{"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.","models":[{"s":"gpt-6-astra","n":"GPT-6 Astra","o":"OpenAI","iq":149.64,"d":150,"lo":146,"hi":153,"t":"main","r":"2026-09-03","a":"api","b":8,"c":{"reasoning":154,"math":148,"knowledge":149},"p":[10.0,50.0],"x":{"chess_puzzles":0.74,"furniture_assembly":0.8,"mystery_game_puzzles":0.84,"frontiermath_t4":0.976,"frontiermath_t13":0.9368421052631579,"otis_mock_aime":1.0,"gpqa_diamond":0.9577020202020202,"or_gpqa_diamond":0.9472503333333333,"simpleqa_verified":0.756,"or_tau2_airline":0.6766665000000001}},{"s":"gpt-6-1-sol","n":"GPT-6.1 Sol","o":"OpenAI","iq":147.93,"d":148,"lo":144,"hi":152,"t":"main","r":"2026-09-29","a":"api","b":8,"c":{"reasoning":150,"math":148,"knowledge":147},"p":[2.0,10.0],"x":{"chess_puzzles":0.68,"furniture_assembly":0.8,"mystery_game_puzzles":0.8,"frontiermath_t4":1.0,"frontiermath_t13":0.9368421052631579,"otis_mock_aime":1.0,"gpqa_diamond":0.9539141414141414,"or_gpqa_diamond":0.944444,"simpleqa_verified":0.739,"or_tau2_airline":0.6822223333333333}},{"s":"claude-opus-5-5","n":"Claude Opus 5.5","o":"Anthropic","iq":144.42,"d":144,"lo":141,"hi":148,"t":"main","r":"2026-09-22","a":"api","b":8,"c":{"reasoning":146,"math":145,"knowledge":137},"p":[4.0,20.0],"x":{"chess_puzzles":0.67,"furniture_assembly":0.8333333333333334,"mystery_game_puzzles":0.71,"frontiermath_t4":0.95,"frontiermath_t13":0.9122807017543859,"otis_mock_aime":1.0,"gpqa_diamond":0.9059343434343434,"or_gpqa_diamond":0.9020199999999999,"simpleqa_verified":0.722,"or_tau2_airline":0.756}},{"s":"claude-sonnet-5-5","n":"Claude Sonnet 5.5","o":"Anthropic","iq":140.29,"d":140,"lo":137,"hi":143,"t":"main","r":"2026-09-28","a":"api","b":8,"c":{"reasoning":142,"math":140,"knowledge":137},"p":[2.0,10.0],"x":{"chess_puzzles":0.59,"furniture_assembly":0.75,"mystery_game_puzzles":0.65,"frontiermath_t4":0.8048780487804879,"frontiermath_t13":0.887719298245614,"otis_mock_aime":1.0,"gpqa_diamond":0.9558080808080808,"or_gpqa_diamond":0.92929275,"simpleqa_verified":0.465,"or_tau2_airline":0.775}},{"s":"gpt-6-sol","n":"GPT-6 Sol","o":"OpenAI","iq":140.29,"d":140,"lo":137,"hi":144,"t":"main","r":"2026-09-22","a":"api","b":8,"c":{"reasoning":139,"math":143,"knowledge":138},"p":[2.0,10.0],"x":{"chess_puzzles":0.56,"furniture_assembly":0.5833333333333334,"mystery_game_puzzles":0.56,"frontiermath_t4":0.9,"frontiermath_t13":0.8982456140350877,"otis_mock_aime":1.0,"gpqa_diamond":0.9431818181818182,"or_gpqa_diamond":0.9208749999999999,"simpleqa_verified":0.607,"or_tau2_airline":0.7022223333333333}},{"s":"gemini-4-argon","n":"Gemini 4 Argon","o":"Google DeepMind","iq":140.16,"d":140,"lo":137,"hi":143,"t":"main","r":"2026-09-30","a":"unknown","b":8,"c":{"reasoning":142,"math":138,"knowledge":148},"p":[2.0,10.0],"x":{"chess_puzzles":0.59,"furniture_assembly":0.725,"mystery_game_puzzles":0.64,"frontiermath_t4":0.7804878048780488,"frontiermath_t13":0.8596491228070176,"otis_mock_aime":1.0,"gpqa_diamond":0.9640151515151515,"or_gpqa_diamond":0.964646,"simpleqa_verified":0.76,"or_tau2_airline":0.786667}},{"s":"gpt-5-6-sol","n":"GPT-5.6 Sol","o":"OpenAI","iq":140.01,"d":140,"lo":137,"hi":143,"t":"main","r":"2026-07-09","a":"api","b":8,"c":{"reasoning":140,"math":141,"knowledge":139},"p":[4.0,20.0],"x":{"chess_puzzles":0.59,"furniture_assembly":0.5666666666666667,"mystery_game_puzzles":0.58,"frontiermath_t4":0.8292682926829268,"frontiermath_t13":0.8912280701754386,"otis_mock_aime":1.0,"gpqa_diamond":0.9349747474747475,"or_gpqa_diamond":0.9234005000000001,"simpleqa_verified":0.697,"or_tau2_airline":0.73333325}},{"s":"claude-fable-5-1","n":"Claude Fable 5.1","o":"Anthropic","iq":139.76,"d":140,"lo":136,"hi":143,"t":"main","r":"2026-09-01","a":"api","b":8,"c":{"reasoning":137,"math":142,"knowledge":137},"p":[10.0,50.0],"x":{"chess_puzzles":0.48,"furniture_assembly":0.7,"mystery_game_puzzles":0.58,"frontiermath_t4":0.8780487804878049,"frontiermath_t13":0.9017543859649123,"otis_mock_aime":1.0,"or_gpqa_diamond":0.8894498333333334,"simpleqa_verified":0.708,"or_tau2_airline":0.7906666}},{"s":"gpt-5-5","n":"GPT-5.5","o":"OpenAI","iq":137.9,"d":138,"lo":135,"hi":141,"t":"main","r":"2026-04-23","a":"api","b":9,"c":{"reasoning":141,"math":137,"knowledge":139},"p":[5.0,30.0],"x":{"chess_puzzles":0.63,"furniture_assembly":0.44166666666666665,"mystery_game_puzzles":0.56,"frontiermath_t4":0.725,"frontiermath_t13":0.8526315789473684,"otis_mock_aime":1.0,"swe_bench_verified":0.8057851239669421,"gpqa_diamond":0.9400252525252525,"or_gpqa_diamond":0.9360266666666668,"simpleqa_verified":0.63,"or_tau2_airline":0.75}},{"s":"claude-fable-5","n":"Claude Fable 5","o":"Anthropic","iq":137.73,"d":138,"lo":134,"hi":141,"t":"main","r":"2026-06-09","a":"api","b":8,"c":{"reasoning":135,"math":141,"knowledge":130},"p":[10.0,50.0],"x":{"chess_puzzles":0.47,"furniture_assembly":0.35833333333333334,"mystery_game_puzzles":0.52,"frontiermath_t4":0.902,"frontiermath_t13":0.8701754385964913,"otis_mock_aime":1.0,"gpqa_diamond":0.8585858585858586,"or_gpqa_diamond":0.8615317499999998,"simpleqa_verified":0.707,"or_tau2_airline":0.7957576363636364}},{"s":"claude-opus-5","n":"Claude Opus 5","o":"Anthropic","iq":136.44,"d":136,"lo":133,"hi":140,"t":"main","r":"2026-07-24","a":"api","b":8,"c":{"reasoning":136,"math":137,"knowledge":135},"p":[5.0,25.0],"x":{"chess_puzzles":0.43,"furniture_assembly":0.6083333333333333,"mystery_game_puzzles":0.59,"frontiermath_t4":0.7317073170731707,"frontiermath_t13":0.856140350877193,"otis_mock_aime":0.9888888888888889,"gpqa_diamond":0.9387626262626263,"or_gpqa_diamond":0.8957629166666667,"simpleqa_verified":0.599,"or_tau2_airline":0.7727272727272727}},{"s":"gpt-5-6-terra","n":"GPT-5.6 Terra","o":"OpenAI","iq":133.78,"d":134,"lo":131,"hi":137,"t":"main","r":"2026-07-09","a":"api","b":8,"c":{"reasoning":130,"math":137,"knowledge":130},"p":[2.0,12.0],"x":{"chess_puzzles":0.47,"furniture_assembly":0.5416666666666666,"mystery_game_puzzles":0.35,"frontiermath_t4":0.7073170731707317,"frontiermath_t13":0.8596491228070176,"otis_mock_aime":0.9972222222222222,"gpqa_diamond":0.9330808080808081,"or_gpqa_diamond":0.89267675,"simpleqa_verified":0.432,"or_tau2_airline":0.715}},{"s":"claude-opus-4-8","n":"Claude Opus 4.8","o":"Anthropic","iq":132.03,"d":132,"lo":129,"hi":135,"t":"main","r":"2026-05-28","a":"api","b":8,"c":{"reasoning":132,"math":133,"knowledge":130},"p":[5.0,25.0],"x":{"chess_puzzles":0.52,"furniture_assembly":0.425,"mystery_game_puzzles":0.36,"frontiermath_t4":0.5609756097560976,"frontiermath_t13":0.8,"otis_mock_aime":0.9833333333333333,"gpqa_diamond":0.9103535353535354,"or_gpqa_diamond":0.8959834999999999,"simpleqa_verified":0.53,"or_tau2_airline":0.7776190714285715}},{"s":"gemini-3-7-flash","n":"Gemini 3.7 Flash","o":"Google DeepMind","iq":131.07,"d":131,"lo":128,"hi":134,"t":"main","r":"2026-08-13","a":"api","b":8,"c":{"reasoning":135,"math":128,"knowledge":139},"p":[0.75,3.75],"x":{"chess_puzzles":0.66,"furniture_assembly":0.26666666666666666,"mystery_game_puzzles":0.37,"frontiermath_t4":0.36585365853658536,"frontiermath_t13":0.7157894736842105,"otis_mock_aime":0.9722222222222222,"gpqa_diamond":0.9482323232323232,"or_gpqa_diamond":0.9391951653543308,"simpleqa_verified":0.692,"or_tau2_airline":0.7831052054794521}},{"s":"gpt-5-4","n":"GPT-5.4","o":"OpenAI","iq":130.56,"d":131,"lo":128,"hi":133,"t":"main","r":"2026-03-05","a":"api","b":9,"c":{"reasoning":131,"math":131,"knowledge":130},"p":[2.5,15.0],"x":{"chess_puzzles":0.48,"furniture_assembly":0.375,"mystery_game_puzzles":0.37,"frontiermath_t4":0.49,"frontiermath_t13":0.7859649122807018,"otis_mock_aime":0.9777777777777777,"swe_bench_verified":0.768595041322314,"gpqa_diamond":0.933,"or_gpqa_diamond":0.899551,"simpleqa_verified":0.451,"or_tau2_airline":0.73166675}},{"s":"gpt-5-6-luna","n":"GPT-5.6 Luna","o":"OpenAI","iq":130.4,"d":130,"lo":127,"hi":133,"t":"main","r":"2026-07-09","a":"api","b":8,"c":{"reasoning":124,"math":134,"knowledge":126},"p":[0.2,1.2],"x":{"chess_puzzles":0.43,"furniture_assembly":0.425,"mystery_game_puzzles":0.21,"frontiermath_t4":0.6097560975609756,"frontiermath_t13":0.8210526315789474,"otis_mock_aime":0.9833333333333333,"gpqa_diamond":0.9160353535353535,"or_gpqa_diamond":0.8724745,"simpleqa_verified":0.41,"or_tau2_airline":0.72333325}},{"s":"gpt-6-luna","n":"GPT-6 Luna","o":"OpenAI","iq":130.21,"d":130,"lo":127,"hi":133,"t":"main","r":"2026-09-22","a":"api","b":8,"c":{"reasoning":126,"math":132,"knowledge":126},"p":[0.1,0.5],"x":{"chess_puzzles":0.36,"furniture_assembly":0.44166666666666665,"mystery_game_puzzles":0.07,"frontiermath_t4":0.5609756097560976,"frontiermath_t13":0.7894736842105263,"otis_mock_aime":0.9888888888888889,"gpqa_diamond":0.9046717171717171,"or_gpqa_diamond":0.8815936666666665,"simpleqa_verified":0.414,"or_tau2_airline":0.68}},{"s":"gemini-3-8-flash","n":"Gemini 3.8 Flash","o":"Google DeepMind","iq":129.9,"d":130,"lo":127,"hi":133,"t":"main","r":"2026-09-02","a":"api","b":8,"c":{"reasoning":136,"math":125,"knowledge":140},"p":[0.75,3.75],"x":{"chess_puzzles":0.58,"furniture_assembly":0.31666666666666665,"mystery_game_puzzles":0.47,"frontiermath_t4":0.21951219512195122,"frontiermath_t13":0.6842105263157895,"otis_mock_aime":0.9888888888888889,"gpqa_diamond":0.9539141414141414,"or_gpqa_diamond":0.9482614885496183,"simpleqa_verified":0.697,"or_tau2_airline":0.734694}},{"s":"claude-haiku-5-5","n":"Claude Haiku 5.5","o":"Anthropic","iq":129.4,"d":129,"lo":126,"hi":132,"t":"main","r":"2026-10-07","a":"api","b":8,"c":{"reasoning":130,"math":130,"knowledge":121},"p":[0.1,0.5],"x":{"chess_puzzles":0.55,"furniture_assembly":0.475,"mystery_game_puzzles":0.3,"frontiermath_t4":0.4634146341463415,"frontiermath_t13":0.7508771929824561,"otis_mock_aime":0.9888888888888889,"gpqa_diamond":0.8964646464646465,"or_gpqa_diamond":0.8692479999999999,"simpleqa_verified":0.238,"or_tau2_airline":0.7577776666666667}},{"s":"deepseek-v4-1-flash","n":"DeepSeek V4.1 Flash","o":"DeepSeek","iq":127.71,"d":128,"lo":125,"hi":131,"t":"main","r":"2026-09-09","a":"open_restricted","b":8,"c":{"reasoning":132,"math":126,"knowledge":125},"p":null,"x":{"chess_puzzles":0.48,"furniture_assembly":0.3416666666666667,"mystery_game_puzzles":0.43,"frontiermath_t4":0.2682926829268293,"frontiermath_t13":0.6736842105263158,"otis_mock_aime":0.9833333333333333,"gpqa_diamond":0.8983585858585859,"or_gpqa_diamond":0.8838381666666666,"simpleqa_verified":0.429,"or_tau2_airline":0.745}},{"s":"deepseek-v4-pro-0813","n":"DeepSeek V4 Pro 0813","o":"DeepSeek","iq":127.62,"d":128,"lo":125,"hi":131,"t":"main","r":"2026-08-13","a":"open_restricted","b":8,"c":{"reasoning":132,"math":125,"knowledge":129},"p":null,"x":{"chess_puzzles":0.46,"mystery_game_puzzles":0.43,"frontiermath_t4":0.2682926829268293,"frontiermath_t13":0.6456140350877193,"otis_mock_aime":0.9861111111111112,"gpqa_diamond":0.9166666666666666,"or_gpqa_diamond":0.892567903763697,"simpleqa_verified":0.5290581162324649,"or_tau2_airline":0.767500125}},{"s":"muse-spark-open","n":"Muse Spark Open","o":"Meta AI","iq":127.07,"d":127,"lo":124,"hi":130,"t":"main","r":"2026-10-15","a":"open_restricted","b":6,"c":{"math":127,"knowledge":128},"p":null,"x":{"frontiermath_t4":0.3170731707317073,"frontiermath_t13":0.6982456140350877,"otis_mock_aime":0.9805555555555555,"gpqa_diamond":0.8857323232323232,"or_gpqa_diamond":0.905724,"simpleqa_verified":0.566,"or_tau2_airline":0.78}},{"s":"kimi-k3","n":"Kimi K3","o":"Moonshot","iq":127.06,"d":127,"lo":124,"hi":130,"t":"main","r":"2026-07-16","a":"open_noncommercial","b":8,"c":{"reasoning":124,"math":128,"knowledge":130},"p":[3.0,15.0],"x":{"chess_puzzles":0.37,"furniture_assembly":0.3416666666666667,"mystery_game_puzzles":0.26,"frontiermath_t4":0.3902439024390244,"frontiermath_t13":0.721830985915493,"otis_mock_aime":0.9722222222222222,"gpqa_diamond":0.9311868686868687,"or_gpqa_diamond":0.9157357830756013,"simpleqa_verified":0.506,"or_tau2_airline":0.7347416579476861}},{"s":"claude-opus-4-7","n":"Claude Opus 4.7","o":"Anthropic","iq":126.95,"d":127,"lo":124,"hi":130,"t":"main","r":"2026-04-16","a":"api","b":9,"c":{"reasoning":125,"math":127,"knowledge":127},"p":[5.0,25.0],"x":{"chess_puzzles":0.41,"furniture_assembly":0.3333333333333333,"mystery_game_puzzles":0.28,"frontiermath_t4":0.3170731707317073,"frontiermath_t13":0.7017543859649122,"otis_mock_aime":0.978,"swe_bench_verified":0.8347107438016529,"gpqa_diamond":0.9015151515151515,"or_gpqa_diamond":0.892375117408907,"simpleqa_verified":0.517,"or_tau2_airline":0.7757142142857143}},{"s":"gemini-3-1-pro","n":"Gemini 3.1 Pro","o":"Google DeepMind","iq":126.85,"d":127,"lo":124,"hi":130,"t":"main","r":"2026-02-19","a":"api","b":9,"c":{"reasoning":130,"math":124,"knowledge":139},"p":[2.0,12.0],"x":{"chess_puzzles":0.51,"furniture_assembly":0.26666666666666666,"mystery_game_puzzles":0.34,"frontiermath_t4":0.2682926829268293,"frontiermath_t13":0.5964912280701754,"otis_mock_aime":0.956,"swe_bench_verified":0.756198347107438,"gpqa_diamond":0.9444444444444444,"or_gpqa_diamond":0.9483723333333332,"simpleqa_verified":0.735,"or_tau2_airline":0.7422223333333333}},{"s":"gemini-3-5-flash","n":"Gemini 3.5 Flash","o":"Google DeepMind","iq":126.32,"d":126,"lo":123,"hi":129,"t":"main","r":"2026-05-19","a":"api","b":9,"c":{"reasoning":128,"math":125,"knowledge":134},"p":[1.5,9.0],"x":{"chess_puzzles":0.45,"mystery_game_puzzles":0.32,"frontiermath_t4":0.2682926829268293,"frontiermath_t13":0.6280701754385964,"otis_mock_aime":0.9555555555555556,"swe_bench_verified":0.7933884297520661,"gpqa_diamond":0.928030303030303,"or_gpqa_diamond":0.9242421666666667,"simpleqa_verified":0.662,"or_tau2_airline":0.7333336666666668}},{"s":"grok-4-6","n":"Grok 4.6","o":"xAI","iq":126.28,"d":126,"lo":123,"hi":129,"t":"main","r":"2026-08-12","a":"api","b":8,"c":{"reasoning":125,"math":126,"knowledge":131},"p":[2.0,6.0],"x":{"chess_puzzles":0.33,"furniture_assembly":0.4,"mystery_game_puzzles":0.34,"frontiermath_t4":0.3170731707317073,"frontiermath_t13":0.6596491228070176,"otis_mock_aime":0.9916666666666667,"gpqa_diamond":0.9400252525252525,"or_gpqa_diamond":0.9246375695652174,"simpleqa_verified":0.493,"or_tau2_airline":0.747619}},{"s":"claude-sonnet-5","n":"Claude Sonnet 5","o":"Anthropic","iq":126.1,"d":126,"lo":123,"hi":129,"t":"main","r":"2026-06-30","a":"api","b":8,"c":{"reasoning":129,"math":125,"knowledge":122},"p":[2.0,10.0],"x":{"chess_puzzles":0.45,"mystery_game_puzzles":0.35,"frontiermath_t4":0.2926829268292683,"frontiermath_t13":0.656140350877193,"otis_mock_aime":0.9472222222222222,"gpqa_diamond":0.9053030303030303,"or_gpqa_diamond":0.8576035833333334,"simpleqa_verified":0.337,"or_tau2_airline":0.76}},{"s":"glm-5-3","n":"GLM-5.3","o":"Z.ai (Zhipu AI)","iq":125.32,"d":125,"lo":122,"hi":128,"t":"main","r":"2026-08-14","a":"open_restricted","b":8,"c":{"reasoning":126,"math":125,"knowledge":124},"p":[1.4,4.4],"x":{"chess_puzzles":0.37,"mystery_game_puzzles":0.33,"frontiermath_t4":0.2926829268292683,"frontiermath_t13":0.6877192982456141,"otis_mock_aime":0.9111111111111111,"gpqa_diamond":0.9090909090909091,"or_gpqa_diamond":0.8639263412162163,"simpleqa_verified":0.41,"or_tau2_airline":0.78083325}},{"s":"gpt-5-2","n":"GPT-5.2","o":"OpenAI","iq":125.06,"d":125,"lo":122,"hi":128,"t":"main","r":"2025-12-11","a":"api","b":10,"c":{"reasoning":126,"math":126,"knowledge":124,"agentic":117},"p":[1.75,14.0],"x":{"chess_puzzles":0.48,"furniture_assembly":0.38333333333333336,"mystery_game_puzzles":0.23,"frontiermath_t4":0.317,"frontiermath_t13":0.674,"otis_mock_aime":0.9611111111111111,"swe_bench_verified":0.737603305785124,"gpqa_diamond":0.914,"or_gpqa_diamond":0.878788,"simpleqa_verified":0.371,"bfcl_overall":0.5587,"or_tau2_airline":0.726667}},{"s":"qwen3-7-max","n":"Qwen3.7-Max","o":"Alibaba","iq":124.99,"d":125,"lo":122,"hi":128,"t":"main","r":"2026-05-19","a":"api","b":9,"c":{"reasoning":122,"math":126,"knowledge":129},"p":[2.5,7.5],"x":{"chess_puzzles":0.26,"mystery_game_puzzles":0.32,"frontiermath_t4":0.34146341463414637,"frontiermath_t13":0.6456140350877193,"otis_mock_aime":0.9555555555555556,"swe_bench_verified":0.7727272727272727,"gpqa_diamond":0.9090909090909091,"or_gpqa_diamond":0.9090909999999999,"simpleqa_verified":0.5576730190571715,"or_tau2_airline":0.72}},{"s":"gemini-3-6-flash","n":"Gemini 3.6 Flash","o":"Google DeepMind","iq":124.73,"d":125,"lo":122,"hi":128,"t":"main","r":"2026-07-21","a":"api","b":8,"c":{"reasoning":126,"math":123,"knowledge":135},"p":[0.75,3.75],"x":{"chess_puzzles":0.42,"furniture_assembly":0.23333333333333334,"mystery_game_puzzles":0.3,"frontiermath_t4":0.21951219512195122,"frontiermath_t13":0.5894736842105263,"otis_mock_aime":0.9416666666666667,"gpqa_diamond":0.9412878787878788,"or_gpqa_diamond":0.930415,"simpleqa_verified":0.662,"or_tau2_airline":0.72}},{"s":"deepseek-v4-flash-0731","n":"DeepSeek V4 Flash 0731","o":"DeepSeek","iq":123.61,"d":124,"lo":121,"hi":127,"t":"main","r":"2026-07-31","a":"open_restricted","b":8,"c":{"reasoning":125,"math":123,"knowledge":123},"p":null,"x":{"chess_puzzles":0.32,"mystery_game_puzzles":0.34,"frontiermath_t4":0.24390243902439024,"frontiermath_t13":0.5754385964912281,"otis_mock_aime":0.9444444444444444,"gpqa_diamond":0.9103535353535354,"or_gpqa_diamond":0.8996633999999999,"simpleqa_verified":0.33633633633633636,"or_tau2_airline":0.7766665}},{"s":"claude-opus-4-6","n":"Claude Opus 4.6","o":"Anthropic","iq":122.95,"d":123,"lo":120,"hi":126,"t":"main","r":"2026-02-05","a":"api","b":9,"c":{"reasoning":117,"math":125,"knowledge":124},"p":[5.0,25.0],"x":{"chess_puzzles":0.21,"furniture_assembly":0.2833333333333333,"mystery_game_puzzles":0.25,"frontiermath_t4":0.2682926829268293,"frontiermath_t13":0.6596491228070176,"otis_mock_aime":0.9444444444444444,"swe_bench_verified":0.7871900826446281,"gpqa_diamond":0.9053030303030303,"or_gpqa_diamond":0.856643153846154,"simpleqa_verified":0.47,"or_tau2_airline":0.7638095}},{"s":"gemini-3-flash","n":"Gemini 3 Flash","o":"Google DeepMind","iq":122.36,"d":122,"lo":119,"hi":125,"t":"main","r":"2025-12-17","a":"api","b":9,"c":{"reasoning":124,"math":121,"knowledge":128},"p":[0.5,3.0],"x":{"chess_puzzles":0.39,"mystery_game_puzzles":0.26,"frontiermath_t4":0.17073170731707318,"frontiermath_t13":0.512280701754386,"otis_mock_aime":0.9555555555555556,"swe_bench_verified":0.7541322314049587,"gpqa_diamond":0.8939393939393939,"or_gpqa_diamond":0.8855220000000001,"simpleqa_verified":0.668,"or_tau2_airline":0.7533333333333333}},{"s":"kimi-k2-6","n":"Kimi K2.6","o":"Moonshot","iq":121.05,"d":121,"lo":118,"hi":124,"t":"main","r":"2026-04-20","a":"open_restricted","b":9,"c":{"reasoning":113,"math":123,"knowledge":122},"p":[0.95,4.0],"x":{"chess_puzzles":0.2,"furniture_assembly":0.21666666666666667,"mystery_game_puzzles":0.18,"frontiermath_t4":0.2564102564102564,"frontiermath_t13":0.5719298245614035,"otis_mock_aime":0.9611111111111111,"swe_bench_verified":0.7665289256198347,"gpqa_diamond":0.9078282828282829,"or_gpqa_diamond":0.8799901428571427,"simpleqa_verified":0.349,"or_tau2_airline":0.7671130223214285}},{"s":"gpt-5","n":"GPT-5","o":"OpenAI","iq":120.88,"d":121,"lo":118,"hi":124,"t":"main","r":"2025-08-07","a":"api","b":11,"c":{"reasoning":122,"math":121,"coding":121,"knowledge":121},"p":[1.25,10.0],"x":{"chess_puzzles":0.36,"mystery_game_puzzles":0.23,"frontiermath_t4":0.21951219512195122,"frontiermath_t13":0.5543859649122806,"math_level_5":0.9813066465256798,"otis_mock_aime":0.9138888888888889,"aider_polyglot":0.88,"swe_bench_verified":0.7355371900826446,"gpqa_diamond":0.8617424242424242,"or_gpqa_diamond":0.8501685000000001,"simpleqa_verified":0.501,"or_tau2_airline":0.7066666666666667}},{"s":"glm-5-2","n":"GLM-5.2","o":"Z.ai (Zhipu AI)","iq":120.83,"d":121,"lo":118,"hi":124,"t":"main","r":"2026-06-16","a":"open_restricted","b":9,"c":{"reasoning":114,"math":123,"knowledge":121},"p":[1.4,4.4],"x":{"chess_puzzles":0.22,"mystery_game_puzzles":0.19,"frontiermath_t4":0.2926829268292683,"frontiermath_t13":0.592057761732852,"otis_mock_aime":0.8638888888888889,"swe_bench_verified":0.787,"gpqa_diamond":0.9185606060606061,"or_gpqa_diamond":0.8334862727272728,"simpleqa_verified":0.342,"or_tau2_airline":0.7169697272727272}},{"s":"glm-5-3-flash","n":"GLM-5.3-Flash","o":"Z.ai (Zhipu AI)","iq":120.49,"d":120,"lo":117,"hi":124,"t":"main","r":"2026-08-20","a":"open_restricted","b":7,"c":{"reasoning":114,"math":121},"p":[0.15,0.5],"x":{"chess_puzzles":0.21,"mystery_game_puzzles":0.08,"frontiermath_t4":0.17073170731707318,"frontiermath_t13":0.5578947368421052,"otis_mock_aime":0.9388888888888889,"gpqa_diamond":0.9015151515151515,"or_gpqa_diamond":0.9090909999999999,"or_tau2_airline":0.762499875}},{"s":"gpt-5-1","n":"GPT-5.1","o":"OpenAI","iq":120.18,"d":120,"lo":115,"hi":125,"t":"main","r":"2025-11-13","a":"api","b":7,"c":{"reasoning":122,"knowledge":122},"p":[1.25,10.0],"x":{"chess_puzzles":0.42,"mystery_game_puzzles":0.19,"otis_mock_aime":0.8861111111111111,"swe_bench_verified":0.6797520661157025,"gpqa_diamond":0.8762626262626263,"or_gpqa_diamond":0.8692479999999999,"simpleqa_verified":0.48,"or_tau2_airline":0.7583332500000001}},{"s":"kimi-k2-5","n":"Kimi K2.5","o":"Moonshot","iq":118.82,"d":119,"lo":112,"hi":125,"t":"main","r":"2026-01-27","a":"open_restricted","b":5,"c":{"knowledge":118},"p":[0.6,3.0],"x":{"otis_mock_aime":0.922,"swe_bench_verified":0.737603305785124,"gpqa_diamond":0.876,"or_gpqa_diamond":0.8592592,"simpleqa_verified":0.343,"or_tau2_airline":0.7277775}},{"s":"kimi-k2-7-code","n":"Kimi K2.7 Code","o":"Moonshot","iq":118.46,"d":118,"lo":115,"hi":122,"t":"main","r":"2026-06-12","a":"open_restricted","b":7,"c":{"math":120,"knowledge":120},"p":[0.95,4.0],"x":{"chess_puzzles":0.14,"frontiermath_t4":0.12195121951219512,"frontiermath_t13":0.5403508771929825,"otis_mock_aime":0.9555555555555556,"gpqa_diamond":0.8787878787878788,"or_gpqa_diamond":0.8847767229341582,"simpleqa_verified":0.365,"or_tau2_airline":0.7383231627502177}},{"s":"inkling-small","n":"Inkling-Small","o":"Thinking Machines","iq":118.12,"d":118,"lo":115,"hi":122,"t":"main","r":"2026-07-15","a":"open_restricted","b":7,"c":{"math":119,"knowledge":115},"p":null,"x":{"mystery_game_puzzles":0.06,"frontiermath_t4":0.17073170731707318,"frontiermath_t13":0.4631578947368421,"otis_mock_aime":0.9,"gpqa_diamond":0.88510101010101,"or_gpqa_diamond":0.8703701666666666,"simpleqa_verified":0.191,"or_tau2_airline":0.6076188571428572}},{"s":"gpt-5-4-nano","n":"GPT-5.4 Nano","o":"OpenAI","iq":118.05,"d":118,"lo":115,"hi":121,"t":"main","r":"2026-03-17","a":"api","b":8,"c":{"reasoning":129,"math":117,"knowledge":105},"p":[0.2,1.25],"x":{"chess_puzzles":0.45,"mystery_game_puzzles":0.09,"frontiermath_t4":0.12195121951219512,"frontiermath_t13":0.44912280701754387,"otis_mock_aime":0.8778,"gpqa_diamond":0.7847,"or_gpqa_diamond":0.77567325,"simpleqa_verified":0.117,"or_tau2_airline":0.65166675}},{"s":"gpt-5-4-mini","n":"GPT-5.4 Mini","o":"OpenAI","iq":116.64,"d":117,"lo":113,"hi":120,"t":"main","r":"2026-03-17","a":"api","b":8,"c":{"reasoning":114,"math":118,"knowledge":115},"p":[0.75,4.5],"x":{"chess_puzzles":0.23,"mystery_game_puzzles":0.11,"frontiermath_t4":0.0975609756097561,"frontiermath_t13":0.512280701754386,"otis_mock_aime":0.8888888888888888,"gpqa_diamond":0.8686868686868687,"or_gpqa_diamond":0.84048825,"simpleqa_verified":0.294,"or_tau2_airline":0.6216667499999999}},{"s":"deepseek-v4-pro","n":"DeepSeek-V4-Pro","o":"DeepSeek","iq":116.56,"d":117,"lo":113,"hi":120,"t":"main","r":"2026-04-24","a":"open_restricted","b":9,"c":{"reasoning":111,"math":117,"knowledge":122},"p":[1.32,3.96],"x":{"chess_puzzles":0.19,"mystery_game_puzzles":0.17,"frontiermath_t4":0.024390243902439025,"frontiermath_t13":0.45263157894736844,"otis_mock_aime":0.9666666666666667,"swe_bench_verified":0.7763975155279503,"gpqa_diamond":0.9090909090909091,"or_gpqa_diamond":0.853535,"simpleqa_verified":0.46993987975951906,"or_tau2_airline":0.788889}},{"s":"o3","n":"o3","o":"OpenAI","iq":115.91,"d":116,"lo":113,"hi":119,"t":"main","r":"2025-04-16","a":"api","b":10,"c":{"reasoning":124,"math":113,"coding":111,"knowledge":114},"p":[2.0,8.0],"x":{"chess_puzzles":0.37,"mystery_game_puzzles":0.29,"frontiermath_t13":0.3333333333333333,"math_level_5":0.9777190332326284,"otis_mock_aime":0.8444444444444444,"aider_polyglot":0.813,"swe_bench_verified":0.6231884057971014,"gpqa_diamond":0.8181818181818182,"simpleqa_verified":0.494,"bfcl_overall":0.6305}},{"s":"glm-5-1","n":"GLM-5.1","o":"Z.ai (Zhipu AI)","iq":115.54,"d":116,"lo":112,"hi":120,"t":"main","r":"2026-04-07","a":"open_restricted","b":7,"c":{"math":115,"knowledge":117},"p":[1.4,4.4],"x":{"chess_puzzles":0.2,"frontiermath_t13":0.3684210526315789,"otis_mock_aime":0.9333333333333333,"swe_bench_verified":0.7417,"gpqa_diamond":0.898989898989899,"or_gpqa_diamond":0.8115756996197718,"simpleqa_verified":0.34,"or_tau2_airline":0.7433332500000001}},{"s":"gpt-5-mini","n":"GPT-5 mini","o":"OpenAI","iq":114.88,"d":115,"lo":112,"hi":118,"t":"main","r":"2025-08-07","a":"api","b":11,"c":{"reasoning":115,"math":117,"knowledge":106,"agentic":112},"p":[0.25,2.0],"x":{"chess_puzzles":0.24,"mystery_game_puzzles":0.1,"frontiermath_t4":0.12195121951219512,"frontiermath_t13":0.4666666666666667,"math_level_5":0.9784743202416919,"otis_mock_aime":0.8666666666666667,"swe_bench_verified":0.6466942148760331,"gpqa_diamond":0.75,"or_gpqa_diamond":0.8007853333333332,"simpleqa_verified":0.216,"bfcl_overall":0.5546,"or_tau2_airline":0.712121101010101}},{"s":"qwen3-6-27b","n":"Qwen3.6 27B","o":"Alibaba","iq":114.77,"d":115,"lo":110,"hi":119,"t":"main","r":"2026-04-22","a":"open_restricted","b":5,"c":{"math":114},"p":null,"x":{"mystery_game_puzzles":0.07,"frontiermath_t13":0.3508771929824561,"otis_mock_aime":0.9111111111111111,"gpqa_diamond":0.8585858585858586,"or_gpqa_diamond":0.801499818181818,"or_tau2_airline":0.7627176144578314}},{"s":"qwen3-7-plus","n":"Qwen3.7-Plus","o":"Alibaba","iq":114.66,"d":115,"lo":110,"hi":119,"t":"main","r":"2026-06-02","a":"api","b":5,"c":{"math":115},"p":null,"x":{"mystery_game_puzzles":0.17,"frontiermath_t13":0.34385964912280703,"otis_mock_aime":0.9333333333333333,"gpqa_diamond":0.8787878787878788,"or_gpqa_diamond":0.873737,"or_tau2_airline":0.726667}},{"s":"claude-opus-4-5","n":"Claude Opus 4.5","o":"Anthropic","iq":114.58,"d":115,"lo":111,"hi":118,"t":"main","r":"2025-11-24","a":"api","b":10,"c":{"reasoning":111,"math":113,"knowledge":118,"agentic":127},"p":null,"x":{"chess_puzzles":0.14,"furniture_assembly":0.2833333333333333,"mystery_game_puzzles":0.22,"frontiermath_t4":0.04878048780487805,"frontiermath_t13":0.34385964912280703,"otis_mock_aime":0.8611111111111112,"swe_bench_verified":0.7665289256198347,"gpqa_diamond":0.860479797979798,"or_gpqa_diamond":0.8610461538461541,"simpleqa_verified":0.457,"bfcl_overall":0.7746999999999999,"or_tau2_airline":0.7700000714285714}},{"s":"inkling","n":"Inkling","o":"Thinking Machines","iq":113.55,"d":114,"lo":110,"hi":117,"t":"main","r":"2026-07-15","a":"open_restricted","b":7,"c":{"math":113,"knowledge":117},"p":null,"x":{"chess_puzzles":0.21,"frontiermath_t4":0.04878048780487805,"frontiermath_t13":0.3333333333333333,"otis_mock_aime":0.8888888888888888,"gpqa_diamond":0.8825757575757576,"or_gpqa_diamond":0.818035862576065,"simpleqa_verified":0.403,"or_tau2_airline":0.6755556666666667}},{"s":"qwen3-5-397b-a17b","n":"Qwen3.5 397B-A17B","o":"Alibaba","iq":113.51,"d":114,"lo":109,"hi":118,"t":"main","r":"2026-02-13","a":"open_restricted","b":5,"c":{"math":113},"p":null,"x":{"mystery_game_puzzles":0.18,"frontiermath_t13":0.312280701754386,"otis_mock_aime":0.8888888888888888,"gpqa_diamond":0.8636363636363636,"or_gpqa_diamond":0.8728152090966519,"or_tau2_airline":0.7811111111111111}},{"s":"claude-sonnet-4-6","n":"Claude Sonnet 4.6","o":"Anthropic","iq":113.28,"d":113,"lo":108,"hi":118,"t":"main","r":"2026-02-17","a":"api","b":7,"c":{"reasoning":113,"knowledge":111},"p":[3.0,15.0],"x":{"chess_puzzles":0.23,"mystery_game_puzzles":0.16,"otis_mock_aime":0.857936507936508,"swe_bench_verified":0.7520661157024794,"gpqa_diamond":0.8737373737373737,"or_gpqa_diamond":0.6459467692307692,"simpleqa_verified":0.355,"or_tau2_airline":0.7490475714285715}},{"s":"glm-4-7","n":"GLM-4.7","o":"Z.ai (Zhipu AI)","iq":112.29,"d":112,"lo":107,"hi":118,"t":"main","r":"2025-12-22","a":"open_restricted","b":5,"c":{"knowledge":113},"p":[0.6,2.2],"x":{"chess_puzzles":0.21,"otis_mock_aime":0.8333333333333334,"gpqa_diamond":0.8333333333333334,"or_gpqa_diamond":0.8364136921606119,"simpleqa_verified":0.322,"or_tau2_airline":0.7037037777777777}},{"s":"o4-mini","n":"o4-mini","o":"OpenAI","iq":111.71,"d":112,"lo":109,"hi":115,"t":"main","r":"2025-04-16","a":"api","b":10,"c":{"reasoning":113,"math":113,"knowledge":106},"p":[1.1,4.4],"x":{"chess_puzzles":0.22,"mystery_game_puzzles":0.05,"frontiermath_t4":0.04878048780487805,"frontiermath_t13":0.36140350877192984,"math_level_5":0.978285498489426,"otis_mock_aime":0.8166666666666667,"aider_polyglot":0.72,"gpqa_diamond":0.7960858585858586,"simpleqa_verified":0.196,"bfcl_overall":0.5324}},{"s":"qwen3-235b-a22b-thinking-jul-2025","n":"Qwen3-235B-A22B-Thinking (Jul 2025)","o":"Alibaba","iq":111.39,"d":111,"lo":105,"hi":118,"t":"main","r":"2025-07-25","a":"open_restricted","b":5,"c":{"knowledge":111},"p":null,"x":{"mystery_game_puzzles":0.09,"otis_mock_aime":0.8666666666666667,"gpqa_diamond":0.8005050505050505,"or_gpqa_diamond":0.7950335,"simpleqa_verified":0.4044044044044044,"or_tau2_airline":0.6266666666666667}},{"s":"qwen-3-6-35b-a3b","n":"Qwen 3.6 35B-A3B","o":"Alibaba","iq":110.78,"d":111,"lo":107,"hi":115,"t":"main","r":"2026-04-14","a":"open_restricted","b":5,"c":{"math":108},"p":null,"x":{"mystery_game_puzzles":0.22,"frontiermath_t13":0.20350877192982456,"otis_mock_aime":0.8666666666666667,"gpqa_diamond":0.8484848484848485,"or_gpqa_diamond":0.8272847449686571,"or_tau2_airline":0.744993393858478}},{"s":"claude-sonnet-4-5","n":"Claude Sonnet 4.5","o":"Anthropic","iq":109.9,"d":110,"lo":107,"hi":113,"t":"main","r":"2025-09-29","a":"api","b":11,"c":{"reasoning":105,"math":109,"knowledge":110,"agentic":122},"p":[3.0,15.0],"x":{"chess_puzzles":0.1,"mystery_game_puzzles":0.17,"frontiermath_t4":0.024390243902439025,"frontiermath_t13":0.23859649122807017,"math_level_5":0.9773413897280967,"otis_mock_aime":0.7777777777777778,"swe_bench_verified":0.7128099173553719,"gpqa_diamond":0.8232323232323232,"or_gpqa_diamond":0.8111110666666667,"simpleqa_verified":0.307,"bfcl_overall":0.7323999999999999,"or_tau2_airline":0.7528572857142857}},{"s":"gemini-3-5-flash-lite","n":"Gemini 3.5 Flash-Lite","o":"Google DeepMind","iq":109.34,"d":109,"lo":106,"hi":113,"t":"main","r":"2026-07-21","a":"api","b":7,"c":{"reasoning":112,"math":107},"p":[0.3,2.5],"x":{"chess_puzzles":0.21,"mystery_game_puzzles":0.19,"frontiermath_t4":0.0,"frontiermath_t13":0.2596491228070175,"otis_mock_aime":0.7111111111111111,"gpqa_diamond":0.8333333333333334,"or_gpqa_diamond":0.8402775531250001,"or_tau2_airline":0.7349997500000001}},{"s":"gemini-2-5-pro-jun-2025","n":"Gemini 2.5 Pro (Jun 2025)","o":"Google DeepMind","iq":108.47,"d":108,"lo":104,"hi":112,"t":"main","r":"2025-06-05","a":"api","b":7,"c":{"math":108,"coding":108},"p":[1.25,10.0],"x":{"frontiermath_t4":0.0,"frontiermath_t13":0.24561403508771928,"otis_mock_aime":0.8472222222222222,"aider_polyglot":0.831,"swe_bench_verified":0.5755693581780539,"gpqa_diamond":0.8529040404040404,"or_gpqa_diamond":0.806210222222222,"or_tau2_airline":0.5622223333333333}},{"s":"minimax-m3","n":"MiniMax-M3","o":"MiniMax","iq":108.21,"d":108,"lo":102,"hi":114,"t":"main","r":"2026-06-01","a":"open_restricted","b":5,"c":{"reasoning":104},"p":null,"x":{"chess_puzzles":0.13,"mystery_game_puzzles":0.08,"otis_mock_aime":0.7111111111111111,"gpqa_diamond":0.9090909090909091,"or_gpqa_diamond":0.9151233333333333,"or_tau2_airline":0.7388889166666667}},{"s":"gpt-oss-120b","n":"gpt-oss-120b","o":"OpenAI","iq":105.8,"d":106,"lo":99,"hi":112,"t":"main","r":"2025-08-05","a":"open_restricted","b":5,"c":{},"p":null,"x":{"mystery_game_puzzles":0.02,"otis_mock_aime":0.8888888888888888,"aider_polyglot":0.418,"gpqa_diamond":0.7575757575757576,"or_gpqa_diamond":0.7578456145038168,"or_tau2_airline":0.633333}},{"s":"gpt-5-nano","n":"GPT-5 nano","o":"OpenAI","iq":105.46,"d":105,"lo":102,"hi":109,"t":"main","r":"2025-08-07","a":"api","b":10,"c":{"reasoning":112,"math":106,"knowledge":95,"agentic":97},"p":[0.05,0.4],"x":{"chess_puzzles":0.22,"mystery_game_puzzles":0.09,"frontiermath_t4":0.024390243902439025,"frontiermath_t13":0.2,"math_level_5":0.952416918429003,"otis_mock_aime":0.8111111111111111,"gpqa_diamond":0.6944444444444444,"or_gpqa_diamond":0.6843435000000001,"simpleqa_verified":0.117,"bfcl_overall":0.5145000000000001,"or_tau2_airline":0.4511785656565656}},{"s":"o3-mini","n":"o3-mini","o":"OpenAI","iq":104.84,"d":105,"lo":101,"hi":108,"t":"main","r":"2025-01-31","a":"api","b":9,"c":{"reasoning":105,"math":106,"knowledge":101},"p":[1.1,4.4],"x":{"chess_puzzles":0.15,"mystery_game_puzzles":0.07,"frontiermath_t4":0.0,"frontiermath_t13":0.18596491228070175,"math_level_5":0.9648791540785498,"otis_mock_aime":0.7694444444444445,"aider_polyglot":0.5379999999999999,"gpqa_diamond":0.7702020202020202,"simpleqa_verified":0.153}},{"s":"claude-haiku-4-5","n":"Claude Haiku 4.5","o":"Anthropic","iq":103.69,"d":104,"lo":99,"hi":108,"t":"main","r":"2025-10-15","a":"api","b":7,"c":{"math":105,"knowledge":97,"agentic":114},"p":null,"x":{"chess_puzzles":0.08,"math_level_5":0.9636087945413192,"otis_mock_aime":0.6666666666666666,"gpqa_diamond":0.7121212121212122,"or_gpqa_diamond":0.7310605833333333,"simpleqa_verified":0.132,"bfcl_overall":0.687,"or_tau2_airline":0.6657576363636364}},{"s":"claude-3-7-sonnet","n":"Claude 3.7 Sonnet","o":"Anthropic","iq":99.03,"d":99,"lo":95,"hi":103,"t":"main","r":"2025-02-24","a":"api","b":5,"c":{"math":97,"coding":102},"p":null,"x":{"math_level_5":0.9116314199395771,"otis_mock_aime":0.5777777777777777,"aider_polyglot":0.649,"swe_bench_verified":0.609504132231405,"gpqa_diamond":0.7973484848484849}},{"s":"claude-opus-4","n":"Claude Opus 4","o":"Anthropic","iq":97.79,"d":98,"lo":93,"hi":102,"t":"main","r":"2025-05-22","a":"api","b":5,"c":{"math":94,"coding":108},"p":null,"x":{"math_level_5":0.850453172205438,"otis_mock_aime":0.6444444444444445,"aider_polyglot":0.72,"swe_bench_verified":0.7066115702479339,"gpqa_diamond":0.7626262626262627}},{"s":"claude-sonnet-4","n":"Claude Sonnet 4","o":"Anthropic","iq":97.1,"d":97,"lo":93,"hi":101,"t":"main","r":"2025-05-22","a":"api","b":5,"c":{"math":95},"p":null,"x":{"math_level_5":0.8436555891238671,"otis_mock_aime":0.7111111111111111,"aider_polyglot":0.613,"gpqa_diamond":0.7918781725888325,"or_gpqa_diamond":0.7672559999999999,"or_tau2_airline":0.64}},{"s":"qwen3-32b","n":"Qwen3-32B","o":"Alibaba","iq":94.61,"d":95,"lo":89,"hi":100,"t":"main","r":"2025-04-28","a":"open_restricted","b":5,"c":{"agentic":92},"p":null,"x":{"otis_mock_aime":0.6694444444444444,"aider_polyglot":0.4,"gpqa_diamond":0.6571969696969697,"or_gpqa_diamond":0.5572391666666667,"bfcl_overall":0.48710000000000003,"or_tau2_airline":0.4516665}},{"s":"gpt-4-1-mini","n":"GPT-4.1 mini","o":"OpenAI","iq":91.36,"d":91,"lo":88,"hi":95,"t":"main","r":"2025-04-14","a":"api","b":10,"c":{"reasoning":90,"math":92,"knowledge":89,"agentic":92},"p":[0.4,1.6],"x":{"chess_puzzles":0.01,"mystery_game_puzzles":0.07,"frontiermath_t13":0.06666666666666667,"math_level_5":0.8729229607250756,"otis_mock_aime":0.44722222222222224,"aider_polyglot":0.324,"gpqa_diamond":0.6584595959595959,"or_gpqa_diamond":0.6473065000000001,"simpleqa_verified":0.127,"bfcl_overall":0.5045000000000001,"or_tau2_airline":0.44333325}},{"s":"gpt-4-1","n":"GPT-4.1","o":"OpenAI","iq":90.89,"d":91,"lo":87,"hi":94,"t":"main","r":"2025-04-14","a":"api","b":10,"c":{"math":90,"coding":91,"knowledge":95,"agentic":95},"p":[2.0,8.0],"x":{"chess_puzzles":0.03,"frontiermath_t13":0.05964912280701754,"math_level_5":0.8300604229607251,"otis_mock_aime":0.38333333333333336,"aider_polyglot":0.524,"swe_bench_verified":0.48541666666666666,"gpqa_diamond":0.6691919191919192,"or_gpqa_diamond":0.6607744999999999,"simpleqa_verified":0.311,"bfcl_overall":0.5396,"or_tau2_airline":0.5083332500000001}},{"s":"llama-4-maverick","n":"Llama 4 Maverick","o":"Meta AI","iq":80.84,"d":81,"lo":77,"hi":85,"t":"main","r":"2025-04-05","a":"open_restricted","b":6,"c":{"math":80,"agentic":80},"p":null,"x":{"math_level_5":0.7301737160120846,"otis_mock_aime":0.20555555555555555,"aider_polyglot":0.156,"gpqa_diamond":0.6698232323232324,"or_gpqa_diamond":0.6478116,"bfcl_overall":0.3729,"or_tau2_airline":0.43089426016260163}},{"s":"gemma-3-27b","n":"Gemma 3 27B","o":"Google DeepMind","iq":76.78,"d":77,"lo":72,"hi":81,"t":"main","r":"2025-03-12","a":"open_restricted","b":5,"c":{"math":81},"p":null,"x":{"math_level_5":0.740370090634441,"otis_mock_aime":0.225,"aider_polyglot":0.049,"gpqa_diamond":0.4772727272727273,"bfcl_overall":0.29469999999999996}},{"s":"gpt-4-1-nano","n":"GPT-4.1 nano","o":"OpenAI","iq":76.07,"d":76,"lo":72,"hi":80,"t":"main","r":"2025-04-14","a":"api","b":8,"c":{"math":80,"knowledge":72,"agentic":66},"p":[0.1,0.4],"x":{"chess_puzzles":0.0,"math_level_5":0.6999622356495468,"otis_mock_aime":0.28888888888888886,"aider_polyglot":0.08900000000000001,"gpqa_diamond":0.48926767676767674,"or_gpqa_diamond":0.4966332500000001,"simpleqa_verified":0.06,"bfcl_overall":0.33049999999999996,"or_tau2_airline":0.11833325}},{"s":"gpt-4o-aug-2024","n":"GPT-4o (Aug 2024)","o":"OpenAI","iq":72.72,"d":73,"lo":68,"hi":77,"t":"main","r":"2024-08-06","a":"api","b":8,"c":{"math":69,"knowledge":79},"p":[2.5,10.0],"x":{"chess_puzzles":0.06,"frontiermath_t13":0.0035087719298245615,"math_level_5":0.5327605740181269,"otis_mock_aime":0.06388888888888888,"aider_polyglot":0.231,"gpqa_diamond":0.49210858585858586,"or_gpqa_diamond":0.5280586666666666,"simpleqa_verified":0.26,"or_tau2_airline":0.43}},{"s":"gpt-4o-nov-2024","n":"GPT-4o (Nov 2024)","o":"OpenAI","iq":68.66,"d":69,"lo":64,"hi":73,"t":"main","r":"2024-11-20","a":"api","b":5,"c":{"math":68,"coding":68},"p":[2.5,10.0],"x":{"math_level_5":0.49773413897280966,"otis_mock_aime":0.0625,"aider_polyglot":0.182,"swe_bench_verified":0.30991735537190085,"gpqa_diamond":0.4788510101010101}},{"s":"gpt-4o-mini","n":"GPT-4o mini","o":"OpenAI","iq":68.33,"d":68,"lo":64,"hi":73,"t":"main","r":"2024-07-18","a":"api","b":9,"c":{"reasoning":80,"math":70,"knowledge":64},"p":[0.15,0.6],"x":{"chess_puzzles":0.03,"mystery_game_puzzles":0.12,"frontiermath_t13":0.007017543859649123,"math_level_5":0.5263406344410876,"otis_mock_aime":0.06944444444444445,"aider_polyglot":0.036000000000000004,"gpqa_diamond":0.37720959595959597,"or_gpqa_diamond":0.4305555,"simpleqa_verified":0.083,"or_tau2_airline":0.28000025}},{"s":"llama-3-3-70b","n":"Llama 3.3 70B","o":"Meta AI","iq":66.19,"d":66,"lo":61,"hi":71,"t":"main","r":"2024-12-06","a":"open_restricted","b":5,"c":{"math":65,"agentic":68},"p":null,"x":{"math_level_5":0.41597432024169184,"otis_mock_aime":0.05138888888888889,"gpqa_diamond":0.4744318181818182,"or_gpqa_diamond":0.4753785,"bfcl_overall":0.319,"or_tau2_airline":0.313333}},{"s":"gpt-5-5-pro","n":"GPT-5.5 Pro","o":"OpenAI","iq":138.92,"d":139,"lo":135,"hi":142,"t":"insufficient","r":"2026-04-23","a":"api","b":5,"c":{"math":139},"p":null,"x":{"chess_puzzles":0.62,"frontiermath_t4":0.7804878048780488,"frontiermath_t13":0.8771929824561403,"otis_mock_aime":1.0,"gpqa_diamond":0.9392135642135643}},{"s":"ai-co-mathematician","n":"AI Co-Mathematician","o":"Google DeepMind","iq":137.44,"d":137,"lo":132,"hi":142,"t":"insufficient","r":"2026-05-08","a":"unknown","b":1,"c":{},"p":null,"x":{"frontiermath_t4":0.756}},{"s":"muse-wonder","n":"Muse Wonder","o":"Meta AI","iq":135.97,"d":136,"lo":133,"hi":139,"t":"insufficient","r":"2026-10-12","a":"api","b":4,"c":{"math":136},"p":null,"x":{"furniture_assembly":0.5416666666666666,"mystery_game_puzzles":0.51,"frontiermath_t4":0.7073170731707317,"frontiermath_t13":0.8210526315789474,"otis_mock_aime":0.9944444444444445}},{"s":"gpt-5-4-pro","n":"GPT-5.4 Pro","o":"OpenAI","iq":134.57,"d":135,"lo":131,"hi":138,"t":"insufficient","r":"2026-03-05","a":"api","b":5,"c":{"math":134,"knowledge":134},"p":null,"x":{"chess_puzzles":0.59,"frontiermath_t4":0.5853658536585366,"frontiermath_t13":0.8245614035087719,"gpqa_diamond":0.946,"simpleqa_verified":0.463}},{"s":"gpt-5-2-pro","n":"GPT-5.2 Pro","o":"OpenAI","iq":131.58,"d":132,"lo":128,"hi":135,"t":"insufficient","r":"2025-12-11","a":"api","b":3,"c":{"math":130},"p":null,"x":{"chess_puzzles":0.6,"frontiermath_t4":0.46,"frontiermath_t13":0.74}},{"s":"mimo-v2-6-pro","n":"MiMo-V2.6 Pro","o":"Xiaomi Corp","iq":130.64,"d":131,"lo":117,"hi":144,"t":"insufficient","r":"2026-09-21","a":"unknown","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.8989897499999999,"or_tau2_airline":0.7983335000000001}},{"s":"qwen-3-8-max","n":"Qwen 3.8 Max","o":"Alibaba","iq":130.14,"d":130,"lo":127,"hi":133,"t":"insufficient","r":"2026-08-02","a":"api","b":7,"c":{"reasoning":130,"math":130,"knowledge":130},"p":[2.0,6.0],"x":{"chess_puzzles":0.46,"mystery_game_puzzles":0.38,"frontiermath_t4":0.4634146341463415,"frontiermath_t13":0.7473684210526316,"otis_mock_aime":0.9944444444444445,"gpqa_diamond":0.9267676767676768,"simpleqa_verified":0.458}},{"s":"deepseek-v4-flash","n":"DeepSeek-V4-Flash","o":"DeepSeek","iq":129.31,"d":129,"lo":116,"hi":143,"t":"insufficient","r":"2026-04-24","a":"open_restricted","b":2,"c":{},"p":[0.3,1.2],"x":{"or_gpqa_diamond":0.8989900000000001,"or_tau2_airline":0.7755553333333334}},{"s":"tencent-hy4-preview","n":"Tencent Hy4 preview","o":"Tencent","iq":129.16,"d":129,"lo":115,"hi":143,"t":"insufficient","r":"2026-08-28","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.8973063333333335,"or_tau2_airline":0.7777776666666667}},{"s":"muse-spark-1-3","n":"Muse Spark 1.3","o":"Meta AI","iq":127.9,"d":128,"lo":125,"hi":131,"t":"insufficient","r":"2026-09-02","a":"api","b":5,"c":{"reasoning":123,"math":130},"p":null,"x":{"chess_puzzles":0.37,"mystery_game_puzzles":0.25,"frontiermath_t4":0.4634146341463415,"frontiermath_t13":0.743859649122807,"otis_mock_aime":0.9916666666666667}},{"s":"qwen3-8-max-0902","n":"Qwen3.8 Max (0902)","o":"Alibaba","iq":126.55,"d":127,"lo":123,"hi":130,"t":"insufficient","r":"2026-09-01","a":"api","b":6,"c":{"math":127,"knowledge":128},"p":null,"x":{"chess_puzzles":0.37,"furniture_assembly":0.2,"frontiermath_t4":0.34146341463414637,"frontiermath_t13":0.656140350877193,"otis_mock_aime":1.0,"gpqa_diamond":0.922979797979798,"simpleqa_verified":0.473}},{"s":"muse-spark-1-1","n":"Muse Spark 1.1","o":"Meta AI","iq":124.66,"d":125,"lo":116,"hi":133,"t":"insufficient","r":"2026-07-09","a":"api","b":2,"c":{},"p":null,"x":{"chess_puzzles":0.34,"simpleqa_verified":0.5778894472361809}},{"s":"qwen3-8-flash","n":"Qwen3.8 Flash","o":"Alibaba","iq":124.58,"d":125,"lo":111,"hi":138,"t":"insufficient","r":"2026-08-26","a":"api","b":2,"c":{},"p":[0.15,0.47],"x":{"or_gpqa_diamond":0.8962022556962025,"or_tau2_airline":0.7}},{"s":"grok-4-5","n":"Grok 4.5","o":"xAI","iq":124.15,"d":124,"lo":121,"hi":127,"t":"insufficient","r":"2026-07-08","a":"api","b":6,"c":{"math":123,"knowledge":130},"p":[2.0,6.0],"x":{"chess_puzzles":0.35,"furniture_assembly":0.225,"frontiermath_t4":0.24390243902439024,"frontiermath_t13":0.5719298245614035,"otis_mock_aime":0.9777777777777777,"gpqa_diamond":0.9343434343434344,"simpleqa_verified":0.483}},{"s":"gpt-5-pro","n":"GPT-5 Pro","o":"OpenAI","iq":123.99,"d":124,"lo":120,"hi":128,"t":"insufficient","r":"2025-10-07","a":"api","b":3,"c":{"math":122},"p":null,"x":{"chess_puzzles":0.48,"frontiermath_t4":0.1951219512195122,"frontiermath_t13":0.5578947368421052}},{"s":"grok-4-7","n":"Grok 4.7","o":"xAI","iq":123.38,"d":123,"lo":120,"hi":127,"t":"insufficient","r":"2026-09-21","a":"api","b":7,"c":{"reasoning":126,"math":121,"knowledge":130},"p":[2.0,6.0],"x":{"chess_puzzles":0.41,"furniture_assembly":0.20833333333333334,"mystery_game_puzzles":0.29,"frontiermath_t4":0.17073170731707318,"frontiermath_t13":0.5298245614035088,"otis_mock_aime":0.9805555555555555,"gpqa_diamond":0.92739898989899,"simpleqa_verified":0.56}},{"s":"gemini-3-pro","n":"Gemini 3 Pro","o":"Google DeepMind","iq":122.41,"d":122,"lo":115,"hi":130,"t":"insufficient","r":"2025-11-18","a":"api","b":4,"c":{},"p":null,"x":{"otis_mock_aime":0.9138888888888889,"swe_bench_verified":0.7293388429752066,"gpqa_diamond":0.9261363636363636,"bfcl_overall":0.7251000000000001}},{"s":"gpt-5-3-codex","n":"GPT-5.3 Codex","o":"OpenAI","iq":122.35,"d":122,"lo":108,"hi":136,"t":"insufficient","r":"2026-02-05","a":"api","b":2,"c":{},"p":null,"x":{"swe_bench_verified":0.7479338842975206,"or_tau2_airline":0.753333}},{"s":"mistral-large-4","n":"Mistral Large 4","o":"Mistral AI","iq":121.91,"d":122,"lo":119,"hi":125,"t":"insufficient","r":"2026-10-06","a":"unknown","b":7,"c":{"reasoning":119,"math":124,"knowledge":116},"p":[0.68,2.09],"x":{"chess_puzzles":0.33,"furniture_assembly":0.20833333333333334,"mystery_game_puzzles":0.17,"frontiermath_t4":0.2682926829268293,"frontiermath_t13":0.5859649122807018,"otis_mock_aime":0.9833333333333333,"gpqa_diamond":0.8806818181818182,"simpleqa_verified":0.2}},{"s":"mimo-v2-5-pro","n":"MiMo-V2.5-Pro","o":"Xiaomi Corp","iq":121.32,"d":121,"lo":108,"hi":135,"t":"insufficient","r":"2026-04-23","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.8550657272727274,"or_tau2_airline":0.743889}},{"s":"muse-spark-1-2","n":"Muse Spark 1.2","o":"Meta AI","iq":120.53,"d":121,"lo":112,"hi":129,"t":"insufficient","r":"2026-08-05","a":"api","b":2,"c":{},"p":null,"x":{"chess_puzzles":0.27,"simpleqa_verified":0.6030150753768844}},{"s":"minimax-m2-7","n":"MiniMax-M2.7","o":"MiniMax","iq":120.34,"d":120,"lo":107,"hi":134,"t":"insufficient","r":"2026-03-18","a":"open_noncommercial","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.8570973081339713,"or_tau2_airline":0.7203921764705883}},{"s":"minimax-m2-1","n":"MiniMax-M2.1","o":"MiniMax","iq":119.62,"d":120,"lo":106,"hi":133,"t":"insufficient","r":"2025-12-23","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.868687,"or_tau2_airline":0.6783334999999999}},{"s":"qwen-3-8-27b","n":"Qwen 3.8 27B","o":"Alibaba","iq":119.55,"d":120,"lo":106,"hi":133,"t":"insufficient","r":"2026-08-14","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.83367,"or_tau2_airline":0.7592592222222222}},{"s":"o3-pro","n":"o3-pro","o":"OpenAI","iq":119.18,"d":119,"lo":103,"hi":135,"t":"insufficient","r":"2025-06-10","a":"api","b":1,"c":{},"p":null,"x":{"aider_polyglot":0.8490000000000001}},{"s":"minimax-m2-5","n":"MiniMax-M2.5","o":"MiniMax","iq":118.42,"d":118,"lo":105,"hi":132,"t":"insufficient","r":"2026-02-12","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.8539973475609757,"or_tau2_airline":0.6905556666666667}},{"s":"muse-spark","n":"Muse Spark","o":"Meta AI","iq":117.99,"d":118,"lo":110,"hi":126,"t":"insufficient","r":"2026-04-08","a":"api","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.889,"gpqa_diamond":0.898}},{"s":"qwen-3-6-max-preview","n":"Qwen 3.6 Max (Preview)","o":"Alibaba","iq":117.68,"d":118,"lo":112,"hi":124,"t":"insufficient","r":"2026-04-20","a":"unknown","b":5,"c":{"knowledge":121},"p":null,"x":{"mystery_game_puzzles":0.19,"otis_mock_aime":0.9111111111111111,"swe_bench_verified":0.7665289256198347,"gpqa_diamond":0.8737373737373737,"simpleqa_verified":0.5200400801603207}},{"s":"mimo-v2-5","n":"MiMo-V2.5","o":"Xiaomi Corp","iq":117.34,"d":117,"lo":104,"hi":131,"t":"insufficient","r":"2026-04-23","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.8239975454545455,"or_tau2_airline":0.7372220833333334}},{"s":"grok-4-3-beta","n":"Grok 4.3 Beta","o":"xAI","iq":117.22,"d":117,"lo":114,"hi":121,"t":"insufficient","r":"2026-04-17","a":"hosted","b":6,"c":{"math":118,"knowledge":119},"p":[1.25,2.5],"x":{"chess_puzzles":0.18,"frontiermath_t4":0.14634146341463414,"frontiermath_t13":0.4280701754385965,"otis_mock_aime":0.9333333333333333,"gpqa_diamond":0.8882575757575758,"simpleqa_verified":0.332}},{"s":"glm-4-6","n":"GLM-4.6","o":"Z.ai (Zhipu AI)","iq":116.82,"d":117,"lo":106,"hi":128,"t":"insufficient","r":"2025-09-30","a":"open_restricted","b":3,"c":{"agentic":123},"p":[0.6,2.2],"x":{"or_gpqa_diamond":0.7646065075987841,"bfcl_overall":0.7238,"or_tau2_airline":0.7344445}},{"s":"glm-4-5-air","n":"GLM-4.5-Air","o":"Z.ai (Zhipu AI)","iq":114.25,"d":114,"lo":91,"hi":137,"t":"insufficient","r":"2025-07-20","a":"open_restricted","b":1,"c":{},"p":null,"x":{"or_tau2_airline":0.68}},{"s":"deepseek-v3-2","n":"DeepSeek-V3.2","o":"DeepSeek","iq":114.2,"d":114,"lo":101,"hi":127,"t":"insufficient","r":"2025-12-01","a":"open_restricted","b":2,"c":{},"p":[0.28,0.42],"x":{"or_gpqa_diamond":0.802714625,"or_tau2_airline":0.7193332}},{"s":"nemotron-3-ultra","n":"Nemotron 3 Ultra","o":"Nvidia","iq":114.16,"d":114,"lo":108,"hi":120,"t":"insufficient","r":"2026-06-04","a":"open_restricted","b":4,"c":{},"p":null,"x":{"mystery_game_puzzles":0.2,"otis_mock_aime":0.8666666666666667,"gpqa_diamond":0.8535353535353535,"or_tau2_airline":0.72}},{"s":"grok-4","n":"Grok 4","o":"xAI","iq":113.61,"d":114,"lo":107,"hi":120,"t":"insufficient","r":"2025-07-09","a":"api","b":4,"c":{},"p":null,"x":{"otis_mock_aime":0.84,"aider_polyglot":0.7959999999999999,"gpqa_diamond":0.87,"bfcl_overall":0.6297}},{"s":"qwen-3-6-plus","n":"Qwen 3.6 Plus","o":"Alibaba","iq":112.64,"d":113,"lo":109,"hi":117,"t":"insufficient","r":"2026-03-31","a":"api","b":7,"c":{"reasoning":105,"math":116,"knowledge":119},"p":null,"x":{"chess_puzzles":0.14,"mystery_game_puzzles":0.12,"frontiermath_t13":0.3824561403508772,"otis_mock_aime":0.9333333333333333,"swe_bench_verified":0.5785123966942148,"gpqa_diamond":0.8838383838383839,"simpleqa_verified":0.44144144144144143}},{"s":"kimi-k2-thinking","n":"Kimi K2 Thinking","o":"Moonshot","iq":112.4,"d":112,"lo":99,"hi":126,"t":"insufficient","r":"2025-11-06","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.796581,"or_tau2_airline":0.695}},{"s":"qwen3-5-122b-a10b","n":"Qwen3.5-122B-A10B","o":"Alibaba","iq":112.23,"d":112,"lo":103,"hi":121,"t":"insufficient","r":"2026-02-24","a":"open_restricted","b":3,"c":{},"p":null,"x":{"mystery_game_puzzles":0.17,"or_gpqa_diamond":0.8073469346289753,"or_tau2_airline":0.7471783002257337}},{"s":"mimo-v2-6-flash","n":"MiMo-V2.6 Flash","o":"Xiaomi Corp","iq":111.9,"d":112,"lo":99,"hi":125,"t":"insufficient","r":"2026-09-21","a":"unknown","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.758698,"or_tau2_airline":0.76}},{"s":"deepseek-v3-2-exp","n":"DeepSeek-V3.2-Exp","o":"DeepSeek","iq":111.75,"d":112,"lo":103,"hi":121,"t":"insufficient","r":"2025-09-29","a":"open_restricted","b":4,"c":{"agentic":111},"p":null,"x":{"aider_polyglot":0.742,"or_gpqa_diamond":0.8265989999999999,"bfcl_overall":0.5672999999999999,"or_tau2_airline":0.693333}},{"s":"glm-5","n":"GLM-5","o":"Z.ai (Zhipu AI)","iq":111.61,"d":112,"lo":105,"hi":118,"t":"insufficient","r":"2026-02-11","a":"open_restricted","b":4,"c":{},"p":[1.0,3.2],"x":{"otis_mock_aime":0.8,"swe_bench_verified":0.7207792207792207,"gpqa_diamond":0.8781725888324873,"or_gpqa_diamond":0.7285024173913045,"or_tau2_airline":0.7422222222222222}},{"s":"gemini-3-1-flash-lite","n":"Gemini 3.1 Flash-Lite","o":"Google","iq":109.3,"d":109,"lo":105,"hi":114,"t":"insufficient","r":"2026-03-03","a":"api","b":3,"c":{"math":109},"p":[0.25,1.5],"x":{"frontiermath_t13":0.2771929824561403,"otis_mock_aime":0.8,"gpqa_diamond":0.8181818181818182}},{"s":"qwen-3-5-plus-hosted-397b-a17b","n":"Qwen 3.5 Plus (hosted 397B-A17B)","o":"Alibaba","iq":108.96,"d":109,"lo":103,"hi":115,"t":"insufficient","r":"2026-02-16","a":"unknown","b":5,"c":{"reasoning":105,"knowledge":111},"p":null,"x":{"chess_puzzles":0.08,"mystery_game_puzzles":0.17,"otis_mock_aime":0.8666666666666667,"gpqa_diamond":0.8484848484848485,"simpleqa_verified":0.2535070140280561}},{"s":"gemini-2-5-pro-mar-2025","n":"Gemini 2.5 Pro (Mar 2025)","o":"Google DeepMind","iq":107.69,"d":108,"lo":102,"hi":113,"t":"insufficient","r":"2025-03-25","a":"api","b":3,"c":{},"p":null,"x":{"math_level_5":0.9556268882175226,"aider_polyglot":0.7290000000000001,"gpqa_diamond":0.8383838383838383}},{"s":"qwen-3-6-flash","n":"Qwen 3.6 Flash","o":"Alibaba","iq":107.47,"d":107,"lo":103,"hi":111,"t":"insufficient","r":"2026-04-27","a":"unknown","b":6,"c":{"reasoning":106,"math":108,"knowledge":107},"p":null,"x":{"chess_puzzles":0.12,"mystery_game_puzzles":0.18,"frontiermath_t13":0.22456140350877193,"otis_mock_aime":0.8444444444444444,"gpqa_diamond":0.8333333333333334,"simpleqa_verified":0.15915915915915915}},{"s":"qwen3-7-flash","n":"Qwen3.7 Flash","o":"Alibaba","iq":107.46,"d":107,"lo":103,"hi":112,"t":"insufficient","r":"2026-07-27","a":"api","b":4,"c":{"math":107},"p":null,"x":{"mystery_game_puzzles":0.15,"frontiermath_t13":0.19298245614035087,"otis_mock_aime":0.8666666666666667,"gpqa_diamond":0.8232323232323232}},{"s":"gpt-5-5-instant","n":"GPT-5.5 Instant","o":"OpenAI","iq":107.42,"d":107,"lo":103,"hi":111,"t":"insufficient","r":"2026-05-05","a":"api","b":4,"c":{"math":107},"p":null,"x":{"frontiermath_t4":0.024390243902439025,"frontiermath_t13":0.2631578947368421,"otis_mock_aime":0.6805555555555556,"gpqa_diamond":0.8251262626262627}},{"s":"qwen-3-5-flash-hosted-35b-a3b","n":"Qwen 3.5 Flash (hosted 35B-A3B)","o":"Alibaba","iq":107.34,"d":107,"lo":103,"hi":111,"t":"insufficient","r":"2026-02-25","a":"unknown","b":6,"c":{"reasoning":109,"math":106,"knowledge":107},"p":null,"x":{"chess_puzzles":0.14,"mystery_game_puzzles":0.2,"frontiermath_t13":0.1824561403508772,"otis_mock_aime":0.8444444444444444,"gpqa_diamond":0.8232323232323232,"simpleqa_verified":0.2032032032032032}},{"s":"qwen3-max","n":"Qwen3-Max","o":"Alibaba","iq":106.25,"d":106,"lo":103,"hi":110,"t":"insufficient","r":"2025-09-24","a":"api","b":6,"c":{"math":107,"knowledge":105},"p":null,"x":{"mystery_game_puzzles":0.05,"frontiermath_t13":0.18947368421052632,"math_level_5":0.9712990936555891,"otis_mock_aime":0.7333333333333333,"gpqa_diamond":0.726010101010101,"simpleqa_verified":0.4874874874874875}},{"s":"gemma-4-26b-a4b","n":"Gemma 4 26B A4B","o":"Google DeepMind","iq":106.0,"d":106,"lo":100,"hi":112,"t":"insufficient","r":"2026-04-02","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.8222222222222222,"gpqa_diamond":0.7323232323232324,"or_gpqa_diamond":0.7762077565217391,"or_tau2_airline":0.5733334999999999}},{"s":"qwen3-5-35b-a3b","n":"Qwen3.5-35B-A3B","o":"Alibaba","iq":105.72,"d":106,"lo":100,"hi":112,"t":"insufficient","r":"2026-02-24","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.7,"gpqa_diamond":0.8345959595959596,"or_gpqa_diamond":0.7500000000000001,"or_tau2_airline":0.7351189375}},{"s":"claude-opus-4-1","n":"Claude Opus 4.1","o":"Anthropic","iq":105.42,"d":105,"lo":102,"hi":109,"t":"insufficient","r":"2025-08-05","a":"api","b":6,"c":{"math":103},"p":null,"x":{"mystery_game_puzzles":0.21,"frontiermath_t4":0.024390243902439025,"frontiermath_t13":0.12631578947368421,"otis_mock_aime":0.6888888888888889,"swe_bench_verified":0.7334710743801653,"gpqa_diamond":0.7727272727272727}},{"s":"kimi-k2-sep-2025","n":"Kimi K2 (Sep 2025)","o":"Moonshot","iq":105.12,"d":105,"lo":92,"hi":118,"t":"insufficient","r":"2025-09-05","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.7474749999999999,"or_tau2_airline":0.6366665}},{"s":"deepseek-r1-may-2025","n":"DeepSeek-R1 (May 2025)","o":"DeepSeek","iq":104.26,"d":104,"lo":100,"hi":109,"t":"insufficient","r":"2025-05-28","a":"open_restricted","b":4,"c":{"math":105},"p":null,"x":{"math_level_5":0.9663897280966768,"otis_mock_aime":0.6638888888888889,"gpqa_diamond":0.7632575757575758,"or_gpqa_diamond":0.7851099187817259,"or_tau2_airline":0.47874697986577186}},{"s":"gemini-2-5-pro-may-2025","n":"Gemini 2.5 Pro (May 2025)","o":"Google DeepMind","iq":104.02,"d":104,"lo":98,"hi":110,"t":"insufficient","r":"2025-05-06","a":"api","b":3,"c":{},"p":null,"x":{"math_level_5":0.9590256797583081,"aider_polyglot":0.769,"gpqa_diamond":0.6666666666666666}},{"s":"gemma-4-31b-it","n":"Gemma 4 31B IT","o":"Google DeepMind","iq":103.97,"d":104,"lo":98,"hi":110,"t":"insufficient","r":"2026-04-02","a":"open_restricted","b":4,"c":{"knowledge":100},"p":null,"x":{"otis_mock_aime":0.7333333333333333,"gpqa_diamond":0.7575757575757576,"or_gpqa_diamond":0.81649825,"simpleqa_verified":0.104,"or_tau2_airline":0.756666625}},{"s":"qwen3-coder-next","n":"qwen3-coder-next","o":"—","iq":103.24,"d":103,"lo":90,"hi":116,"t":"insufficient","r":"2026-02-02","a":"unknown","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.7575756666666668,"or_tau2_airline":0.5762463812316716}},{"s":"o1","n":"o1","o":"OpenAI","iq":102.84,"d":103,"lo":99,"hi":106,"t":"insufficient","r":"2024-12-17","a":"api","b":6,"c":{"math":103,"knowledge":106},"p":[15.0,60.0],"x":{"chess_puzzles":0.1,"frontiermath_t13":0.14736842105263157,"math_level_5":0.947129909365559,"otis_mock_aime":0.7333333333333333,"gpqa_diamond":0.7676767676767676,"simpleqa_verified":0.411}},{"s":"deepseek-v3-1-terminus","n":"DeepSeek-V3.1-Terminus","o":"DeepSeek","iq":102.34,"d":102,"lo":89,"hi":115,"t":"insufficient","r":"2025-09-22","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.7942762,"or_tau2_airline":0.48266679999999995}},{"s":"gemini-2-5-flash-jun-2025","n":"Gemini 2.5 Flash (Jun 2025)","o":"Google DeepMind","iq":102.12,"d":102,"lo":91,"hi":113,"t":"insufficient","r":"2025-06-17","a":"api","b":3,"c":{"agentic":102},"p":[0.3,2.5],"x":{"or_gpqa_diamond":0.738309,"bfcl_overall":0.5624,"or_tau2_airline":0.5511113333333334}},{"s":"gemini-2-5-flash-may-2025","n":"Gemini 2.5 Flash (May 2025)","o":"Google DeepMind","iq":101.52,"d":102,"lo":94,"hi":109,"t":"insufficient","r":"2025-05-20","a":"api","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.7083333333333334,"aider_polyglot":0.551}},{"s":"gemini-2-5-flash-apr-2025","n":"Gemini 2.5 Flash (Apr 2025)","o":"Google DeepMind","iq":101.19,"d":101,"lo":94,"hi":108,"t":"insufficient","r":"2025-04-17","a":"api","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.7305555555555555,"aider_polyglot":0.47100000000000003}},{"s":"qwen3-5-9b","n":"Qwen3.5-9B","o":"Alibaba","iq":100.89,"d":101,"lo":95,"hi":107,"t":"insufficient","r":"2026-02-24","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.6166666666666667,"gpqa_diamond":0.7897727272727273,"or_gpqa_diamond":0.7462993119730186,"or_tau2_airline":0.650067849593496}},{"s":"grok-3-mini","n":"Grok-3 mini","o":"xAI","iq":100.01,"d":100,"lo":95,"hi":105,"t":"insufficient","r":"2025-04-09","a":"api","b":4,"c":{"math":100},"p":null,"x":{"math_level_5":0.9093655589123867,"otis_mock_aime":0.7777777777777778,"aider_polyglot":0.493,"gpqa_diamond":0.7626262626262627}},{"s":"deepseek-v3-1","n":"DeepSeek-V3.1","o":"DeepSeek","iq":99.74,"d":100,"lo":87,"hi":113,"t":"insufficient","r":"2025-08-21","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.7707982259154932,"or_tau2_airline":0.47222181249999995}},{"s":"qwen3-30b-a3b-thinking-jul-2025","n":"Qwen3-30B-A3B-Thinking (Jul 2025)","o":"Alibaba","iq":99.71,"d":100,"lo":93,"hi":106,"t":"insufficient","r":"2025-07-30","a":"open_restricted","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.7027777777777777,"gpqa_diamond":0.7007575757575758}},{"s":"seed-oss-36b-instruct","n":"seed-oss-36b-instruct","o":"—","iq":99.39,"d":99,"lo":93,"hi":106,"t":"insufficient","r":"2025-08-20","a":"unknown","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.675,"gpqa_diamond":0.7152777777777778}},{"s":"deepseek-r1","n":"DeepSeek-R1","o":"DeepSeek","iq":97.8,"d":98,"lo":93,"hi":102,"t":"insufficient","r":"2025-01-20","a":"open_restricted","b":4,"c":{"math":98},"p":null,"x":{"math_level_5":0.9305135951661632,"otis_mock_aime":0.5333333333333333,"aider_polyglot":0.569,"gpqa_diamond":0.7171717171717171}},{"s":"qwen3-235b-a22b-instruct-jul-2025","n":"Qwen3-235B-A22B-Instruct (Jul 2025)","o":"Alibaba","iq":95.87,"d":96,"lo":85,"hi":107,"t":"insufficient","r":"2025-07-25","a":"open_restricted","b":3,"c":{"agentic":92},"p":null,"x":{"or_gpqa_diamond":0.7388167142857143,"bfcl_overall":0.5215,"or_tau2_airline":0.3961905714285714}},{"s":"grok-3","n":"Grok 3","o":"xAI","iq":95.81,"d":96,"lo":91,"hi":100,"t":"insufficient","r":"2025-04-09","a":"api","b":4,"c":{"math":95},"p":null,"x":{"math_level_5":0.8874622356495468,"otis_mock_aime":0.5555555555555556,"aider_polyglot":0.5329999999999999,"gpqa_diamond":0.7575757575757576}},{"s":"qwen3-5-4b","n":"Qwen3.5-4B","o":"Alibaba","iq":95.56,"d":96,"lo":88,"hi":103,"t":"insufficient","r":"2026-02-24","a":"open_restricted","b":1,"c":{},"p":null,"x":{"otis_mock_aime":0.5583333333333333}},{"s":"mistral-small-4","n":"Mistral Small 4","o":"Mistral AI","iq":95.51,"d":96,"lo":83,"hi":108,"t":"insufficient","r":"2026-03-16","a":"open_restricted","b":2,"c":{},"p":[0.15,0.6],"x":{"or_gpqa_diamond":0.7528056666666667,"or_tau2_airline":0.41142871428571426}},{"s":"gpt-oss-20b","n":"gpt-oss-20b","o":"OpenAI","iq":95.05,"d":95,"lo":89,"hi":101,"t":"insufficient","r":"2025-08-05","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.6527777777777778,"gpqa_diamond":0.6079545454545454,"or_gpqa_diamond":0.6311448,"or_tau2_airline":0.4672696511627907}},{"s":"glm-4-7-flash","n":"glm-4.7-flash","o":"—","iq":94.29,"d":94,"lo":88,"hi":100,"t":"insufficient","r":"","a":"unknown","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.5833333333333334,"gpqa_diamond":0.6054292929292929,"or_gpqa_diamond":0.49197393750000007,"or_tau2_airline":0.6833333333333333}},{"s":"qwen3-30b-a3b","n":"Qwen3-30B-A3B","o":"Alibaba","iq":93.65,"d":94,"lo":88,"hi":100,"t":"insufficient","r":"2025-04-28","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.6277777777777778,"gpqa_diamond":0.6167929292929293,"or_gpqa_diamond":0.604377,"or_tau2_airline":0.423333}},{"s":"cohere-command-a","n":"Cohere Command A","o":"Cohere","iq":93.49,"d":93,"lo":75,"hi":112,"t":"insufficient","r":"2025-03-13","a":"open_noncommercial","b":1,"c":{},"p":null,"x":{"bfcl_overall":0.46490000000000004}},{"s":"deepseek-r1-distill-qwen-32b","n":"DeepSeek-R1-Distill-Qwen-32B","o":"DeepSeek","iq":93.24,"d":93,"lo":87,"hi":100,"t":"insufficient","r":"2025-01-20","a":"open_restricted","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.5555555555555556,"gpqa_diamond":0.6414141414141414}},{"s":"qwen3-14b","n":"Qwen3-14B","o":"Alibaba","iq":93.08,"d":93,"lo":87,"hi":99,"t":"insufficient","r":"2025-04-29","a":"open_restricted","b":4,"c":{"agentic":86},"p":null,"x":{"otis_mock_aime":0.6638888888888889,"gpqa_diamond":0.6376262626262627,"or_gpqa_diamond":0.5331086666666667,"bfcl_overall":0.4103,"or_tau2_airline":0.413333}},{"s":"deepseek-r1-distill-llama-70b","n":"DeepSeek-R1-Distill-Llama-70B","o":"DeepSeek","iq":92.2,"d":92,"lo":88,"hi":97,"t":"insufficient","r":"2025-01-20","a":"open_restricted","b":3,"c":{"math":94},"p":null,"x":{"math_level_5":0.8989803625377644,"otis_mock_aime":0.5138888888888888,"gpqa_diamond":0.5574494949494949}},{"s":"qwq-32b","n":"QwQ-32B","o":"Alibaba","iq":91.67,"d":92,"lo":86,"hi":98,"t":"insufficient","r":"2025-03-05","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.5916666666666667,"aider_polyglot":0.209,"gpqa_diamond":0.6534090909090909}},{"s":"o1-mini","n":"o1-mini","o":"OpenAI","iq":91.6,"d":92,"lo":87,"hi":96,"t":"insufficient","r":"2024-09-12","a":"api","b":4,"c":{"math":93},"p":null,"x":{"math_level_5":0.8918051359516617,"otis_mock_aime":0.46944444444444444,"aider_polyglot":0.32899999999999996,"gpqa_diamond":0.6237373737373737}},{"s":"qwen3-30b-a3b-instruct-jul-2025","n":"Qwen3-30B-A3B-Instruct (Jul 2025)","o":"Alibaba","iq":91.5,"d":91,"lo":86,"hi":97,"t":"insufficient","r":"2025-07-29","a":"open_restricted","b":4,"c":{"agentic":84},"p":null,"x":{"otis_mock_aime":0.6222222222222222,"gpqa_diamond":0.5561868686868687,"or_gpqa_diamond":0.6419754999999999,"bfcl_overall":0.4139,"or_tau2_airline":0.3695237142857143}},{"s":"qwen3-8b","n":"Qwen3-8B","o":"Alibaba","iq":90.55,"d":91,"lo":84,"hi":97,"t":"insufficient","r":"2025-04-28","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.5611111111111111,"gpqa_diamond":0.5675505050505051,"bfcl_overall":0.4257}},{"s":"deepseek-r1-0528-qwen3-8b","n":"deepseek-r1-0528-qwen3-8b","o":"—","iq":90.48,"d":90,"lo":83,"hi":98,"t":"insufficient","r":"2025-05-29","a":"unknown","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.4388888888888889,"gpqa_diamond":0.0928030303030303}},{"s":"qwq-plus","n":"QWQ-Plus","o":"Alibaba","iq":90.31,"d":90,"lo":79,"hi":102,"t":"insufficient","r":"2025-04-08","a":"api","b":1,"c":{},"p":[0.8,2.4],"x":{"gpqa_diamond":0.6540404040404041}},{"s":"deepseek-r1-distill-qwen-14b","n":"DeepSeek-R1-Distill-Qwen-14B","o":"DeepSeek","iq":88.86,"d":89,"lo":84,"hi":93,"t":"insufficient","r":"2025-01-20","a":"open_restricted","b":3,"c":{"math":92},"p":null,"x":{"math_level_5":0.8712235649546828,"otis_mock_aime":0.5055555555555555,"gpqa_diamond":0.44696969696969696}},{"s":"gemini-2-0-pro","n":"Gemini 2.0 Pro","o":"Google DeepMind","iq":88.8,"d":89,"lo":83,"hi":94,"t":"insufficient","r":"2025-02-05","a":"hosted","b":3,"c":{},"p":null,"x":{"math_level_5":0.8345921450151057,"aider_polyglot":0.35600000000000004,"gpqa_diamond":0.6565656565656566}},{"s":"gemini-2-0-flash-thinking-jan-2025","n":"Gemini 2.0 Flash Thinking (Jan 2025)","o":"Google DeepMind","iq":88.63,"d":89,"lo":83,"hi":95,"t":"insufficient","r":"2025-01-21","a":"api","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.5777777777777777,"aider_polyglot":0.182,"gpqa_diamond":0.5707070707070707}},{"s":"gpt-4-5","n":"GPT-4.5","o":"OpenAI","iq":87.18,"d":87,"lo":83,"hi":92,"t":"insufficient","r":"2025-02-27","a":"api","b":3,"c":{"math":86},"p":null,"x":{"math_level_5":0.7862537764350453,"otis_mock_aime":0.37777777777777777,"gpqa_diamond":0.6868686868686869}},{"s":"gemini-2-0-flash-feb-2025","n":"Gemini 2.0 Flash (Feb 2025)","o":"Google DeepMind","iq":86.73,"d":87,"lo":82,"hi":91,"t":"insufficient","r":"2025-02-05","a":"api","b":3,"c":{"math":86},"p":null,"x":{"math_level_5":0.8216578549848943,"otis_mock_aime":0.3111111111111111,"gpqa_diamond":0.6414141414141414}},{"s":"mistral-medium-3","n":"Mistral Medium 3","o":"Mistral AI","iq":85.58,"d":86,"lo":81,"hi":90,"t":"insufficient","r":"2025-05-07","a":"api","b":4,"c":{"math":86},"p":null,"x":{"math_level_5":0.8162764350453172,"otis_mock_aime":0.32222222222222224,"gpqa_diamond":0.5953282828282829,"bfcl_overall":0.37689999999999996}},{"s":"qwen3-4b-instruct-2507","n":"qwen3-4b-instruct-2507","o":"—","iq":85.45,"d":85,"lo":79,"hi":92,"t":"insufficient","r":"2025-08-06","a":"unknown","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.5222222222222223,"gpqa_diamond":0.4583333333333333,"bfcl_overall":0.3568}},{"s":"qwen3-235b-a22b","n":"Qwen3-235B-A22B","o":"Alibaba","iq":85.42,"d":85,"lo":80,"hi":91,"t":"insufficient","r":"2025-04-28","a":"open_restricted","b":3,"c":{},"p":null,"x":{"math_level_5":0.6885699899295065,"aider_polyglot":0.596,"gpqa_diamond":0.7070707070707071}},{"s":"deepseek-v3-mar-2025","n":"DeepSeek-V3 (Mar 2025)","o":"DeepSeek","iq":85.38,"d":85,"lo":81,"hi":90,"t":"insufficient","r":"2025-03-24","a":"open_restricted","b":4,"c":{"math":85},"p":null,"x":{"math_level_5":0.75547583081571,"otis_mock_aime":0.37777777777777777,"gpqa_diamond":0.6761363636363636,"or_gpqa_diamond":0.646465,"or_tau2_airline":0.4337431393442623}},{"s":"qwen3-coder-480b-a35b","n":"Qwen3-Coder-480B-A35B","o":"Alibaba","iq":84.59,"d":85,"lo":72,"hi":98,"t":"insufficient","r":"2025-07-31","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.6035354999999999,"or_tau2_airline":0.43333342857142854}},{"s":"o1-preview","n":"o1-preview","o":"OpenAI","iq":84.17,"d":84,"lo":80,"hi":89,"t":"insufficient","r":"2024-09-12","a":"api","b":3,"c":{"math":86},"p":null,"x":{"math_level_5":0.8164652567975831,"otis_mock_aime":0.3111111111111111,"gpqa_diamond":0.5031565656565656}},{"s":"magistral-small-1-0","n":"Magistral Small 1.0","o":"Mistral AI","iq":82.79,"d":83,"lo":76,"hi":89,"t":"insufficient","r":"2025-06-10","a":"open_restricted","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.3,"gpqa_diamond":0.5606060606060606}},{"s":"mistral-small-3-2","n":"Mistral Small 3.2","o":"Mistral AI","iq":80.45,"d":80,"lo":74,"hi":87,"t":"insufficient","r":"2025-06-20","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.30277777777777776,"gpqa_diamond":0.49053030303030304,"bfcl_overall":0.3715}},{"s":"gemini-1-5-pro-sept-2024","n":"Gemini 1.5 Pro (Sept 2024)","o":"Google DeepMind","iq":80.11,"d":80,"lo":75,"hi":85,"t":"insufficient","r":"2024-09-24","a":"api","b":3,"c":{"math":80},"p":null,"x":{"math_level_5":0.7039274924471299,"otis_mock_aime":0.23055555555555557,"gpqa_diamond":0.5722853535353535}},{"s":"gemini-2-0-flash-dec-2024","n":"Gemini 2.0 Flash (Dec 2024)","o":"Google DeepMind","iq":79.52,"d":80,"lo":64,"hi":95,"t":"insufficient","r":"2024-12-11","a":"api","b":1,"c":{},"p":null,"x":{"aider_polyglot":0.222}},{"s":"magistral-small-1-2","n":"Magistral Small 1.2","o":"Mistral AI","iq":79.08,"d":79,"lo":72,"hi":86,"t":"insufficient","r":"2025-09-18","a":"open_restricted","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.28055555555555556,"gpqa_diamond":0.476010101010101}},{"s":"qwen2-5-max","n":"Qwen2.5-Max","o":"Alibaba","iq":77.7,"d":78,"lo":73,"hi":82,"t":"insufficient","r":"2025-01-25","a":"api","b":4,"c":{"math":77},"p":null,"x":{"math_level_5":0.6718277945619335,"otis_mock_aime":0.16111111111111112,"aider_polyglot":0.218,"gpqa_diamond":0.5612373737373737}},{"s":"deepseek-v3","n":"DeepSeek-V3","o":"DeepSeek","iq":77.43,"d":77,"lo":73,"hi":82,"t":"insufficient","r":"2024-12-26","a":"open_restricted","b":4,"c":{"math":76},"p":null,"x":{"math_level_5":0.6485083081570997,"otis_mock_aime":0.15833333333333333,"gpqa_diamond":0.5653409090909091,"or_gpqa_diamond":0.661616,"or_tau2_airline":0.4053599698492462}},{"s":"glm-4-7-flash-none","n":"glm-4.7-flash_none","o":"—","iq":76.99,"d":77,"lo":70,"hi":84,"t":"insufficient","r":"","a":"unknown","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.25,"gpqa_diamond":0.4513888888888889}},{"s":"qwen3-4b","n":"Qwen3-4B","o":"Alibaba","iq":76.73,"d":77,"lo":65,"hi":89,"t":"insufficient","r":"2025-04-29","a":"open_restricted","b":1,"c":{},"p":null,"x":{"gpqa_diamond":0.5233585858585859}},{"s":"phi-4","n":"Phi-4","o":"Microsoft Research","iq":75.98,"d":76,"lo":71,"hi":81,"t":"insufficient","r":"2024-12-12","a":"open_restricted","b":4,"c":{"math":76},"p":null,"x":{"math_level_5":0.6493580060422961,"otis_mock_aime":0.1375,"gpqa_diamond":0.5606060606060606,"bfcl_overall":0.2879}},{"s":"qwen-plus-jan-2025","n":"Qwen Plus (Jan 2025)","o":"Alibaba","iq":75.95,"d":76,"lo":71,"hi":81,"t":"insufficient","r":"2025-01-25","a":"api","b":3,"c":{"math":77},"p":[0.4,1.2],"x":{"math_level_5":0.6527567975830816,"otis_mock_aime":0.17777777777777778,"gpqa_diamond":0.4810606060606061}},{"s":"claude-3-5-sonnet-october-2024","n":"Claude 3.5 Sonnet (October 2024)","o":"Anthropic","iq":75.67,"d":76,"lo":71,"hi":80,"t":"insufficient","r":"2024-10-22","a":"api","b":4,"c":{"math":72},"p":null,"x":{"math_level_5":0.5694864048338368,"otis_mock_aime":0.08472222222222223,"aider_polyglot":0.516,"gpqa_diamond":0.553030303030303}},{"s":"grok-2-dec-2024","n":"Grok-2 (Dec 2024)","o":"xAI","iq":75.25,"d":75,"lo":70,"hi":80,"t":"insufficient","r":"2024-12-12","a":"api","b":3,"c":{"math":75},"p":null,"x":{"math_level_5":0.6351963746223565,"otis_mock_aime":0.11527777777777778,"gpqa_diamond":0.5378787878787878}},{"s":"qwen2-5-coder-32b-instruct","n":"Qwen2.5-Coder-32B-Instruct","o":"Alibaba","iq":74.57,"d":75,"lo":59,"hi":90,"t":"insufficient","r":"2024-11-21","a":"open_restricted","b":1,"c":{},"p":null,"x":{"aider_polyglot":0.16399999999999998}},{"s":"gemini-1-5-flash-sep-2024","n":"Gemini 1.5 Flash (Sep 2024)","o":"Google DeepMind","iq":74.5,"d":74,"lo":70,"hi":79,"t":"insufficient","r":"2024-09-24","a":"api","b":3,"c":{"math":75},"p":null,"x":{"math_level_5":0.6186744712990937,"otis_mock_aime":0.1625,"gpqa_diamond":0.47316919191919193}},{"s":"llama-4-scout","n":"Llama 4 Scout","o":"Meta AI","iq":73.31,"d":73,"lo":68,"hi":78,"t":"insufficient","r":"2025-04-05","a":"open_restricted","b":4,"c":{"math":73},"p":null,"x":{"math_level_5":0.6227341389728097,"otis_mock_aime":0.07777777777777778,"gpqa_diamond":0.5183080808080808,"bfcl_overall":0.2813}},{"s":"gemma-3-12b","n":"Gemma 3 12B","o":"Google DeepMind","iq":72.63,"d":73,"lo":66,"hi":79,"t":"insufficient","r":"2025-03-12","a":"open_restricted","b":4,"c":{"agentic":75},"p":null,"x":{"otis_mock_aime":0.16666666666666666,"gpqa_diamond":0.39457070707070707,"or_gpqa_diamond":0.37878799999999996,"bfcl_overall":0.3043,"or_tau2_airline":0.48}},{"s":"deepseek-r1-distill-qwen-1-5b","n":"DeepSeek-R1-Distill-Qwen-1.5B","o":"DeepSeek","iq":72.61,"d":73,"lo":65,"hi":80,"t":"insufficient","r":"2025-01-20","a":"open_restricted","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.21388888888888888,"gpqa_diamond":0.33585858585858586}},{"s":"qwen2-5-72b","n":"Qwen2.5-72B","o":"Alibaba","iq":72.3,"d":72,"lo":68,"hi":77,"t":"insufficient","r":"2024-09-19","a":"open_restricted","b":4,"c":{"math":74},"p":null,"x":{"math_level_5":0.631703172205438,"otis_mock_aime":0.08055555555555556,"gpqa_diamond":0.4914772727272727,"or_gpqa_diamond":0.461279,"or_tau2_airline":0.25}},{"s":"mistral-large-2-nov-2024","n":"Mistral Large 2 (Nov 2024)","o":"Mistral AI","iq":71.08,"d":71,"lo":66,"hi":76,"t":"insufficient","r":"2024-11-18","a":"open_noncommercial","b":4,"c":{"math":69},"p":null,"x":{"math_level_5":0.5028323262839879,"otis_mock_aime":0.07777777777777778,"gpqa_diamond":0.5132575757575758,"bfcl_overall":0.3837}},{"s":"yi-lightning","n":"Yi-Lightning","o":"01.AI","iq":70.88,"d":71,"lo":55,"hi":87,"t":"insufficient","r":"2024-12-02","a":"api","b":1,"c":{},"p":null,"x":{"aider_polyglot":0.129}},{"s":"claude-3-5-sonnet","n":"Claude 3.5 Sonnet","o":"Anthropic","iq":70.85,"d":71,"lo":66,"hi":76,"t":"insufficient","r":"2024-06-20","a":"api","b":3,"c":{"math":69},"p":null,"x":{"math_level_5":0.5168051359516617,"otis_mock_aime":0.06527777777777778,"gpqa_diamond":0.5404040404040404}},{"s":"qwen2-5-32b","n":"Qwen2.5-32B","o":"Alibaba","iq":70.59,"d":71,"lo":66,"hi":76,"t":"insufficient","r":"2024-09-17","a":"open_restricted","b":3,"c":{"math":71},"p":null,"x":{"math_level_5":0.5607061933534743,"otis_mock_aime":0.07361111111111111,"gpqa_diamond":0.46085858585858586}},{"s":"gpt-4o-may-2024","n":"GPT-4o (May 2024)","o":"OpenAI","iq":70.33,"d":70,"lo":66,"hi":75,"t":"insufficient","r":"2024-05-13","a":"api","b":4,"c":{"math":69},"p":[5.0,15.0],"x":{"math_level_5":0.5104796072507553,"otis_mock_aime":0.0625,"gpqa_diamond":0.4889520202020202,"or_gpqa_diamond":0.542088,"or_tau2_airline":0.44}},{"s":"llama-3-1-405b","n":"Llama 3.1-405B","o":"Meta AI","iq":70.33,"d":70,"lo":65,"hi":75,"t":"insufficient","r":"2024-07-23","a":"open_restricted","b":3,"c":{"math":69},"p":null,"x":{"math_level_5":0.49773413897280966,"otis_mock_aime":0.09722222222222222,"gpqa_diamond":0.5091540404040404}},{"s":"qwen-turbo","n":"Qwen-Turbo","o":"Alibaba","iq":69.46,"d":69,"lo":64,"hi":75,"t":"insufficient","r":"2024-11-01","a":"api","b":3,"c":{"math":70},"p":[0.05,0.2],"x":{"math_level_5":0.5623111782477341,"otis_mock_aime":0.06111111111111111,"gpqa_diamond":0.41792929292929293}},{"s":"gpt-4-turbo-apr-2024","n":"GPT-4 Turbo (Apr 2024)","o":"OpenAI","iq":68.39,"d":68,"lo":64,"hi":73,"t":"insufficient","r":"2024-04-09","a":"api","b":4,"c":{"math":68},"p":[10.0,30.0],"x":{"frontiermath_t13":0.007017543859649123,"math_level_5":0.46733383685800606,"otis_mock_aime":0.06666666666666667,"gpqa_diamond":0.4659090909090909}},{"s":"mistral-large-2-jul-2024","n":"Mistral Large 2 (Jul 2024)","o":"Mistral AI","iq":68.18,"d":68,"lo":63,"hi":73,"t":"insufficient","r":"2024-07-24","a":"open_noncommercial","b":3,"c":{"math":67},"p":null,"x":{"math_level_5":0.4481684290030212,"otis_mock_aime":0.08472222222222223,"gpqa_diamond":0.49021464646464646}},{"s":"mistral-small-3-1","n":"Mistral Small 3.1","o":"Mistral AI","iq":67.75,"d":68,"lo":63,"hi":73,"t":"insufficient","r":"2025-03-17","a":"open_restricted","b":3,"c":{"math":67},"p":null,"x":{"math_level_5":0.4677114803625378,"otis_mock_aime":0.058333333333333334,"gpqa_diamond":0.47474747474747475}},{"s":"openhands-lm-32b-v0-1","n":"openhands-lm-32b-v0.1","o":"—","iq":67.42,"d":67,"lo":52,"hi":83,"t":"insufficient","r":"2024-03-26","a":"unknown","b":1,"c":{},"p":null,"x":{"aider_polyglot":0.102}},{"s":"mistral-small-3","n":"Mistral Small 3","o":"Mistral AI","iq":67.32,"d":67,"lo":62,"hi":72,"t":"insufficient","r":"2025-01-25","a":"open_restricted","b":3,"c":{"math":67},"p":null,"x":{"math_level_5":0.4481684290030212,"otis_mock_aime":0.06666666666666667,"gpqa_diamond":0.47285353535353536}},{"s":"claude-3-5-haiku","n":"Claude 3.5 Haiku","o":"Anthropic","iq":67.31,"d":67,"lo":62,"hi":72,"t":"insufficient","r":"2024-10-22","a":"api","b":4,"c":{"math":66},"p":null,"x":{"math_level_5":0.46355740181268884,"otis_mock_aime":0.043055555555555555,"aider_polyglot":0.28,"gpqa_diamond":0.3813131313131313}},{"s":"gemini-1-5-pro-may-2024","n":"Gemini 1.5 Pro (May 2024)","o":"Google DeepMind","iq":65.78,"d":66,"lo":61,"hi":71,"t":"insufficient","r":"2024-05-14","a":"api","b":3,"c":{"math":65},"p":null,"x":{"math_level_5":0.4074773413897281,"otis_mock_aime":0.06805555555555555,"gpqa_diamond":0.4586489898989899}},{"s":"claude-3-opus","n":"Claude 3 Opus","o":"Anthropic","iq":65.4,"d":65,"lo":60,"hi":70,"t":"insufficient","r":"2024-02-29","a":"api","b":5,"c":{"math":63,"knowledge":71},"p":null,"x":{"chess_puzzles":0.03,"math_level_5":0.37481117824773413,"otis_mock_aime":0.04722222222222222,"gpqa_diamond":0.4715909090909091,"simpleqa_verified":0.126}},{"s":"qwen3-1-7b","n":"Qwen3-1.7B","o":"Alibaba","iq":64.62,"d":65,"lo":57,"hi":73,"t":"insufficient","r":"2025-04-29","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.08055555555555556,"gpqa_diamond":0.380050505050505,"bfcl_overall":0.2841}},{"s":"qwen3-0-6b","n":"Qwen3-0.6B","o":"Alibaba","iq":64.19,"d":64,"lo":45,"hi":83,"t":"insufficient","r":"2025-04-29","a":"open_restricted","b":1,"c":{},"p":null,"x":{"bfcl_overall":0.23929999999999998}},{"s":"qwen2-72b","n":"Qwen2-72B","o":"Alibaba","iq":63.7,"d":64,"lo":58,"hi":69,"t":"insufficient","r":"2024-06-07","a":"open_restricted","b":2,"c":{},"p":null,"x":{"math_level_5":0.39067220543806647,"gpqa_diamond":0.4078282828282828}},{"s":"llama-3-1-70b","n":"Llama 3.1-70B","o":"Meta AI","iq":63.16,"d":63,"lo":58,"hi":68,"t":"insufficient","r":"2024-07-23","a":"open_restricted","b":3,"c":{"math":62},"p":null,"x":{"math_level_5":0.36678625377643503,"otis_mock_aime":0.03611111111111111,"gpqa_diamond":0.44191919191919193}},{"s":"gemma-3-4b","n":"Gemma 3 4B","o":"Google DeepMind","iq":62.93,"d":63,"lo":53,"hi":73,"t":"insufficient","r":"2025-03-12","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.075,"gpqa_diamond":0.23232323232323232,"or_gpqa_diamond":0.271044,"bfcl_overall":0.1962}},{"s":"llama-3-2-3b","n":"Llama 3.2 3B","o":"Meta AI","iq":60.94,"d":61,"lo":42,"hi":80,"t":"insufficient","r":"2024-09-24","a":"open_restricted","b":2,"c":{},"p":null,"x":{"or_gpqa_diamond":0.17340049999999999,"bfcl_overall":0.2195}},{"s":"wizardlm-2-8x22b","n":"WizardLM-2 8x22B","o":"Microsoft","iq":58.71,"d":59,"lo":53,"hi":64,"t":"insufficient","r":"2024-04-15","a":"open_restricted","b":2,"c":{},"p":null,"x":{"math_level_5":0.25736404833836857,"gpqa_diamond":0.43434343434343436}},{"s":"gemini-1-5-flash-may-2024","n":"Gemini 1.5 Flash (May 2024)","o":"Google DeepMind","iq":57.83,"d":58,"lo":53,"hi":63,"t":"insufficient","r":"2024-05-23","a":"api","b":3,"c":{"math":57},"p":null,"x":{"math_level_5":0.2512273413897281,"otis_mock_aime":0.03888888888888889,"gpqa_diamond":0.40372474747474746}},{"s":"gemma-2-27b","n":"Gemma 2 27B","o":"Google DeepMind","iq":57.15,"d":57,"lo":52,"hi":63,"t":"insufficient","r":"2024-06-24","a":"open_restricted","b":3,"c":{"math":57},"p":null,"x":{"math_level_5":0.2788897280966767,"otis_mock_aime":0.013888888888888888,"gpqa_diamond":0.3648989898989899}},{"s":"gpt-4-jun-2023","n":"GPT-4 (Jun 2023)","o":"OpenAI","iq":56.99,"d":57,"lo":51,"hi":63,"t":"insufficient","r":"2023-06-13","a":"api","b":4,"c":{"math":55},"p":[30.0,60.0],"x":{"mystery_game_puzzles":0.12,"math_level_5":0.22970166163141995,"otis_mock_aime":0.011111111111111112,"gpqa_diamond":0.30650252525252525}},{"s":"gemini-1-5-flash-8b","n":"Gemini 1.5 Flash 8B","o":"Google DeepMind","iq":56.97,"d":57,"lo":47,"hi":67,"t":"insufficient","r":"2024-10-03","a":"api","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.04583333333333333,"gpqa_diamond":0.32954545454545453}},{"s":"llama-3-70b","n":"Llama 3-70B","o":"Meta AI","iq":56.92,"d":57,"lo":52,"hi":62,"t":"insufficient","r":"2024-04-18","a":"open_restricted","b":3,"c":{"math":56},"p":null,"x":{"math_level_5":0.225547583081571,"otis_mock_aime":0.043055555555555555,"gpqa_diamond":0.40561868686868685}},{"s":"mistral-large","n":"Mistral Large","o":"Mistral AI","iq":56.36,"d":56,"lo":51,"hi":62,"t":"insufficient","r":"2024-02-26","a":"api","b":3,"c":{"math":56},"p":null,"x":{"math_level_5":0.24461858006042297,"otis_mock_aime":0.019444444444444445,"gpqa_diamond":0.38762626262626265}},{"s":"granite-4-0-1b","n":"granite-4.0-1b","o":"—","iq":55.46,"d":55,"lo":37,"hi":74,"t":"insufficient","r":"2025-10-28","a":"unknown","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.008333333333333333,"gpqa_diamond":0.2398989898989899}},{"s":"hermes-2-theta-llama-3-70b","n":"Hermes 2 Theta Llama-3 70B","o":"Nous Research","iq":55.35,"d":55,"lo":50,"hi":61,"t":"insufficient","r":"2024-06-20","a":"open_restricted","b":3,"c":{"math":55},"p":null,"x":{"math_level_5":0.22686933534743203,"otis_mock_aime":0.025,"gpqa_diamond":0.3746843434343434}},{"s":"mixtral-8x22b","n":"Mixtral 8x22B","o":"Mistral AI","iq":55.13,"d":55,"lo":49,"hi":61,"t":"insufficient","r":"2024-04-17","a":"open_restricted","b":2,"c":{},"p":null,"x":{"math_level_5":0.24244712990936557,"gpqa_diamond":0.34059343434343436}},{"s":"llama-3-1-8b","n":"Llama 3.1-8B","o":"Meta AI","iq":54.63,"d":55,"lo":49,"hi":60,"t":"insufficient","r":"2024-07-23","a":"open_restricted","b":3,"c":{"math":55},"p":null,"x":{"math_level_5":0.22875755287009064,"otis_mock_aime":0.016666666666666666,"gpqa_diamond":0.26957070707070707,"or_gpqa_diamond":0.26941151269035535}},{"s":"mistral-7b-v0-3","n":"Mistral 7B v0.3","o":"Mistral AI","iq":54.34,"d":54,"lo":34,"hi":75,"t":"insufficient","r":"2024-05-27","a":"open_restricted","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.002777777777777778,"gpqa_diamond":0.1518308080808081}},{"s":"granite-4-0-micro","n":"granite-4.0-micro","o":"—","iq":54.11,"d":54,"lo":41,"hi":67,"t":"insufficient","r":"2025-10-02","a":"unknown","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.027777777777777776,"gpqa_diamond":0.2828282828282828}},{"s":"claude-3-sonnet","n":"Claude 3 Sonnet","o":"Anthropic","iq":53.92,"d":54,"lo":49,"hi":59,"t":"insufficient","r":"2024-02-29","a":"api","b":3,"c":{"math":52},"p":null,"x":{"math_level_5":0.18174093655589124,"otis_mock_aime":0.025,"gpqa_diamond":0.4059343434343434}},{"s":"gemma-2-9b","n":"Gemma 2 9B","o":"Google DeepMind","iq":52.91,"d":53,"lo":47,"hi":59,"t":"insufficient","r":"2024-06-24","a":"open_restricted","b":3,"c":{"math":53},"p":null,"x":{"math_level_5":0.2100641993957704,"otis_mock_aime":0.005555555555555556,"gpqa_diamond":0.2746212121212121}},{"s":"granite-4-0-350m","n":"granite-4.0-350m","o":"—","iq":52.5,"d":53,"lo":37,"hi":68,"t":"insufficient","r":"2025-10-28","a":"unknown","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.002777777777777778,"gpqa_diamond":0.11237373737373738,"bfcl_overall":0.1898}},{"s":"gpt-4-mar-2023","n":"GPT-4 (Mar 2023)","o":"OpenAI","iq":52.45,"d":52,"lo":40,"hi":65,"t":"insufficient","r":"2023-03-14","a":"api","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.005555555555555556,"gpqa_diamond":0.3573232323232323}},{"s":"claude-2-1","n":"Claude 2.1","o":"Anthropic","iq":51.81,"d":52,"lo":40,"hi":64,"t":"insufficient","r":"2023-11-21","a":"api","b":2,"c":{},"p":null,"x":{"otis_mock_aime":0.019444444444444445,"gpqa_diamond":0.32954545454545453}},{"s":"eurus-2-7b-prime","n":"Eurus-2-7B-PRIME","o":"Tsinghua University","iq":51.11,"d":51,"lo":35,"hi":67,"t":"insufficient","r":"2024-12-31","a":"open_restricted","b":1,"c":{},"p":null,"x":{"gpqa_diamond":0.3390151515151515}},{"s":"phi-3-medium-14b","n":"phi-3-medium 14B","o":"Microsoft","iq":50.75,"d":51,"lo":45,"hi":57,"t":"insufficient","r":"2024-04-23","a":"open_restricted","b":2,"c":{},"p":null,"x":{"math_level_5":0.17560422960725075,"gpqa_diamond":0.2758838383838384}},{"s":"qwen2-5-7b","n":"Qwen2.5-7B","o":"Alibaba","iq":50.69,"d":51,"lo":41,"hi":60,"t":"insufficient","r":"2024-09-19","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.025,"gpqa_diamond":0.3547979797979798,"or_gpqa_diamond":0.3417510000000001,"or_tau2_airline":0.166667}},{"s":"claude-3-haiku","n":"Claude 3 Haiku","o":"Anthropic","iq":50.18,"d":50,"lo":45,"hi":56,"t":"insufficient","r":"2024-03-07","a":"api","b":3,"c":{"math":49},"p":null,"x":{"math_level_5":0.1487915407854985,"otis_mock_aime":0.018055555555555554,"gpqa_diamond":0.3630050505050505}},{"s":"gpt-3-5-turbo-nov-2023","n":"GPT-3.5 Turbo (Nov 2023)","o":"OpenAI","iq":49.27,"d":49,"lo":43,"hi":55,"t":"insufficient","r":"2023-11-06","a":"api","b":2,"c":{},"p":[1.0,2.0],"x":{"math_level_5":0.15889350453172205,"gpqa_diamond":0.2803030303030303}},{"s":"ministral-3b","n":"Ministral 3B","o":"Mistral AI","iq":48.79,"d":49,"lo":43,"hi":55,"t":"insufficient","r":"2024-10-16","a":"api","b":2,"c":{},"p":null,"x":{"math_level_5":0.14444864048338368,"gpqa_diamond":0.25252525252525254}},{"s":"claude-2","n":"Claude 2","o":"Anthropic","iq":47.67,"d":48,"lo":42,"hi":53,"t":"insufficient","r":"2023-07-11","a":"api","b":3,"c":{"math":47},"p":null,"x":{"math_level_5":0.1172583081570997,"otis_mock_aime":0.025,"gpqa_diamond":0.3465909090909091}},{"s":"gpt-3-5-turbo-jan-2024","n":"GPT-3.5 Turbo (Jan 2024)","o":"OpenAI","iq":47.25,"d":47,"lo":42,"hi":53,"t":"insufficient","r":"2024-01-25","a":"api","b":5,"c":{"math":47},"p":[0.5,1.5],"x":{"mystery_game_puzzles":0.03,"frontiermath_t13":0.0,"math_level_5":0.1163141993957704,"otis_mock_aime":0.022222222222222223,"gpqa_diamond":0.27178030303030304}},{"s":"ministral-8b","n":"Ministral 8B","o":"Mistral AI","iq":47.12,"d":47,"lo":41,"hi":53,"t":"insufficient","r":"2024-10-16","a":"open_noncommercial","b":3,"c":{},"p":null,"x":{"math_level_5":0.14935800604229607,"gpqa_diamond":0.27146464646464646,"bfcl_overall":0.111}},{"s":"mistral-nemo","n":"Mistral NeMo","o":"Mistral AI","iq":46.81,"d":47,"lo":41,"hi":53,"t":"insufficient","r":"2024-07-18","a":"open_restricted","b":3,"c":{},"p":null,"x":{"math_level_5":0.1082892749244713,"gpqa_diamond":0.2989267676767677,"bfcl_overall":0.2763}},{"s":"gemini-1-0-pro","n":"Gemini 1.0 Pro","o":"Google DeepMind","iq":46.14,"d":46,"lo":40,"hi":52,"t":"insufficient","r":"2023-12-13","a":"api","b":3,"c":{"math":45},"p":null,"x":{"math_level_5":0.11244335347432025,"otis_mock_aime":0.011111111111111112,"gpqa_diamond":0.33964646464646464}},{"s":"dbrx","n":"DBRX","o":"Databricks","iq":45.77,"d":46,"lo":40,"hi":52,"t":"insufficient","r":"2024-03-27","a":"open_restricted","b":2,"c":{},"p":null,"x":{"math_level_5":0.11650302114803625,"gpqa_diamond":0.32891414141414144}},{"s":"mixtral-8x7b","n":"Mixtral 8x7B","o":"Mistral AI","iq":43.33,"d":43,"lo":37,"hi":49,"t":"insufficient","r":"2023-12-11","a":"open_restricted","b":2,"c":{},"p":null,"x":{"math_level_5":0.09950906344410876,"gpqa_diamond":0.3058712121212121}},{"s":"llama-3-2-1b","n":"Llama 3.2 1B","o":"Meta AI","iq":42.1,"d":42,"lo":27,"hi":58,"t":"insufficient","r":"2024-09-24","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.005555555555555556,"gpqa_diamond":0.23926767676767677,"bfcl_overall":0.1082}},{"s":"llama-3-8b","n":"Llama 3-8B","o":"Meta AI","iq":39.75,"d":40,"lo":34,"hi":46,"t":"insufficient","r":"2024-04-18","a":"open_restricted","b":3,"c":{"math":39},"p":null,"x":{"math_level_5":0.0612726586102719,"otis_mock_aime":0.019444444444444445,"gpqa_diamond":0.26073232323232326}},{"s":"gemma-3-1b","n":"Gemma 3 1B","o":"Google DeepMind","iq":39.7,"d":40,"lo":25,"hi":55,"t":"insufficient","r":"2025-03-12","a":"open_restricted","b":3,"c":{},"p":null,"x":{"otis_mock_aime":0.011111111111111112,"gpqa_diamond":0.1994949494949495,"bfcl_overall":0.0717}}],"benchmarks":{"chess_puzzles":"Chess Puzzles","furniture_assembly":"Furniture Assembly","mystery_game_puzzles":"Mystery Game Puzzles","frontiermath_t4":"FrontierMath Tier 4","frontiermath_t13":"FrontierMath Tiers 1–3","math_level_5":"MATH Level 5","otis_mock_aime":"OTIS Mock AIME 2024–2025","aider_polyglot":"Aider Polyglot","swe_bench_verified":"SWE-bench Verified (Epoch AI run)","gpqa_diamond":"GPQA Diamond","or_gpqa_diamond":"GPQA Diamond (OpenRouter run)","simpleqa_verified":"SimpleQA Verified","bfcl_overall":"Berkeley Function Calling Leaderboard","or_tau2_airline":"τ²-bench Airline (OpenRouter run)"}}