpqa_diamond":[["2026-10-18",0.818035862576065]],"or_tau2_airline":[["2026-10-18",0.6755556666666667]],"otis_mock_aime":[["2026-10-18",0.8888888888888888]],"simpleqa_verified":[["2026-10-18",0.403]]}},"inkling-small":{"points":[["2026-10-18",118.11501]],"inputs":{"frontiermath_t13":[["2026-10-18",0.4631578947368421]],"frontiermath_t4":[["2026-10-18",0.17073170731707318]],"gpqa_diamond":[["2026-10-18",0.88510101010101]],"mystery_game_puzzles":[["2026-10-18",0.06]],"or_gpqa_diamond":[["2026-10-18",0.8703701666666666]],"or_tau2_airline":[["2026-10-18",0.6076188571428572]],"otis_mock_aime":[["2026-10-18",0.9]],"simpleqa_verified":[["2026-10-18",0.191]]}},"kimi-k2-5":{"points":[["2026-10-18",118.816495]],"inputs":{"gpqa_diamond":[["2026-10-18",0.876]],"or_gpqa_diamond":[["2026-10-18",0.8592592]],"or_tau2_airline":[["2026-10-18",0.7277775]],"otis_mock_aime":[["2026-10-18",0.922]],"simpleqa_verified":[["2026-10-18",0.343]],"swe_bench_verified":[["2026-10-18",0.737603305785124]]}},"kimi-k2-6":{"points":[["2026-10-18",121.047867]],"inputs":{"chess_puzzles":[["2026-10-18",0.2]],"frontiermath_t13":[["2026-10-18",0.5719298245614035]],"frontiermath_t4":[["2026-10-18",0.2564102564102564]],"gpqa_diamond":[["2026-10-18",0.9078282828282829]],"mystery_game_puzzles":[["2026-10-18",0.18]],"or_gpqa_diamond":[["2026-10-18",0.8799901428571427]],"or_tau2_airline":[["2026-10-18",0.7671130223214285]],"otis_mock_aime":[["2026-10-18",0.9611111111111111]],"simpleqa_verified":[["2026-10-18",0.349]],"swe_bench_verified":[["2026-10-18",0.7665289256198347]]}},"kimi-k2-7-code":{"points":[["2026-10-18",118.46375]],"inputs":{"chess_puzzles":[["2026-10-18",0.14]],"frontiermath_t13":[["2026-10-18",0.5403508771929825]],"frontiermath_t4":[["2026-10-18",0.12195121951219512]],"gpqa_diamond":[["2026-10-18",0.8787878787878788]],"or_gpqa_diamond":[["2026-10-18",0.8847767229341582]],"or_tau2_airline":[["2026-10-18",0.7383231627502177]],"otis_mock_aime":[["2026-10-18",0.9555555555555556]],"simpleqa_verified":[["2026-10-18",0.365]]}},"kimi-k2-sep-2025":{"points":[["2026-10-18",105.120912]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.7474749999999999]],"or_tau2_airline":[["2026-10-18",0.6366665]]}},"kimi-k2-thinking":{"points":[["2026-10-18",112.401053]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.796581]],"or_tau2_airline":[["2026-10-18",0.695]]}},"kimi-k3":{"points":[["2026-10-18",127.057795]],"inputs":{"chess_puzzles":[["2026-10-18",0.37]],"frontiermath_t13":[["2026-10-18",0.721830985915493]],"frontiermath_t4":[["2026-10-18",0.3902439024390244]],"gpqa_diamond":[["2026-10-18",0.9311868686868687]],"mystery_game_puzzles":[["2026-10-18",0.26]],"or_gpqa_diamond":[["2026-10-18",0.9157357830756013]],"or_tau2_airline":[["2026-10-18",0.7347416579476861]],"otis_mock_aime":[["2026-10-18",0.9722222222222222]],"simpleqa_verified":[["2026-10-18",0.506]]}},"llama-3-1-405b":{"points":[["2026-10-18",70.329938]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5091540404040404]],"math_level_5":[["2026-10-18",0.49773413897280966]],"otis_mock_aime":[["2026-10-18",0.09722222222222222]]}},"llama-3-1-70b":{"points":[["2026-10-18",63.16128]],"inputs":{"gpqa_diamond":[["2026-10-18",0.44191919191919193]],"math_level_5":[["2026-10-18",0.36678625377643503]],"otis_mock_aime":[["2026-10-18",0.03611111111111111]]}},"llama-3-1-8b":{"points":[["2026-10-18",54.631296]],"inputs":{"gpqa_diamond":[["2026-10-18",0.26957070707070707]],"math_level_5":[["2026-10-18",0.22875755287009064]],"or_gpqa_diamond":[["2026-10-18",0.26941151269035535]],"otis_mock_aime":[["2026-10-18",0.016666666666666666]]}},"llama-3-2-1b":{"points":[["2026-10-18",42.095115]],"inputs":{"bfcl_overall":[["2026-10-18",0.1082]],"gpqa_diamond":[["2026-10-18",0.23926767676767677]],"otis_mock_aime":[["2026-10-18",0.005555555555555556]]}},"llama-3-2-3b":{"points":[["2026-10-18",60.943338]],"inputs":{"bfcl_overall":[["2026-10-18",0.2195]],"or_gpqa_diamond":[["2026-10-18",0.17340049999999999]]}},"llama-3-3-70b":{"points":[["2026-10-18",66.185326]],"inputs":{"bfcl_overall":[["2026-10-18",0.319]],"gpqa_diamond":[["2026-10-18",0.4744318181818182]],"math_level_5":[["2026-10-18",0.41597432024169184]],"or_gpqa_diamond":[["2026-10-18",0.4753785]],"or_tau2_airline":[["2026-10-18",0.313333]],"otis_mock_aime":[["2026-10-18",0.05138888888888889]]}},"llama-3-70b":{"points":[["2026-10-18",56.918261]],"inputs":{"gpqa_diamond":[["2026-10-18",0.40561868686868685]],"math_level_5":[["2026-10-18",0.225547583081571]],"otis_mock_aime":[["2026-10-18",0.043055555555555555]]}},"llama-3-8b":{"points":[["2026-10-18",39.747898]],"inputs":{"gpqa_diamond":[["2026-10-18",0.26073232323232326]],"math_level_5":[["2026-10-18",0.0612726586102719]],"otis_mock_aime":[["2026-10-18",0.019444444444444445]]}},"llama-4-maverick":{"points":[["2026-10-18",80.843677]],"inputs":{"aider_polyglot":[["2026-10-18",0.156]],"bfcl_overall":[["2026-10-18",0.3729]],"gpqa_diamond":[["2026-10-18",0.6698232323232324]],"math_level_5":[["2026-10-18",0.7301737160120846]],"or_gpqa_diamond":[["2026-10-18",0.6478116]],"or_tau2_airline":[["2026-10-18",0.43089426016260163]],"otis_mock_aime":[["2026-10-18",0.20555555555555555]]}},"llama-4-scout":{"points":[["2026-10-18",73.309928]],"inputs":{"bfcl_overall":[["2026-10-18",0.2813]],"gpqa_diamond":[["2026-10-18",0.5183080808080808]],"math_level_5":[["2026-10-18",0.6227341389728097]],"otis_mock_aime":[["2026-10-18",0.07777777777777778]]}},"magistral-small-1-0":{"points":[["2026-10-18",82.794326]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5606060606060606]],"otis_mock_aime":[["2026-10-18",0.3]]}},"magistral-small-1-2":{"points":[["2026-10-18",79.082879]],"inputs":{"gpqa_diamond":[["2026-10-18",0.476010101010101]],"otis_mock_aime":[["2026-10-18",0.28055555555555556]]}},"mimo-v2-5":{"points":[["2026-10-18",117.337743]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.8239975454545455]],"or_tau2_airline":[["2026-10-18",0.7372220833333334]]}},"mimo-v2-5-pro":{"points":[["2026-10-18",121.31747]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.8550657272727274]],"or_tau2_airline":[["2026-10-18",0.743889]]}},"mimo-v2-6-flash":{"points":[["2026-10-18",111.895076]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.758698]],"or_tau2_airline":[["2026-10-18",0.76]]}},"mimo-v2-6-pro":{"points":[["2026-10-18",130.644209]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.8989897499999999]],"or_tau2_airline":[["2026-10-18",0.7983335000000001]]}},"minimax-m2-1":{"points":[["2026-10-18",119.616221]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.868687]],"or_tau2_airline":[["2026-10-18",0.6783334999999999]]}},"minimax-m2-5":{"points":[["2026-10-18",118.418933]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.8539973475609757]],"or_tau2_airline":[["2026-10-18",0.6905556666666667]]}},"minimax-m2-7":{"points":[["2026-10-18",120.339276]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.8570973081339713]],"or_tau2_airline":[["2026-10-18",0.7203921764705883]]}},"minimax-m3":{"points":[["2026-10-18",108.208916]],"inputs":{"chess_puzzles":[["2026-10-18",0.13]],"gpqa_diamond":[["2026-10-18",0.9090909090909091]],"mystery_game_puzzles":[["2026-10-18",0.08]],"or_gpqa_diamond":[["2026-10-18",0.9151233333333333]],"or_tau2_airline":[["2026-10-18",0.7388889166666667]],"otis_mock_aime":[["2026-10-18",0.7111111111111111]]}},"ministral-3b":{"points":[["2026-10-18",48.793371]],"inputs":{"gpqa_diamond":[["2026-10-18",0.25252525252525254]],"math_level_5":[["2026-10-18",0.14444864048338368]]}},"ministral-8b":{"points":[["2026-10-18",47.122179]],"inputs":{"bfcl_overall":[["2026-10-18",0.111]],"gpqa_diamond":[["2026-10-18",0.27146464646464646]],"math_level_5":[["2026-10-18",0.14935800604229607]]}},"mistral-7b-v0-3":{"points":[["2026-10-18",54.34396]],"inputs":{"gpqa_diamond":[["2026-10-18",0.1518308080808081]],"otis_mock_aime":[["2026-10-18",0.002777777777777778]]}},"mistral-large":{"points":[["2026-10-18",56.357651]],"inputs":{"gpqa_diamond":[["2026-10-18",0.38762626262626265]],"math_level_5":[["2026-10-18",0.24461858006042297]],"otis_mock_aime":[["2026-10-18",0.019444444444444445]]}},"mistral-large-2-jul-2024":{"points":[["2026-10-18",68.180127]],"inputs":{"gpqa_diamond":[["2026-10-18",0.49021464646464646]],"math_level_5":[["2026-10-18",0.4481684290030212]],"otis_mock_aime":[["2026-10-18",0.08472222222222223]]}},"mistral-large-2-nov-2024":{"points":[["2026-10-18",71.077629]],"inputs":{"bfcl_overall":[["2026-10-18",0.3837]],"gpqa_diamond":[["2026-10-18",0.5132575757575758]],"math_level_5":[["2026-10-18",0.5028323262839879]],"otis_mock_aime":[["2026-10-18",0.07777777777777778]]}},"mistral-large-4":{"points":[["2026-10-18",121.910183]],"inputs":{"chess_puzzles":[["2026-10-18",0.33]],"frontiermath_t13":[["2026-10-18",0.5859649122807018]],"frontiermath_t4":[["2026-10-18",0.2682926829268293]],"gpqa_diamond":[["2026-10-18",0.8806818181818182]],"mystery_game_puzzles":[["2026-10-18",0.17]],"otis_mock_aime":[["2026-10-18",0.9833333333333333]],"simpleqa_verified":[["2026-10-18",0.2]]}},"mistral-medium-3":{"points":[["2026-10-18",85.578128]],"inputs":{"bfcl_overall":[["2026-10-18",0.37689999999999996]],"gpqa_diamond":[["2026-10-18",0.5953282828282829]],"math_level_5":[["2026-10-18",0.8162764350453172]],"otis_mock_aime":[["2026-10-18",0.32222222222222224]]}},"mistral-nemo":{"points":[["2026-10-18",46.809651]],"inputs":{"bfcl_overall":[["2026-10-18",0.2763]],"gpqa_diamond":[["2026-10-18",0.2989267676767677]],"math_level_5":[["2026-10-18",0.1082892749244713]]}},"mistral-small-3":{"points":[["2026-10-18",67.320283]],"inputs":{"gpqa_diamond":[["2026-10-18",0.47285353535353536]],"math_level_5":[["2026-10-18",0.4481684290030212]],"otis_mock_aime":[["2026-10-18",0.06666666666666667]]}},"mistral-small-3-1":{"points":[["2026-10-18",67.753997]],"inputs":{"gpqa_diamond":[["2026-10-18",0.47474747474747475]],"math_level_5":[["2026-10-18",0.4677114803625378]],"otis_mock_aime":[["2026-10-18",0.058333333333333334]]}},"mistral-small-3-2":{"points":[["2026-10-18",80.446582]],"inputs":{"bfcl_overall":[["2026-10-18",0.3715]],"gpqa_diamond":[["2026-10-18",0.49053030303030304]],"otis_mock_aime":[["2026-10-18",0.30277777777777776]]}},"mistral-small-4":{"points":[["2026-10-18",95.509383]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.7528056666666667]],"or_tau2_airline":[["2026-10-18",0.41142871428571426]]}},"mixtral-8x22b":{"points":[["2026-10-18",55.133518]],"inputs":{"gpqa_diamond":[["2026-10-18",0.34059343434343436]],"math_level_5":[["2026-10-18",0.24244712990936557]]}},"mixtral-8x7b":{"points":[["2026-10-18",43.328036]],"inputs":{"gpqa_diamond":[["2026-10-18",0.3058712121212121]],"math_level_5":[["2026-10-18",0.09950906344410876]]}},"muse-spark":{"points":[["2026-10-18",117.985106]],"inputs":{"gpqa_diamond":[["2026-10-18",0.898]],"otis_mock_aime":[["2026-10-18",0.889]]}},"muse-spark-1-1":{"points":[["2026-10-18",124.6582]],"inputs":{"chess_puzzles":[["2026-10-18",0.34]],"simpleqa_verified":[["2026-10-18",0.5778894472361809]]}},"muse-spark-1-2":{"points":[["2026-10-18",120.533692]],"inputs":{"chess_puzzles":[["2026-10-18",0.27]],"simpleqa_verified":[["2026-10-18",0.6030150753768844]]}},"muse-spark-1-3":{"points":[["2026-10-18",127.90137]],"inputs":{"chess_puzzles":[["2026-10-18",0.37]],"frontiermath_t13":[["2026-10-18",0.743859649122807]],"frontiermath_t4":[["2026-10-18",0.4634146341463415]],"mystery_game_puzzles":[["2026-10-18",0.25]],"otis_mock_aime":[["2026-10-18",0.9916666666666667]]}},"muse-spark-open":{"points":[["2026-10-18",127.07045]],"inputs":{"frontiermath_t13":[["2026-10-18",0.6982456140350877]],"frontiermath_t4":[["2026-10-18",0.3170731707317073]],"gpqa_diamond":[["2026-10-18",0.8857323232323232]],"or_gpqa_diamond":[["2026-10-18",0.905724]],"or_tau2_airline":[["2026-10-18",0.78]],"otis_mock_aime":[["2026-10-18",0.9805555555555555]],"simpleqa_verified":[["2026-10-18",0.566]]}},"muse-wonder":{"points":[["2026-10-18",135.970011]],"inputs":{"frontiermath_t13":[["2026-10-18",0.8210526315789474]],"frontiermath_t4":[["2026-10-18",0.7073170731707317]],"mystery_game_puzzles":[["2026-10-18",0.51]],"otis_mock_aime":[["2026-10-18",0.9944444444444445]]}},"nemotron-3-ultra":{"points":[["2026-10-18",114.161043]],"inputs":{"gpqa_diamond":[["2026-10-18",0.8535353535353535]],"mystery_game_puzzles":[["2026-10-18",0.2]],"or_tau2_airline":[["2026-10-18",0.72]],"otis_mock_aime":[["2026-10-18",0.8666666666666667]]}},"o1":{"points":[["2026-10-18",102.843258]],"inputs":{"chess_puzzles":[["2026-10-18",0.1]],"frontiermath_t13":[["2026-10-18",0.14736842105263157]],"gpqa_diamond":[["2026-10-18",0.7676767676767676]],"math_level_5":[["2026-10-18",0.947129909365559]],"otis_mock_aime":[["2026-10-18",0.7333333333333333]],"simpleqa_verified":[["2026-10-18",0.411]]}},"o1-mini":{"points":[["2026-10-18",91.599848]],"inputs":{"aider_polyglot":[["2026-10-18",0.32899999999999996]],"gpqa_diamond":[["2026-10-18",0.6237373737373737]],"math_level_5":[["2026-10-18",0.8918051359516617]],"otis_mock_aime":[["2026-10-18",0.46944444444444444]]}},"o1-preview":{"points":[["2026-10-18",84.171949]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5031565656565656]],"math_level_5":[["2026-10-18",0.8164652567975831]],"otis_mock_aime":[["2026-10-18",0.3111111111111111]]}},"o3":{"points":[["2026-10-18",115.912574]],"inputs":{"aider_polyglot":[["2026-10-18",0.813]],"bfcl_overall":[["2026-10-18",0.6305]],"chess_puzzles":[["2026-10-18",0.37]],"frontiermath_t13":[["2026-10-18",0.3333333333333333]],"gpqa_diamond":[["2026-10-18",0.8181818181818182]],"math_level_5":[["2026-10-18",0.9777190332326284]],"mystery_game_puzzles":[["2026-10-18",0.29]],"otis_mock_aime":[["2026-10-18",0.8444444444444444]],"simpleqa_verified":[["2026-10-18",0.494]],"swe_bench_verified":[["2026-10-18",0.6231884057971014]]}},"o3-mini":{"points":[["2026-10-18",104.840037]],"inputs":{"aider_polyglot":[["2026-10-18",0.5379999999999999]],"chess_puzzles":[["2026-10-18",0.15]],"frontiermath_t13":[["2026-10-18",0.18596491228070175]],"frontiermath_t4":[["2026-10-18",0.0]],"gpqa_diamond":[["2026-10-18",0.7702020202020202]],"math_level_5":[["2026-10-18",0.9648791540785498]],"mystery_game_puzzles":[["2026-10-18",0.07]],"otis_mock_aime":[["2026-10-18",0.7694444444444445]],"simpleqa_verified":[["2026-10-18",0.153]]}},"o3-pro":{"points":[["2026-10-18",119.181932]],"inputs":{"aider_polyglot":[["2026-10-18",0.8490000000000001]]}},"o4-mini":{"points":[["2026-10-18",111.712734]],"inputs":{"aider_polyglot":[["2026-10-18",0.72]],"bfcl_overall":[["2026-10-18",0.5324]],"chess_puzzles":[["2026-10-18",0.22]],"frontiermath_t13":[["2026-10-18",0.36140350877192984]],"frontiermath_t4":[["2026-10-18",0.04878048780487805]],"gpqa_diamond":[["2026-10-18",0.7960858585858586]],"math_level_5":[["2026-10-18",0.978285498489426]],"mystery_game_puzzles":[["2026-10-18",0.05]],"otis_mock_aime":[["2026-10-18",0.8166666666666667]],"simpleqa_verified":[["2026-10-18",0.196]]}},"openhands-lm-32b-v0-1":{"points":[["2026-10-18",67.419848]],"inputs":{"aider_polyglot":[["2026-10-18",0.102]]}},"phi-3-medium-14b":{"points":[["2026-10-18",50.746513]],"inputs":{"gpqa_diamond":[["2026-10-18",0.2758838383838384]],"math_level_5":[["2026-10-18",0.17560422960725075]]}},"phi-4":{"points":[["2026-10-18",75.98252]],"inputs":{"bfcl_overall":[["2026-10-18",0.2879]],"gpqa_diamond":[["2026-10-18",0.5606060606060606]],"math_level_5":[["2026-10-18",0.6493580060422961]],"otis_mock_aime":[["2026-10-18",0.1375]]}},"qwen-3-5-flash-hosted-35b-a3b":{"points":[["2026-10-18",107.337886]],"inputs":{"chess_puzzles":[["2026-10-18",0.14]],"frontiermath_t13":[["2026-10-18",0.1824561403508772]],"gpqa_diamond":[["2026-10-18",0.8232323232323232]],"mystery_game_puzzles":[["2026-10-18",0.2]],"otis_mock_aime":[["2026-10-18",0.8444444444444444]],"simpleqa_verified":[["2026-10-18",0.2032032032032032]]}},"qwen-3-5-plus-hosted-397b-a17b":{"points":[["2026-10-18",108.961196]],"inputs":{"chess_puzzles":[["2026-10-18",0.08]],"gpqa_diamond":[["2026-10-18",0.8484848484848485]],"mystery_game_puzzles":[["2026-10-18",0.17]],"otis_mock_aime":[["2026-10-18",0.8666666666666667]],"simpleqa_verified":[["2026-10-18",0.2535070140280561]]}},"qwen-3-6-35b-a3b":{"points":[["2026-10-18",110.780052]],"inputs":{"frontiermath_t13":[["2026-10-18",0.20350877192982456]],"gpqa_diamond":[["2026-10-18",0.8484848484848485]],"mystery_game_puzzles":[["2026-10-18",0.22]],"or_gpqa_diamond":[["2026-10-18",0.8272847449686571]],"or_tau2_airline":[["2026-10-18",0.744993393858478]],"otis_mock_aime":[["2026-10-18",0.8666666666666667]]}},"qwen-3-6-flash":{"points":[["2026-10-18",107.471461]],"inputs":{"chess_puzzles":[["2026-10-18",0.12]],"frontiermath_t13":[["2026-10-18",0.22456140350877193]],"gpqa_diamond":[["2026-10-18",0.8333333333333334]],"mystery_game_puzzles":[["2026-10-18",0.18]],"otis_mock_aime":[["2026-10-18",0.8444444444444444]],"simpleqa_verified":[["2026-10-18",0.15915915915915915]]}},"qwen-3-6-max-preview":{"points":[["2026-10-18",117.684134]],"inputs":{"gpqa_diamond":[["2026-10-18",0.8737373737373737]],"mystery_game_puzzles":[["2026-10-18",0.19]],"otis_mock_aime":[["2026-10-18",0.9111111111111111]],"simpleqa_verified":[["2026-10-18",0.5200400801603207]],"swe_bench_verified":[["2026-10-18",0.7665289256198347]]}},"qwen-3-6-plus":{"points":[["2026-10-18",112.636385]],"inputs":{"chess_puzzles":[["2026-10-18",0.14]],"frontiermath_t13":[["2026-10-18",0.3824561403508772]],"gpqa_diamond":[["2026-10-18",0.8838383838383839]],"mystery_game_puzzles":[["2026-10-18",0.12]],"otis_mock_aime":[["2026-10-18",0.9333333333333333]],"simpleqa_verified":[["2026-10-18",0.44144144144144143]],"swe_bench_verified":[["2026-10-18",0.5785123966942148]]}},"qwen-3-8-27b":{"points":[["2026-10-18",119.546864]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.83367]],"or_tau2_airline":[["2026-10-18",0.7592592222222222]]}},"qwen-3-8-max":{"points":[["2026-10-18",130.138923]],"inputs":{"chess_puzzles":[["2026-10-18",0.46]],"frontiermath_t13":[["2026-10-18",0.7473684210526316]],"frontiermath_t4":[["2026-10-18",0.4634146341463415]],"gpqa_diamond":[["2026-10-18",0.9267676767676768]],"mystery_game_puzzles":[["2026-10-18",0.38]],"otis_mock_aime":[["2026-10-18",0.9944444444444445]],"simpleqa_verified":[["2026-10-18",0.458]]}},"qwen-plus-jan-2025":{"points":[["2026-10-18",75.945222]],"inputs":{"gpqa_diamond":[["2026-10-18",0.4810606060606061]],"math_level_5":[["2026-10-18",0.6527567975830816]],"otis_mock_aime":[["2026-10-18",0.17777777777777778]]}},"qwen-turbo":{"points":[["2026-10-18",69.463004]],"inputs":{"gpqa_diamond":[["2026-10-18",0.41792929292929293]],"math_level_5":[["2026-10-18",0.5623111782477341]],"otis_mock_aime":[["2026-10-18",0.06111111111111111]]}},"qwen2-5-32b":{"points":[["2026-10-18",70.588449]],"inputs":{"gpqa_diamond":[["2026-10-18",0.46085858585858586]],"math_level_5":[["2026-10-18",0.5607061933534743]],"otis_mock_aime":[["2026-10-18",0.07361111111111111]]}},"qwen2-5-72b":{"points":[["2026-10-18",72.300909]],"inputs":{"gpqa_diamond":[["2026-10-18",0.4914772727272727]],"math_level_5":[["2026-10-18",0.631703172205438]],"or_gpqa_diamond":[["2026-10-18",0.461279]],"or_tau2_airline":[["2026-10-18",0.25]],"otis_mock_aime":[["2026-10-18",0.08055555555555556]]}},"qwen2-5-7b":{"points":[["2026-10-18",50.689639]],"inputs":{"gpqa_diamond":[["2026-10-18",0.3547979797979798]],"or_gpqa_diamond":[["2026-10-18",0.3417510000000001]],"or_tau2_airline":[["2026-10-18",0.166667]],"otis_mock_aime":[["2026-10-18",0.025]]}},"qwen2-5-coder-32b-instruct":{"points":[["2026-10-18",74.565449]],"inputs":{"aider_polyglot":[["2026-10-18",0.16399999999999998]]}},"qwen2-5-max":{"points":[["2026-10-18",77.698679]],"inputs":{"aider_polyglot":[["2026-10-18",0.218]],"gpqa_diamond":[["2026-10-18",0.5612373737373737]],"math_level_5":[["2026-10-18",0.6718277945619335]],"otis_mock_aime":[["2026-10-18",0.16111111111111112]]}},"qwen2-72b":{"points":[["2026-10-18",63.699544]],"inputs":{"gpqa_diamond":[["2026-10-18",0.4078282828282828]],"math_level_5":[["2026-10-18",0.39067220543806647]]}},"qwen3-0-6b":{"points":[["2026-10-18",64.185851]],"inputs":{"bfcl_overall":[["2026-10-18",0.23929999999999998]]}},"qwen3-1-7b":{"points":[["2026-10-18",64.617987]],"inputs":{"bfcl_overall":[["2026-10-18",0.2841]],"gpqa_diamond":[["2026-10-18",0.380050505050505]],"otis_mock_aime":[["2026-10-18",0.08055555555555556]]}},"qwen3-14b":{"points":[["2026-10-18",93.076974]],"inputs":{"bfcl_overall":[["2026-10-18",0.4103]],"gpqa_diamond":[["2026-10-18",0.6376262626262627]],"or_gpqa_diamond":[["2026-10-18",0.5331086666666667]],"or_tau2_airline":[["2026-10-18",0.413333]],"otis_mock_aime":[["2026-10-18",0.6638888888888889]]}},"qwen3-235b-a22b":{"points":[["2026-10-18",85.424185]],"inputs":{"aider_polyglot":[["2026-10-18",0.596]],"gpqa_diamond":[["2026-10-18",0.7070707070707071]],"math_level_5":[["2026-10-18",0.6885699899295065]]}},"qwen3-235b-a22b-instruct-jul-2025":{"points":[["2026-10-18",95.867711]],"inputs":{"bfcl_overall":[["2026-10-18",0.5215]],"or_gpqa_diamond":[["2026-10-18",0.7388167142857143]],"or_tau2_airline":[["2026-10-18",0.3961905714285714]]}},"qwen3-235b-a22b-thinking-jul-2025":{"points":[["2026-10-18",111.386497]],"inputs":{"gpqa_diamond":[["2026-10-18",0.8005050505050505]],"mystery_game_puzzles":[["2026-10-18",0.09]],"or_gpqa_diamond":[["2026-10-18",0.7950335]],"or_tau2_airline":[["2026-10-18",0.6266666666666667]],"otis_mock_aime":[["2026-10-18",0.8666666666666667]],"simpleqa_verified":[["2026-10-18",0.4044044044044044]]}},"qwen3-30b-a3b":{"points":[["2026-10-18",93.650165]],"inputs":{"gpqa_diamond":[["2026-10-18",0.6167929292929293]],"or_gpqa_diamond":[["2026-10-18",0.604377]],"or_tau2_airline":[["2026-10-18",0.423333]],"otis_mock_aime":[["2026-10-18",0.6277777777777778]]}},"qwen3-30b-a3b-instruct-jul-2025":{"points":[["2026-10-18",91.499739]],"inputs":{"bfcl_overall":[["2026-10-18",0.4139]],"gpqa_diamond":[["2026-10-18",0.5561868686868687]],"or_gpqa_diamond":[["2026-10-18",0.6419754999999999]],"or_tau2_airline":[["2026-10-18",0.3695237142857143]],"otis_mock_aime":[["2026-10-18",0.6222222222222222]]}},"qwen3-30b-a3b-thinking-jul-2025":{"points":[["2026-10-18",99.711287]],"inputs":{"gpqa_diamond":[["2026-10-18",0.7007575757575758]],"otis_mock_aime":[["2026-10-18",0.7027777777777777]]}},"qwen3-32b":{"points":[["2026-10-18",94.611782]],"inputs":{"aider_polyglot":[["2026-10-18",0.4]],"bfcl_overall":[["2026-10-18",0.48710000000000003]],"gpqa_diamond":[["2026-10-18",0.6571969696969697]],"or_gpqa_diamond":[["2026-10-18",0.5572391666666667]],"or_tau2_airline":[["2026-10-18",0.4516665]],"otis_mock_aime":[["2026-10-18",0.6694444444444444]]}},"qwen3-4b":{"points":[["2026-10-18",76.732105]],"inputs":{"gpqa_diamond":[["2026-10-18",0.5233585858585859]]}},"qwen3-4b-instruct-2507":{"points":[["2026-10-18",85.445293]],"inputs":{"bfcl_overall":[["2026-10-18",0.3568]],"gpqa_diamond":[["2026-10-18",0.4583333333333333]],"otis_mock_aime":[["2026-10-18",0.5222222222222223]]}},"qwen3-5-122b-a10b":{"points":[["2026-10-18",112.229854]],"inputs":{"mystery_game_puzzles":[["2026-10-18",0.17]],"or_gpqa_diamond":[["2026-10-18",0.8073469346289753]],"or_tau2_airline":[["2026-10-18",0.7471783002257337]]}},"qwen3-5-35b-a3b":{"points":[["2026-10-18",105.716898]],"inputs":{"gpqa_diamond":[["2026-10-18",0.8345959595959596]],"or_gpqa_diamond":[["2026-10-18",0.7500000000000001]],"or_tau2_airline":[["2026-10-18",0.7351189375]],"otis_mock_aime":[["2026-10-18",0.7]]}},"qwen3-5-397b-a17b":{"points":[["2026-10-18",113.507214]],"inputs":{"frontiermath_t13":[["2026-10-18",0.312280701754386]],"gpqa_diamond":[["2026-10-18",0.8636363636363636]],"mystery_game_puzzles":[["2026-10-18",0.18]],"or_gpqa_diamond":[["2026-10-18",0.8728152090966519]],"or_tau2_airline":[["2026-10-18",0.7811111111111111]],"otis_mock_aime":[["2026-10-18",0.8888888888888888]]}},"qwen3-5-4b":{"points":[["2026-10-18",95.564049]],"inputs":{"otis_mock_aime":[["2026-10-18",0.5583333333333333]]}},"qwen3-5-9b":{"points":[["2026-10-18",100.892838]],"inputs":{"gpqa_diamond":[["2026-10-18",0.7897727272727273]],"or_gpqa_diamond":[["2026-10-18",0.7462993119730186]],"or_tau2_airline":[["2026-10-18",0.650067849593496]],"otis_mock_aime":[["2026-10-18",0.6166666666666667]]}},"qwen3-6-27b":{"points":[["2026-10-18",114.7733]],"inputs":{"frontiermath_t13":[["2026-10-18",0.3508771929824561]],"gpqa_diamond":[["2026-10-18",0.8585858585858586]],"mystery_game_puzzles":[["2026-10-18",0.07]],"or_gpqa_diamond":[["2026-10-18",0.801499818181818]],"or_tau2_airline":[["2026-10-18",0.7627176144578314]],"otis_mock_aime":[["2026-10-18",0.9111111111111111]]}},"qwen3-7-flash":{"points":[["2026-10-18",107.458292]],"inputs":{"frontiermath_t13":[["2026-10-18",0.19298245614035087]],"gpqa_diamond":[["2026-10-18",0.8232323232323232]],"mystery_game_puzzles":[["2026-10-18",0.15]],"otis_mock_aime":[["2026-10-18",0.8666666666666667]]}},"qwen3-7-max":{"points":[["2026-10-18",124.985571]],"inputs":{"chess_puzzles":[["2026-10-18",0.26]],"frontiermath_t13":[["2026-10-18",0.6456140350877193]],"frontiermath_t4":[["2026-10-18",0.34146341463414637]],"gpqa_diamond":[["2026-10-18",0.9090909090909091]],"mystery_game_puzzles":[["2026-10-18",0.32]],"or_gpqa_diamond":[["2026-10-18",0.9090909999999999]],"or_tau2_airline":[["2026-10-18",0.72]],"otis_mock_aime":[["2026-10-18",0.9555555555555556]],"simpleqa_verified":[["2026-10-18",0.5576730190571715]],"swe_bench_verified":[["2026-10-18",0.7727272727272727]]}},"qwen3-7-plus":{"points":[["2026-10-18",114.660524]],"inputs":{"frontiermath_t13":[["2026-10-18",0.34385964912280703]],"gpqa_diamond":[["2026-10-18",0.8787878787878788]],"mystery_game_puzzles":[["2026-10-18",0.17]],"or_gpqa_diamond":[["2026-10-18",0.873737]],"or_tau2_airline":[["2026-10-18",0.726667]],"otis_mock_aime":[["2026-10-18",0.9333333333333333]]}},"qwen3-8-flash":{"points":[["2026-10-18",124.58187]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.8962022556962025]],"or_tau2_airline":[["2026-10-18",0.7]]}},"qwen3-8-max-0902":{"points":[["2026-10-18",126.551596]],"inputs":{"chess_puzzles":[["2026-10-18",0.37]],"frontiermath_t13":[["2026-10-18",0.656140350877193]],"frontiermath_t4":[["2026-10-18",0.34146341463414637]],"gpqa_diamond":[["2026-10-18",0.922979797979798]],"otis_mock_aime":[["2026-10-18",1.0]],"simpleqa_verified":[["2026-10-18",0.473]]}},"qwen3-8b":{"points":[["2026-10-18",90.547035]],"inputs":{"bfcl_overall":[["2026-10-18",0.4257]],"gpqa_diamond":[["2026-10-18",0.5675505050505051]],"otis_mock_aime":[["2026-10-18",0.5611111111111111]]}},"qwen3-coder-480b-a35b":{"points":[["2026-10-18",84.587904]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.6035354999999999]],"or_tau2_airline":[["2026-10-18",0.43333342857142854]]}},"qwen3-coder-next":{"points":[["2026-10-18",103.238768]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.7575756666666668]],"or_tau2_airline":[["2026-10-18",0.5762463812316716]]}},"qwen3-max":{"points":[["2026-10-18",106.250084]],"inputs":{"frontiermath_t13":[["2026-10-18",0.18947368421052632]],"gpqa_diamond":[["2026-10-18",0.726010101010101]],"math_level_5":[["2026-10-18",0.9712990936555891]],"mystery_game_puzzles":[["2026-10-18",0.05]],"otis_mock_aime":[["2026-10-18",0.7333333333333333]],"simpleqa_verified":[["2026-10-18",0.4874874874874875]]}},"qwq-32b":{"points":[["2026-10-18",91.670024]],"inputs":{"aider_polyglot":[["2026-10-18",0.209]],"gpqa_diamond":[["2026-10-18",0.6534090909090909]],"otis_mock_aime":[["2026-10-18",0.5916666666666667]]}},"qwq-plus":{"points":[["2026-10-18",90.313035]],"inputs":{"gpqa_diamond":[["2026-10-18",0.6540404040404041]]}},"seed-oss-36b-instruct":{"points":[["2026-10-18",99.390084]],"inputs":{"gpqa_diamond":[["2026-10-18",0.7152777777777778]],"otis_mock_aime":[["2026-10-18",0.675]]}},"tencent-hy4-preview":{"points":[["2026-10-18",129.162447]],"inputs":{"or_gpqa_diamond":[["2026-10-18",0.8973063333333335]],"or_tau2_airline":[["2026-10-18",0.7777776666666667]]}},"wizardlm-2-8x22b":{"points":[["2026-10-18",58.713211]],"inputs":{"gpqa_diamond":[["2026-10-18",0.43434343434343436]],"math_level_5":[["2026-10-18",0.25736404833836857]]}},"yi-lightning":{"points":[["2026-10-18",70.87595]],"inputs":{"aider_polyglot":[["2026-10-18",0.129]]}}}}
