{"schema_version":"mostlyright-public-table-preview.v1","dataset":{"id":"f644292a-2f98-415c-b28a-560181d74f1c","slug":"llm-benchmark-scores-by-model-since-2019","title":"LLM benchmark scores by model, since 2019","publisher_handle":"mostlyrightmd","url":"https://mostlyright.md/datasets/llm-benchmark-scores-by-model-since-2019"},"table":{"id":"9687578e-158b-4a35-a894-0152d5fba679","slug":"llm-benchmark-results","title":"llm_benchmark_results","license":null,"url":"https://mostlyright.md/datasets/llm-benchmark-scores-by-model-since-2019/tables?table=llm-benchmark-results"},"version":{"id":"dde2b5b0-4267-5ba8-80d1-91188ea9f96c","label":null,"released_at":"2026-10-23T18:47:14.762Z","content_digest":null},"columns":[{"name":"result_id","type":"string"},{"name":"benchmark","type":"string"},{"name":"benchmark_release_date","type":"date"},{"name":"model","type":"string"},{"name":"model_version","type":"string"},{"name":"organization","type":"string"},{"name":"country","type":"string"},{"name":"model_access","type":"string"},{"name":"model_release_date","type":"date"},{"name":"training_compute_flop","type":"number"},{"name":"score","type":"number"},{"name":"score_unit","type":"string"},{"name":"score_fraction","type":"number"},{"name":"higher_is_better","type":"boolean"},{"name":"stderr","type":"number"},{"name":"result_date","type":"date"},{"name":"reported_by","type":"string"},{"name":"source","type":"string"},{"name":"source_url","type":"string"},{"name":"evaluation_setup","type":"string"},{"name":"notes","type":"string"},{"name":"epoch_file","type":"string"}],"rows":[["262FWwUwrjPpxVN8G8sDZT","Mystery Game Puzzles","2026-07-30","GPT-5","gpt-5-2025-08-07_low","OpenAI","United States of America","API access","2025-08-07","6.6000000000000002e+25","0.16","fraction","0.16",true,"0.03684529491774706","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["298stsbTPpZp7toZsS5cp8","OTIS Mock AIME 2024-2025","2024-12-19","GPT-5 nano","gpt-5-nano-2025-08-07_low","OpenAI","United States of America","API access","2025-08-07",null,"0.46666666666666667","fraction","0.46666666666666667",true,"0.075210143309035485","2026-07-13","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F298stsbTPpZp7toZsS5cp8.eval",null,null,"otis_mock_aime_2024_2025.csv"],["2AbeCjy9w4KJWKhbKjtFTJ","Mystery Game Puzzles","2026-07-30","Claude Opus 4.1","claude-opus-4-1-20250805_24K","Anthropic","United States of America","API access","2025-08-05",null,"0.20999999999999999","fraction","0.20999999999999999",true,"0.040936018074033236","2026-07-25","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["2CdomqtBVz2it7a2Zx2G2t","GPQA diamond","2023-11-20","GPT-5.5","gpt-5.5_low","OpenAI","United States of America","API access","2026-04-23",null,"0.90656565656565657","fraction","0.90656565656565657",true,"0.017532658377721708","2026-05-05","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2CdomqtBVz2it7a2Zx2G2t.eval",null,null,"gpqa_diamond.csv"],["2QAt4ptgGkLtcbVL3hdAvL","FrontierMath-Tiers-1-3-v2-Private","2026-06-12","Claude Haiku 5.5","claude-haiku-5-5_max","Anthropic","United States of America","API access","2026-10-07",null,"0.75087719298245614","fraction","0.75087719298245614",true,"0.025664454102329461","2026-10-07","Epoch AI","Epoch AI",null,null,null,"frontiermath_tiers_1_3_v2.csv"],["2RiSB2ii5kf2Q6fDBv2P3E","MATH level 5","2021-03-05","o3-mini","o3-mini-2025-01-31_medium","OpenAI","United States of America","API access","2025-01-31",null,"0.95166163141993954","fraction","0.95166163141993954",true,"0.0046519178576215781","2025-01-31","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["2UmuBfhBvYbbnTg5BnQqov","FrontierMath-Tier-4-v2-Private","2026-06-12","GPT-5.5 Instant","gpt-5.5-instant","OpenAI","United States of America","API access","2026-05-05",null,"0.024390243902439025","fraction","0.024390243902439025",true,"0.024390243902439022","2026-08-02","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2UmuBfhBvYbbnTg5BnQqov.eval",null,null,"frontiermath_tier_4_v2.csv"],["2WxRbjq5ZWTgiXZPqYUG4R","FrontierMath-Tier-4-v2-Private","2026-06-12","GPT-5 mini","gpt-5-mini-2025-08-07_high","OpenAI","United States of America","API access","2025-08-07",null,"0.12195121951219512","fraction","0.12195121951219512",true,"0.051739520574625435","2026-06-12","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2WxRbjq5ZWTgiXZPqYUG4R.eval",null,null,"frontiermath_tier_4_v2.csv"],["2a2uhidAfksbnAJC8yUrZK","Mystery Game Puzzles","2026-07-30","GPT-5.1","gpt-5.1-2025-11-13_none","OpenAI","United States of America","API access","2025-11-13",null,"0.14999999999999999","fraction","0.14999999999999999",true,"0.035887028128263679","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["2c4rvmf5N7QXTugrFLMZ83","SimpleQA Verified","2025-09-09","Claude Opus 4.7","claude-opus-4-7_xhigh","Anthropic","United States of America","API access","2026-04-16",null,"0.51700000000000002","fraction","0.51700000000000002",true,"0.015810153729833274","2026-08-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2c4rvmf5N7QXTugrFLMZ83.eval",null,null,"simpleqa_verified.csv"],["2e2NePZeU3iB4wvhwCaTci","Mystery Game Puzzles","2026-07-30","GPT-5.4 Nano","gpt-5.4-nano-2026-03-17_high","OpenAI","United States of America","API access","2026-03-17",null,"0.050000000000000003","fraction","0.050000000000000003",true,"0.021904291355759033","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["2eMHpXXR9h7P2oNPDQkTBY","FrontierMath-2025-02-28-Private","2025-02-28","GPT-5 nano","gpt-5-nano-2025-08-07_high","OpenAI","United States of America","API access","2025-08-07",null,"0.082758620689655171","fraction","0.082758620689655171",true,"0.016206883858367691","2025-10-30","Epoch AI","Epoch AI",null,null,null,"frontiermath.csv"],["2ekT2UzaebvmGprKvmeeEa","FrontierMath-2025-02-28-Private","2025-02-28","o1-mini","o1-mini-2024-09-12_high","OpenAI","United States of America","API access","2024-09-12",null,"0.013793103448275862","fraction","0.013793103448275862",true,"0.0068606630934230266","2025-03-06","Epoch AI","Epoch AI",null,null,null,"frontiermath.csv"],["2f8Vn5QBdJnc9i5y9jzXS7","OTIS Mock AIME 2024-2025","2024-12-19","Qwen3.8 Max (0902)","qwen3.8-max-0902_xhigh","Alibaba","China","API access","2026-09-01",null,"1","fraction","1",true,"0","2026-09-02","Epoch AI","Epoch AI",null,null,null,"otis_mock_aime_2024_2025.csv"],["2fQJP3brRApfBdQq7Zy3bm","OTIS Mock AIME 2024-2025","2024-12-19","Llama 3.1-405B","Llama-3.1-405B-Instruct","Meta AI","United States of America","Open weights (restricted use)","2024-07-23","3.8e+25","0.097222222222222224","fraction","0.097222222222222224",true,"0.03218644609162339","2025-02-25","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2fQJP3brRApfBdQq7Zy3bm.eval",null,null,"otis_mock_aime_2024_2025.csv"],["2gzNF2d53h2oCKDnojLtSP","GPQA diamond","2023-11-20","Qwen3-30B-A3B-Thinking (Jul 2025)","qwen3-30b-a3b-thinking-2507","Alibaba","China","Open weights (unrestricted)","2025-07-30","6.4800000000000005e+23","0.7007575757575758","fraction","0.7007575757575758",true,"0.028327897613545493","2026-08-30","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2gzNF2d53h2oCKDnojLtSP.eval",null,null,"gpqa_diamond.csv"],["2hH2GAPUFaJR7pfVKhhicg","SWE-Bench verified","2024-08-13","Claude Opus 4.6","claude-opus-4-6","Anthropic","United States of America","API access","2026-02-05",null,"0.78719008264462809","fraction","0.78719008264462809",true,"0.01862353730305288","2026-02-18","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2hH2GAPUFaJR7pfVKhhicg.eval",null,null,"swe_bench_verified.csv"],["2hbbp8z6PhB7c2T33os9q5","FrontierMath-Tier-4-v2-Private","2026-06-12","Claude Opus 4.6","claude-opus-4-6_max","Anthropic","United States of America","API access","2026-02-05",null,"0.26829268292682928","fraction","0.26829268292682928",true,"0.070055642030951576","2026-06-11","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2hbbp8z6PhB7c2T33os9q5.eval",null,null,"frontiermath_tier_4_v2.csv"],["2jKf4iEfVQnHkgAwEtD9Nn","Chess Puzzles","2025-12-10","Claude Fable 5","claude-fable-5_low","Anthropic","United States of America","API access","2026-06-09",null,"0.31","fraction","0.31",true,"0.046482319871173169","2026-10-13","Epoch AI","Epoch AI",null,null,null,"chess_puzzles.csv"],["2o8XZ8V6W5jKD7TuY4frux","FrontierMath-Tier-4-2025-07-01-Private","2025-07-11","Claude Sonnet 4.5","claude-sonnet-4-5-20250929","Anthropic","United States of America","API access","2025-09-29",null,"0.020833333333333332","fraction","0.020833333333333332",true,"0.020833333333333332","2025-09-29","Epoch AI","Epoch AI",null,null,null,"frontiermath_tier_4.csv"],["2pSDjMSGDh4HsAxkqUuNQP","GPQA diamond","2023-11-20","GPT-5 nano","gpt-5-nano-2025-08-07_high","OpenAI","United States of America","API access","2025-08-07",null,"0.69444444444444442","fraction","0.69444444444444442",true,"0.027594508998251045","2025-10-30","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2pSDjMSGDh4HsAxkqUuNQP.eval",null,null,"gpqa_diamond.csv"],["2t26VSNdsAE5pefQEMP25x","GPQA diamond","2023-11-20","Claude 3.7 Sonnet","claude-3-7-sonnet-20250219_64K","Anthropic","United States of America","API access","2025-02-24","3.3500000000000002e+25","0.79734848484848486","fraction","0.79734848484848486",true,"0.026506883123060064","2025-05-26","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2t26VSNdsAE5pefQEMP25x.eval",null,null,"gpqa_diamond.csv"],["2vg9qw9pd8zSyRMu9YNiVm","OTIS Mock AIME 2024-2025","2024-12-19","Claude 2.1","claude-2.1","Anthropic","United States of America","API access","2023-11-21",null,"0.019444444444444445","fraction","0.019444444444444445",true,"0.010477515876628662","2025-03-07","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2vg9qw9pd8zSyRMu9YNiVm.eval",null,null,"otis_mock_aime_2024_2025.csv"],["2wd9khVKiBzsAMUquz2R5s","MATH level 5","2021-03-05","DeepSeek-R1 (May 2025)","DeepSeek-R1-0528","DeepSeek","China","Open weights (unrestricted)","2025-05-28","4.0200100000000008e+24","0.96638972809667678","fraction","0.96638972809667678",true,"0.0042156161735636515","2025-05-29","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["2xMn6dbY9mw4pmkh8Tz9Gn","OTIS Mock AIME 2024-2025","2024-12-19","QwQ-32B","QwQ-32B","Alibaba","China","Open weights (unrestricted)","2025-03-05","3.5099999999999999e+24","0.59166666666666667","fraction","0.59166666666666667",true,"0.063489639654311647","2026-08-28","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2xMn6dbY9mw4pmkh8Tz9Gn.eval",null,null,"otis_mock_aime_2024_2025.csv"],["2xNPhKLsiWLHQBLLDGU4VJ","OTIS Mock AIME 2024-2025","2024-12-19","Claude 3.5 Sonnet","claude-3-5-sonnet-20240620","Anthropic","United States of America","API access","2024-06-20","2.7000000000000009e+25","0.065277777777777782","fraction","0.065277777777777782",true,"0.022293131815660016","2025-02-25","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2xNPhKLsiWLHQBLLDGU4VJ.eval",null,null,"otis_mock_aime_2024_2025.csv"],["2xfFf6KZAp2gUWYhHGkFgs","SimpleQA Verified","2025-09-09","DeepSeek V4 Pro 0813","deepseek-v4-pro-0813_max","DeepSeek","China","Open weights (unrestricted)","2026-08-13","9.7019999999999994e+24","0.5290581162324649","fraction","0.5290581162324649",true,"0.015808394665706597","2026-08-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2xfFf6KZAp2gUWYhHGkFgs.eval",null,null,"simpleqa_verified.csv"],["2y5jXmHGjyEyZvGjNDtRZe","Mystery Game Puzzles","2026-07-30","Qwen 3.6 Flash","qwen3.6-flash","Alibaba","China",null,"2026-04-27",null,"0.12","fraction","0.12",true,"0.032659863237109038","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["2z7kL9DpfvY44T9Wo99FYx","FrontierMath-Tier-4-v2-Private","2026-06-12","Gemini 2.5 Pro (Jun 2025)","gemini-2.5-pro","Google DeepMind","United States of America","API access","2025-06-17",null,"0","fraction","0",true,"0","2026-06-11","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2z7kL9DpfvY44T9Wo99FYx.eval",null,null,"frontiermath_tier_4_v2.csv"],["3542DFKGpjD6k8AZfGKD7W","EBR-bench","2026-07-01","GPT-5.2","gpt-5.2-2025-12-11_xhigh","OpenAI","United States of America","API access","2025-12-11",null,"0.230159","fraction","0.230159",true,null,"2026-06-26","Epoch AI","Epoch AI",null,null,null,"ebr_bench.csv"],["37pJqPpXTE6ia9ikmmGPJ4","OTIS Mock AIME 2024-2025","2024-12-19","Claude Opus 4.8","claude-opus-4-8_max","Anthropic","United States of America","API access","2026-05-28",null,"0.98333333333333328","fraction","0.98333333333333328",true,"0.014101901870444154","2026-06-07","Epoch AI","Epoch AI",null,null,null,"otis_mock_aime_2024_2025.csv"],["3CGChL5vNDM6Df5C8Z8owN","OTIS Mock AIME 2024-2025","2024-12-19","Gemma 3 1B","gemma-3-1b-it","Google DeepMind","United States of America","Open weights (restricted use)","2025-03-12","1.2e+22","0.011111111111111112","fraction","0.011111111111111112",true,"0.0053628183286856812","2026-08-28","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3CGChL5vNDM6Df5C8Z8owN.eval",null,null,"otis_mock_aime_2024_2025.csv"],["3D8aaFBLZwQcnWHYKwvnmq","OTIS Mock AIME 2024-2025","2024-12-19","GPT-5","gpt-5-2025-08-07_high","OpenAI","United States of America","API access","2025-08-07","6.6000000000000002e+25","0.91388888888888886","fraction","0.91388888888888886",true,"0.036588721867554137","2025-10-29","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3D8aaFBLZwQcnWHYKwvnmq.eval",null,null,"otis_mock_aime_2024_2025.csv"],["3GzYKQW2K4iijm6a73rVeh","FrontierMath-2025-02-28-Private","2025-02-28","Claude Sonnet 4.5","claude-sonnet-4-5-20250929_59K","Anthropic","United States of America","API access","2025-09-29",null,"0.13494809688581316","fraction","0.13494809688581316",true,"0.020132987375676092","2025-11-13","Epoch AI","Epoch AI",null,null,null,"frontiermath.csv"],["3JJ4ChNxMo8CGAh3HrKNrw","SimpleQA Verified","2025-09-09","DeepSeek V4.1 Flash","deepseek-v4.1-flash_max","DeepSeek","China","Open weights (unrestricted)","2026-09-09","4.3199999999999998e+24","0.42899999999999999","fraction","0.42899999999999999",true,"0.015658997547870177","2026-10-13","Epoch AI","Epoch AI",null,null,null,"simpleqa_verified.csv"],["3L22tfAid5ZM42p92tqC73","Mystery Game Puzzles","2026-07-30","Gemini 3.6 Flash","gemini-3.6-flash_minimal","Google DeepMind","United States of America","API access","2026-07-21",null,"0.25","fraction","0.25",true,"0.043519413988924463","2026-08-05","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["3NYyCGnM6XhgytjyVGtwh8","MATH level 5","2021-03-05","GPT-5 mini","gpt-5-mini-2025-08-07_medium","OpenAI","United States of America","API access","2025-08-07",null,"0.9679003021148036","fraction","0.9679003021148036",true,"0.003853475747353661","2025-08-20","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["3PVdaSEYFJKgYUgHnF4DBu","Mystery Game Puzzles","2026-07-30","Claude Sonnet 5.5","claude-sonnet-5-5_max","Anthropic","United States of America","API access","2026-09-28",null,"0.65000000000000002","fraction","0.65000000000000002",true,"0.047937248544110217","2026-09-29","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["3Q6osT8EYezayG7yfxkSpr","GPQA diamond","2023-11-20","GPT-5.2","gpt-5.2-2025-12-11_high","OpenAI","United States of America","API access","2025-12-11",null,"0.88194444444444442","fraction","0.88194444444444442",true,"0.019138582776339241","2025-12-11","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3Q6osT8EYezayG7yfxkSpr.eval",null,null,"gpqa_diamond.csv"],["3QBsxKkbF2R2LEXTd6HDrJ","SimpleQA Verified","2025-09-09","GPT-5.4 Nano","gpt-5.4-nano-2026-03-17_high","OpenAI","United States of America","API access","2026-03-17",null,"0.11700000000000001","fraction","0.11700000000000001",true,"0.010169287802713345","2026-08-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3QBsxKkbF2R2LEXTd6HDrJ.eval",null,null,"simpleqa_verified.csv"],["3QjP5HPi8tKUzHtNJktfv4","OTIS Mock AIME 2024-2025","2024-12-19","gpt-oss-120b","openai/gpt-oss-120b_high","OpenAI","United States of America","Open weights (unrestricted)","2025-08-05","4.9400000000000001e+24","0.88888888888888884","fraction","0.88888888888888884",true,"0.044633436556132729","2025-12-11","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3QjP5HPi8tKUzHtNJktfv4.eval",null,null,"otis_mock_aime_2024_2025.csv"],["3QtkFWzSLzd4hgYGsNd5cL","Mystery Game Puzzles","2026-07-30","Qwen 3.6 Flash","qwen3.6-flash_none","Alibaba","China",null,"2026-04-27",null,"0.17999999999999999","fraction","0.17999999999999999",true,"0.038612291966536913","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["3S6fjGAMKWKK3zcdxkmh9H","OTIS Mock AIME 2024-2025","2024-12-19","Gemini 1.5 Pro (May 2024)","gemini-1.5-pro-001","Google DeepMind","United States of America","API access","2024-05-14",null,"0.06805555555555555","fraction","0.06805555555555555",true,"0.018930342955148779","2025-02-25","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3S6fjGAMKWKK3zcdxkmh9H.eval",null,null,"otis_mock_aime_2024_2025.csv"],["3UbYVQELDHAcQgu7sTTnRf","GPQA diamond","2023-11-20","Magistral Small 1.2","magistral-small-2509","Mistral AI","France","Open weights (unrestricted)","2025-09-18",null,"0.47601010101010099","fraction","0.47601010101010099",true,"0.025993462698453398","2026-08-30","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3UbYVQELDHAcQgu7sTTnRf.eval",null,null,"gpqa_diamond.csv"],["3VDhPT5WvzjJZkRc36Kuvi","MATH level 5","2021-03-05","o3-mini","o3-mini-2025-01-31_high","OpenAI","United States of America","API access","2025-01-31",null,"0.96487915407854985","fraction","0.96487915407854985",true,"0.0042652634619846693","2025-02-13","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["3ZnPtGRJkvqHk8wvWWRgCe","Mystery Game Puzzles","2026-07-30","Claude Opus 4.8","claude-opus-4-8_xhigh","Anthropic","United States of America","API access","2026-05-28",null,"0.31","fraction","0.31",true,"0.046482319871173169","2026-07-26","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["3ZzqFaVH7RgvRyxCt6RseN","Mystery Game Puzzles","2026-07-30","GPT-5","gpt-5-2025-08-07_medium","OpenAI","United States of America","API access","2025-08-07","6.6000000000000002e+25","0.14999999999999999","fraction","0.14999999999999999",true,"0.035887028128263672","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["3h8STJpG2VzY9LiBUzwotv","GPQA diamond","2023-11-20","GPT-6 Astra","gpt-6-astra_max","OpenAI","United States of America","API access","2026-09-03","9.3999999999999995e+26","0.95770202020202022","fraction","0.95770202020202022",true,"0.013696812097020311","2026-08-30","Epoch AI","Epoch AI",null,null,null,"gpqa_diamond.csv"],["3iRQkf5v7Wu7YuZhxa76Gg","FrontierMath-Tier-4-v2-Private","2026-06-12","Grok 4.3 Beta","grok-4.3_high","xAI","United States of America","Hosted access (no API)","2026-04-17",null,"0.14634146341463414","fraction","0.14634146341463414",true,"0.055885069450680974","2026-06-17","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3iRQkf5v7Wu7YuZhxa76Gg.eval",null,null,"frontiermath_tier_4_v2.csv"],["3n5KDcBaKqJh3WTg7qU2rs","OTIS Mock AIME 2024-2025","2024-12-19","Qwen 3.6 35B-A3B","qwen3.6-35b-a3b","Alibaba","China","Open weights (unrestricted)","2026-04-14",null,"0.8666666666666667","fraction","0.8666666666666667",true,"0.051247074319053836","2026-08-07","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3n5KDcBaKqJh3WTg7qU2rs.eval",null,null,"otis_mock_aime_2024_2025.csv"],["3obcsGCfuwYeEm9wRyqzPg","GPQA diamond","2023-11-20","Claude Opus 4.1","claude-opus-4-1-20250805_27K","Anthropic","United States of America","API access","2025-08-05",null,"0.76767676767676762","fraction","0.76767676767676762",true,"0.030088629490217445","2025-08-05","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3obcsGCfuwYeEm9wRyqzPg.eval",null,null,"gpqa_diamond.csv"],["3qLHwibDhgtWEbKGwxUYVa","OTIS Mock AIME 2024-2025","2024-12-19","GPT-4.1 nano","gpt-4.1-nano-2025-04-14","OpenAI","United States of America","API access","2025-04-14",null,"0.28888888888888886","fraction","0.28888888888888886",true,"0.059700195609227458","2025-04-14","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3qLHwibDhgtWEbKGwxUYVa.eval",null,null,"otis_mock_aime_2024_2025.csv"],["3w2dD9rcMPHLYsEsJmYsCX","MATH level 5","2021-03-05","Claude Haiku 4.5","claude-haiku-4-5-20251001","Anthropic","United States of America","API access","2025-10-15",null,"0.86914652567975825","fraction","0.86914652567975825",true,"0.0077475516872147722","2025-10-16","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["3zda4kRmrZfxiafpk8BtMM","EBR-bench","2026-07-01","Claude Opus 4.8","claude-opus-4-8_max","Anthropic","United States of America","API access","2026-05-28",null,"0.2857142857142857","fraction","0.2857142857142857",true,"0.014197256999998662","2026-08-07","Epoch AI","Epoch AI",null,null,null,"ebr_bench.csv"],["433Hqw9fVgtRtAKQfareFr","Furniture Assembly","2026-09-23","Claude Fable 5","claude-fable-5_max","Anthropic","United States of America","API access","2026-06-09",null,"0.35833333333333334","fraction","0.35833333333333334",true,"0.06185876325418331","2026-09-10","Epoch AI","Epoch AI",null,null,null,"furniture_assembly.csv"],["43f36RTDoJGxXWQDVvTLJj","OTIS Mock AIME 2024-2025","2024-12-19","Gemini 4 Argon","gemini-4-argon_high","Google DeepMind","United States of America","Limited access","2026-09-30",null,"1","fraction","1",true,"0","2026-10-13","Epoch AI","Epoch AI",null,null,null,"otis_mock_aime_2024_2025.csv"],["452pB5w5ea6uy92e2q2NMv","OTIS Mock AIME 2024-2025","2024-12-19","Qwen3.6 27B","qwen3.6-27b","Alibaba","China","Open weights (unrestricted)","2026-04-22",null,"0.91111111111111109","fraction","0.91111111111111109",true,"0.042902546629485457","2026-08-07","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F452pB5w5ea6uy92e2q2NMv.eval",null,null,"otis_mock_aime_2024_2025.csv"],["46RCssznDADYeg8MuSgvsj","GPQA diamond","2023-11-20","Qwen3-Max","qwen3-max-2025-09-23","Alibaba","China","API access","2025-09-24","1.5120000000000001e+25","0.72601010101010099","fraction","0.72601010101010099",true,"0.027345281031712351","2025-10-06","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F46RCssznDADYeg8MuSgvsj.eval",null,null,"gpqa_diamond.csv"],["4ACEC4x26HWRGiAepHGw43","SimpleQA Verified","2025-09-09","Qwen3-235B-A22B-Thinking (Jul 2025)","Qwen3-235B-A22B-Thinking-2507","Alibaba","China","Open weights (unrestricted)","2025-07-25","4.7520000000000001e+24","0.40440440440440439","fraction","0.40440440440440439",true,"0.015535255725079345","2026-08-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4ACEC4x26HWRGiAepHGw43.eval",null,null,"simpleqa_verified.csv"],["4AfhcmYVNrw6gM5u8CQsyy","SWE-Bench verified","2024-08-13","GLM-5.2","glm-5.2_max","Z.ai (Zhipu AI)","China","Open weights (unrestricted)","2026-06-16",null,"0.78700000000000003","fraction","0.78700000000000003",true,"0.018656911901656907","2026-06-25","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4AfhcmYVNrw6gM5u8CQsyy.eval",null,null,"swe_bench_verified.csv"],["4BCZTu7HQKmhdwRR2W4bzT","FrontierMath-Tier-4-v2-Private","2026-06-12","GPT-6 Astra","gpt-6-astra_none","OpenAI","United States of America","API access","2026-09-03","9.3999999999999995e+26","0.82926829268292679","fraction","0.82926829268292679",true,"0.059494199598294967","2026-08-30","Epoch AI","Epoch AI",null,null,null,"frontiermath_tier_4_v2.csv"],["4CzMJvWvuiLMCZhe2JGmSb","Mystery Game Puzzles","2026-07-30","GPT-5.4 Mini","gpt-5.4-mini-2026-03-17_medium","OpenAI","United States of America","API access","2026-03-17",null,"0.070000000000000007","fraction","0.070000000000000007",true,"0.02564323999762428","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["4DNcqcs4R97ZWNTMDrXSZN","FrontierMath-2025-02-28-Private","2025-02-28","GLM-5.1","glm-5.1","Z.ai (Zhipu AI)","China","Open weights (unrestricted)","2026-04-07",null,"0.33448275862068966","fraction","0.33448275862068966",true,"0.027753489933368777","2026-05-11","Epoch AI","Epoch AI",null,null,null,"frontiermath.csv"],["4DWnpJowAfeQDHc2xDNy2C","MATH level 5","2021-03-05","o1-mini","o1-mini-2024-09-12_high","OpenAI","United States of America","API access","2024-09-12",null,"0.89180513595166166","fraction","0.89180513595166166",true,"0.0068028201660656484","2025-02-13","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["4E5xGsuRMwMBhAfC4F2G4N","OTIS Mock AIME 2024-2025","2024-12-19","Kimi K3","kimi-k3_high","Moonshot","China","Open weights (non-commercial)","2026-07-16","2.0000999999999998e+25","0.93333333333333335","fraction","0.93333333333333335",true,"0.037605071654517749","2026-08-07","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4E5xGsuRMwMBhAfC4F2G4N.eval",null,null,"otis_mock_aime_2024_2025.csv"],["4EayGByBV2xodNBkrZMcFb","Chess Puzzles","2025-12-10","GPT-5.5","gpt-5.5_low","OpenAI","United States of America","API access","2026-04-23",null,"0.29999999999999999","fraction","0.29999999999999999",true,"0.046056618647183821","2026-10-13","Epoch AI","Epoch AI",null,null,null,"chess_puzzles.csv"],["4HVvM9ZWKKPLQPcC8WYYMT","OTIS Mock AIME 2024-2025","2024-12-19","DeepSeek V4 Pro 0813","deepseek-v4-pro-0813_max","DeepSeek","China","Open weights (unrestricted)","2026-08-13","9.7019999999999994e+24","0.98611111111111116","fraction","0.98611111111111116",true,"0.0099098065001760501","2026-08-18","Epoch AI","Epoch AI",null,null,null,"otis_mock_aime_2024_2025.csv"],["4Jq9M5CbuWMyxRHHxavMwA","Furniture Assembly","2026-09-23","Claude Opus 4.6","claude-opus-4-6_max","Anthropic","United States of America","API access","2026-02-05",null,"0.28333333333333333","fraction","0.28333333333333333",true,"0.058665318423131239","2026-09-10","Epoch AI","Epoch AI",null,null,null,"furniture_assembly.csv"],["4LWNorP8Fy8V8doxirNFcH","SimpleQA Verified","2025-09-09","Qwen 3.6 Plus","qwen3.6-plus","Alibaba","China","API access","2026-03-31",null,"0.44144144144144143","fraction","0.44144144144144143",true,"0.015718302238794238","2026-08-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4LWNorP8Fy8V8doxirNFcH.eval",null,null,"simpleqa_verified.csv"],["4MyKFuqZDpWQCFpKuHbMyD","Chess Puzzles","2025-12-10","o4-mini","o4-mini-2025-04-16_high","OpenAI","United States of America","API access","2025-04-16",null,"0.13","fraction","0.13",true,"0.033799766898963107","2026-10-13","Epoch AI","Epoch AI",null,null,null,"chess_puzzles.csv"],["4NiUpCrLfz3oFaerkrMeBt","GPQA diamond","2023-11-20","o1-mini","o1-mini-2024-09-12_medium","OpenAI","United States of America","API access","2024-09-12",null,"0.5950126262626263","fraction","0.5950126262626263",true,"0.027951242386372761","2025-01-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4NiUpCrLfz3oFaerkrMeBt.eval",null,null,"gpqa_diamond.csv"],["4PTATufH2ra3guNeLwT9p9","MATH level 5","2021-03-05","Mixtral 8x7B","Mixtral-8x7B-Instruct-v0.1","Mistral AI","France","Open weights (unrestricted)","2023-12-11","7.74e+23","0.092900302114803629","fraction","0.092900302114803629",true,"0.0051024645463178531","2025-01-27","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["4QM4h7ndQiDRL2anjKeddK","OTIS Mock AIME 2024-2025","2024-12-19","Gemini 3 Pro","gemini-3-pro-preview","Google DeepMind","United States of America","API access","2025-11-18",null,"0.91388888888888886","fraction","0.91388888888888886",true,"0.036588721867554137","2025-11-19","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4QM4h7ndQiDRL2anjKeddK.eval",null,null,"otis_mock_aime_2024_2025.csv"],["4QRM7D5HeCwCvWVZqhJKRS","Chess Puzzles","2025-12-10","GPT-5","gpt-5-2025-08-07_medium","OpenAI","United States of America","API access","2025-08-07","6.6000000000000002e+25","0.32000000000000001","fraction","0.32000000000000001",true,"0.046882617226215062","2026-10-13","Epoch AI","Epoch AI",null,null,null,"chess_puzzles.csv"],["4QrkRM7KEDCQvg4wvfhz7N","Furniture Assembly","2026-09-23","Claude Opus 5.5","claude-opus-5-5_max","Anthropic","United States of America","API access","2026-09-22",null,"0.83333333333333337","fraction","0.83333333333333337",true,"0.047040472216649226","2026-09-22","Epoch AI","Epoch AI",null,null,null,"furniture_assembly.csv"],["4RnNJhaFMGdLSFjoHHMR8k","FrontierMath-Tiers-1-3-v2-Private","2026-06-12","o1","o1-2024-12-17_medium","OpenAI","United States of America","API access","2024-12-17",null,"0.10175438596491228","fraction","0.10175438596491228",true,"0.017939690721286369","2026-08-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4RnNJhaFMGdLSFjoHHMR8k.eval",null,null,"frontiermath_tiers_1_3_v2.csv"],["4S3ZrJDkwh4gmGrmJQdvzR","FrontierMath-Tier-4-v2-Private","2026-06-12","GLM-5.3","glm-5.3_max","Z.ai (Zhipu AI)","China","Open weights (restricted use)","2026-08-14",null,"0.29268292682926828","fraction","0.29268292682926828",true,"0.071940883920744519","2026-08-25","Epoch AI","Epoch AI",null,null,null,"frontiermath_tier_4_v2.csv"],["4S4GXbkRhLz8wWP97jYG57","Mystery Game Puzzles","2026-07-30","DeepSeek V4 Flash 0731","deepseek-v4-flash-0731_max","DeepSeek","China","Open weights (unrestricted)","2026-07-31","2.4960000000000001e+24","0.34000000000000002","fraction","0.34000000000000002",true,"0.04760952285695233","2026-08-05","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["4StdTsQNqgsKc8RFdauiF2","FrontierMath-2025-02-28-Private","2025-02-28","Kimi K2.6","kimi-k2.6","Moonshot","China","Open weights (unrestricted)","2026-04-20",null,"0.3896551724137931","fraction","0.3896551724137931",true,"0.028686590614000477","2026-05-07","Epoch AI","Epoch AI",null,null,null,"frontiermath.csv"],["4a3M8rRWUoPphCSr2dguXH","Mystery Game Puzzles","2026-07-30","Gemini 3.1 Pro","gemini-3.1-pro-preview_low","Google DeepMind","United States of America","API access","2026-02-19",null,"0.28999999999999998","fraction","0.28999999999999998",true,"0.045604802157206872","2026-08-06","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["4afZ2hjLiJnPy5pD7TfE3K","Chess Puzzles","2025-12-10","Claude Opus 4.5","claude-opus-4-5-20251101","Anthropic","United States of America","API access","2025-11-24",null,"0.050000000000000003","fraction","0.050000000000000003",true,"0.021904291355759033","2026-10-13","Epoch AI","Epoch AI",null,null,null,"chess_puzzles.csv"],["4bAYQuh4heJoTNhapVZLNB","MATH level 5","2021-03-05","WizardLM-2 8x22B","WizardLM-2-8x22B","Microsoft","United States of America","Open weights (unrestricted)","2024-04-15",null,"0.25736404833836857","fraction","0.25736404833836857",true,"0.0087195215751901863","2025-01-27","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["4bLcFNu5zF6YuZf3qVKoHE","GPQA diamond","2023-11-20","GPT-5.6 Terra","gpt-5.6-terra_max","OpenAI","United States of America","API access","2026-07-09",null,"0.93308080808080807","fraction","0.93308080808080807",true,"0.015363672147634115","2026-07-09","Epoch AI","Epoch AI",null,null,null,"gpqa_diamond.csv"],["4bkXhqCNoe6RpTe9taJ7kR","MATH level 5","2021-03-05","Llama 2-70B","Llama-2-70b-chat-hf","Meta AI","United States of America","Open weights (restricted use)","2023-07-18","8.1000000000000003e+23","0.032854984894259816","fraction","0.032854984894259816",true,"0.0025422297741566099","2025-01-27","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["4gZy2dAAT2EPZDGz5puD3H","FrontierMath-Tiers-1-3-v2-Private","2026-06-12","Gemini 3.1 Flash-Lite","gemini-3.1-flash-lite_minimal","Google","United States of America","API access","2026-03-03",null,"0.21403508771929824","fraction","0.21403508771929824",true,"0.024338000553262389","2026-08-28","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4gZy2dAAT2EPZDGz5puD3H.eval",null,null,"frontiermath_tiers_1_3_v2.csv"],["4hmmfwG9tgZJvKhL78nKzL","FrontierMath-Tiers-1-3-v2-Private","2026-06-12","GLM-5.1","glm-5.1_none","Z.ai (Zhipu AI)","China","Open weights (unrestricted)","2026-04-07",null,"0.24912280701754386","fraction","0.24912280701754386",true,"0.025664454102329461","2026-08-28","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4hmmfwG9tgZJvKhL78nKzL.eval",null,null,"frontiermath_tiers_1_3_v2.csv"],["4j3WRhhruXrfaq9Jki3NDc","GPQA diamond","2023-11-20","GPT-4 Turbo (Nov 2023)","gpt-4-0125-preview","OpenAI","United States of America","API access","2024-01-25",null,"0.42266414141414144","fraction","0.42266414141414144",true,"0.026795949166711065","2025-01-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4j3WRhhruXrfaq9Jki3NDc.eval",null,null,"gpqa_diamond.csv"],["4oSbA2RKFsfuAfVayAMAww","Mystery Game Puzzles","2026-07-30","Claude Sonnet 4.5","claude-sonnet-4-5-20250929_48K","Anthropic","United States of America","API access","2025-09-29",null,"0.17000000000000001","fraction","0.17000000000000001",true,"0.037752516806863687","2026-07-25","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["4pbEvTxsbzNRCh9kU9Xhun","Chess Puzzles","2025-12-10","Muse Spark 1.1","muse-spark-1.1_xhigh","Meta AI","United States of America","API access","2026-07-09",null,"0.34000000000000002","fraction","0.34000000000000002",true,"0.047609522856952337","2026-10-13","Epoch AI","Epoch AI",null,null,null,"chess_puzzles.csv"],["4sPs53wmM9bvN8JXzsiNCk","GPQA diamond","2023-11-20","GPT-5.2","gpt-5.2-2025-12-11_none","OpenAI","United States of America","API access","2025-12-11",null,"0.73232323232323238","fraction","0.73232323232323238",true,"0.031544498882702825","2026-07-13","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4sPs53wmM9bvN8JXzsiNCk.eval",null,null,"gpqa_diamond.csv"],["4sRo7TxavQAsjaEALPZdDy","Chess Puzzles","2025-12-10","DeepSeek V4.1 Flash 1017","deepseek-v4.1-flash-1017_max","DeepSeek","China","Open weights (unrestricted)","2026-10-17",null,"0.46000000000000002","fraction","0.46000000000000002",true,"0.050090826596203307","2026-10-19","Epoch AI","Epoch AI",null,null,null,"chess_puzzles.csv"],["4tZWwV9tqEgsCaKeSuSoG4","FrontierMath-Tiers-1-3-v2-Private","2026-06-12","Claude Sonnet 5.5","claude-sonnet-5-5_max","Anthropic","United States of America","API access","2026-09-28",null,"0.88771929824561402","fraction","0.88771929824561402",true,"0.018734030360524248","2026-09-29","Epoch AI","Epoch AI",null,null,null,"frontiermath_tiers_1_3_v2.csv"],["4tmJcpwFZKJrmHacCFtPYV","FrontierMath-Tier-4-2025-07-01-Private","2025-07-11","Qwen 3.6 Flash","qwen3.6-flash","Alibaba","China",null,"2026-04-27",null,"0","fraction","0",true,"0","2026-05-12","Epoch AI","Epoch AI",null,null,null,"frontiermath_tier_4.csv"],["4uDz9b6SosxDSZf7swMD9D","OTIS Mock AIME 2024-2025","2024-12-19","GPT-6 Luna","gpt-6-luna_max","OpenAI","United States of America","API access","2026-09-22",null,"0.98888888888888893","fraction","0.98888888888888893",true,"0.0066740279224255109","2026-09-22","Epoch AI","Epoch AI",null,null,null,"otis_mock_aime_2024_2025.csv"],["4uxDyWmq5f5azVYfWBGUHh","Mystery Game Puzzles","2026-07-30","GPT-5.6 Sol","gpt-5.6-sol_none","OpenAI","United States of America","API access","2026-07-09",null,"0.33000000000000002","fraction","0.33000000000000002",true,"0.04725815626252608","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["4wN6FKe2db9CLQ3NUFfYge","MATH level 5","2021-03-05","GPT-5","gpt-5-2025-08-07_high","OpenAI","United States of America","API access","2025-08-07","6.6000000000000002e+25","0.98130664652567978","fraction","0.98130664652567978",true,"0.0031922231523012308","2025-10-29","Epoch AI","Epoch AI",null,null,null,"math_level_5.csv"],["53BDFebxiT9KGeP5FRt6bJ","OTIS Mock AIME 2024-2025","2024-12-19","Inkling-Small","inkling-small_xhigh","Thinking Machines","United States of America","Open weights (unrestricted)","2026-07-15",null,"0.90000000000000002","fraction","0.90000000000000002",true,"0.039648073054937949","2026-08-14","Epoch AI","Epoch AI",null,null,null,"otis_mock_aime_2024_2025.csv"],["53PtW8g64r6zeLY38aK9Q4","FrontierMath-Tiers-1-3-v2-Private","2026-06-12","GPT-5","gpt-5-2025-08-07_minimal","OpenAI","United States of America","API access","2025-08-07","6.6000000000000002e+25","0.18245614035087721","fraction","0.18245614035087721",true,"0.022917941277334045","2026-08-27","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F53PtW8g64r6zeLY38aK9Q4.eval",null,null,"frontiermath_tiers_1_3_v2.csv"],["58MQQiJ7vvgvP9e8LcG6eV","Mystery Game Puzzles","2026-07-30","gpt-oss-120b","gpt-oss-120b_medium","OpenAI","United States of America","Open weights (unrestricted)","2025-08-05","4.9400000000000001e+24","0.02","fraction","0.02",true,"0.014070529413628966","2026-08-27","Epoch AI","Epoch AI",null,null,null,"mystery_game_puzzles.csv"],["58eQmyCfPa3FufhXJFvAL2","GPQA diamond","2023-11-20","Claude Sonnet 4.6","claude-sonnet-4-6_32K","Anthropic","United States of America","API access","2026-02-17",null,"0.8737373737373737","fraction","0.8737373737373737",true,"0.020034282226331888","2026-02-20","Epoch AI","Epoch AI","https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F58eQmyCfPa3FufhXJFvAL2.eval",null,null,"gpqa_diamond.csv"]],"row_count_in_preview":100,"total_row_count":7121,"preview_truncated":true,"limits":{"rows":100,"columns":256},"citation":{"dataset_url":"https://mostlyright.md/datasets/llm-benchmark-scores-by-model-since-2019","table_url":"https://mostlyright.md/datasets/llm-benchmark-scores-by-model-since-2019/tables?table=llm-benchmark-results","table_version_id":"dde2b5b0-4267-5ba8-80d1-91188ea9f96c","content_digest":null}}