{"schema":1,"key":"featured","environment":"production","data":{"10001":{"result_key":"16494cb722a8bf55cf71f13c2949951256ce534190b18306bad9fc412d78647a","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=16494cb722a8bf55cf71f13c2949951256ce534190b18306bad9fc412d78647a","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.6868686868686869","value":"68.68686868686869","display":"68.7%"}},"10002":{"result_key":"9ccf6cf5e8fcc87c0a9d5bc7532006b0f03e1e345dfb4996729bc2ebc7ff4b7d","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=9ccf6cf5e8fcc87c0a9d5bc7532006b0f03e1e345dfb4996729bc2ebc7ff4b7d","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.6691919191919192","value":"66.91919191919192","display":"66.9%"}},"10003":{"result_key":"a698dc376ffe87cc46afbac46ef4fc794a53ed98183c027cef88de8c9780c0ff","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":"high","score":{"raw":"0.8181818181818182","value":"81.81818181818182","display":"81.8%"}},"10004":{"result_key":"b126864b661763939d17a24655d74559b6e008ab74780c37f63fd8431dc871bd","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":"high","score":{"raw":"0.7960858585858586","value":"79.60858585858586","display":"79.6%"}},"10005":{"result_key":"e48598e0b93c40dc44ab461c276e894e365615aca56c17a23026960a06fca96e","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=e48598e0b93c40dc44ab461c276e894e365615aca56c17a23026960a06fca96e","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"64.7%","value":"64.7","display":"64.7%"}},"10006":{"result_key":"3eac4158005bef3391c688cdded89e3ce34588b59e02313f0e05b3d8170b63ad","exact_result_href":"/benchmarks/swe-atlas/codebase-qna-public-codex?view=history&result=3eac4158005bef3391c688cdded89e3ce34588b59e02313f0e05b3d8170b63ad","benchmark":{"name":"SWE Atlas","slug":"swe-atlas","aliases":[]},"benchmark_version":"Codebase QnA — Public; Codex","benchmark_version_slug":"codebase-qna-public-codex","reasoning_level":"xHigh","score":{"raw":"32.6","value":"32.6","display":"32.6%"}},"10007":{"result_key":"023cda713f5001357e6f4e3f8974b9d65d0deda6d56465c37a39a8ccebf6c191","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=023cda713f5001357e6f4e3f8974b9d65d0deda6d56465c37a39a8ccebf6c191","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"xhigh","score":{"raw":"52.4%","value":"52.4","display":"52.4%"}},"10008":{"result_key":"b8afc1adaaa88504aa76aaae47327ca5abae567872052c6650d7685bc066e373","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=b8afc1adaaa88504aa76aaae47327ca5abae567872052c6650d7685bc066e373","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"xhigh","score":{"raw":"55.1%","value":"55.1","display":"55.1%"}},"10009":{"result_key":"ed9c907bf8bd09a4e511fcb30d8e9fc2d30af2b14ae8a9d25a1f4fa2daef32ea","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=ed9c907bf8bd09a4e511fcb30d8e9fc2d30af2b14ae8a9d25a1f4fa2daef32ea","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"43%","value":"43","display":"43.0%"}},"10010":{"result_key":"734e104872e7162deb325c4435d54d74a0aeddaeaafbe1bc162439935fa7faa3","exact_result_href":null,"benchmark":{"name":"AutomationBench","slug":"automationbench","aliases":[]},"benchmark_version":"1.0.6","benchmark_version_slug":"1-0-6","reasoning_level":null,"score":{"raw":"3.81%","value":"3.81","display":"3.8%"}},"10011":{"result_key":"f55c33b23b23aef1aa7679b899b1805d8286cc3143d0f80b1b2a6cdbb8c40c0f","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=f55c33b23b23aef1aa7679b899b1805d8286cc3143d0f80b1b2a6cdbb8c40c0f","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"58.2%","value":"58.2","display":"58.2%"}},"10012":{"result_key":"2822fb2acbcd5526302ab4202c106a6d38fd144eb46f14befc874c5772e2eb50","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":"high","score":{"raw":"0.8819444444444444","value":"88.19444444444444","display":"88.2%"}},"10013":{"result_key":"8630fc2adbb21eb7963474aba7a27dd4e7f8427530cf947abaec15209d80ec34","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=8630fc2adbb21eb7963474aba7a27dd4e7f8427530cf947abaec15209d80ec34","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"44.3%","value":"44.3","display":"44.3%"}},"10014":{"result_key":"9f9c7263f8b2640f6a4470a1486ee42f91b1918a5b71bdf713c604e2d9df234a","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=9f9c7263f8b2640f6a4470a1486ee42f91b1918a5b71bdf713c604e2d9df234a","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"54.3%","value":"54.3","display":"54.3%"}},"10015":{"result_key":"60c9c4a60db5297f4cceceae07410237b43314b89da451570e10031bdb3272c2","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=60c9c4a60db5297f4cceceae07410237b43314b89da451570e10031bdb3272c2","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"60%","value":"60","display":"60.0%"}},"10016":{"result_key":"d55380589e2f265f3b8e3e9c38105c4e48324e15c0a520416f4900af8baf2904","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=d55380589e2f265f3b8e3e9c38105c4e48324e15c0a520416f4900af8baf2904","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.6584595959595959","value":"65.84595959595959","display":"65.8%"}},"10017":{"result_key":"55ec5c263dc40119268982f9a16e58ec9eb1f3885f72aca039b99ddfac7362b1","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=55ec5c263dc40119268982f9a16e58ec9eb1f3885f72aca039b99ddfac7362b1","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.48926767676767674","value":"48.926767676767674","display":"48.9%"}},"10018":{"result_key":"9aa79e2902bf2e2a05fdb4e0d16b9b11ebf0676ae80b287fa4cf8a0c0b64a9c5","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":"high","score":{"raw":"0.8617424242424242","value":"86.17424242424242","display":"86.2%"}},"10019":{"result_key":"fbe03155252bb835c7889479e764e1f3ecd1f310b2eb3f0fbcbad6520e97bd8c","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":"high","score":{"raw":"0.75","value":"75","display":"75.0%"}},"10020":{"result_key":"3c6e17e6688656b198b7d371746c31f30f36ceea10c9eebbc99a1a1db8518d2f","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":"high","score":{"raw":"0.6944444444444444","value":"69.44444444444444","display":"69.4%"}},"10021":{"result_key":"fedde55718659d6bb5cd3c2760208d9aacaba4adaff554d5df76f1aed395405a","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":"high","score":{"raw":"0.8358585858585859","value":"83.58585858585859","display":"83.6%"}},"10022":{"result_key":"d468b9fc9032e8affbe8ab230136180f5fbc9829dbc9ff3df980a4ce7d7844f6","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":"high","score":{"raw":"0.7847","value":"78.47","display":"78.5%"}},"15001":{"result_key":"0752cd0f63a70f4c68a3eee58dae28ea4dac7b10e2773ed16dbe251771b38c62","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=0752cd0f63a70f4c68a3eee58dae28ea4dac7b10e2773ed16dbe251771b38c62","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"4.4%","value":"4.4","display":"4.4%"}},"20001":{"result_key":"564f3b433966fcc1a62bb37e614b03608161d0694c78f0d9581e2070b6d0b9d5","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=564f3b433966fcc1a62bb37e614b03608161d0694c78f0d9581e2070b6d0b9d5","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.6603535353535354","value":"66.03535353535354","display":"66.0%"}},"20002":{"result_key":"926de82386c96ef6f0d9346d38c6dda13e7b561ec215aae72f79957088d4981e","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=926de82386c96ef6f0d9346d38c6dda13e7b561ec215aae72f79957088d4981e","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.6919191919191919","value":"69.19191919191919","display":"69.2%"}},"20003":{"result_key":"7685f5fe82ca37dacd29ce7495b4145db4805c1422cbdfab9018ffdd37c5466b","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=7685f5fe82ca37dacd29ce7495b4145db4805c1422cbdfab9018ffdd37c5466b","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.6666666666666666","value":"66.66666666666666","display":"66.7%"}},"20004":{"result_key":"807b2cafa77185357e0bdb4e8c7f7a77508eea87cfa81ee76e54472d8cfcf171","exact_result_href":null,"benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"59.7%","value":"59.7","display":"59.7%"}},"20005":{"result_key":"0d1516c3ad25c6be91f3ff8cb96dc3b3ed0c1ae1844e3091b9a5eb3fd91e0ffb","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=0d1516c3ad25c6be91f3ff8cb96dc3b3ed0c1ae1844e3091b9a5eb3fd91e0ffb","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.7373737373737373","value":"73.73737373737373","display":"73.7%"}},"20006":{"result_key":"2e926458246f9272be4573f6784fc60a46319cf84210498324f025abdaf4e938","exact_result_href":"/benchmarks/automationbench/1-0-6?view=history&result=2e926458246f9272be4573f6784fc60a46319cf84210498324f025abdaf4e938","benchmark":{"name":"AutomationBench","slug":"automationbench","aliases":[]},"benchmark_version":"1.0.6","benchmark_version_slug":"1-0-6","reasoning_level":null,"score":{"raw":"0.46%","value":"0.46","display":"0.5%"}},"20007":{"result_key":"dfbfafdae0a03fb078f7071bf0d039abeade44639a4224007c60d0a7ab72465a","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=dfbfafdae0a03fb078f7071bf0d039abeade44639a4224007c60d0a7ab72465a","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.8068181818181818","value":"80.68181818181818","display":"80.7%"}},"20008":{"result_key":"5c347cd9af924256905d0beb15aac959194e15ac836bb7d09f03a8adff0953fa","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=5c347cd9af924256905d0beb15aac959194e15ac836bb7d09f03a8adff0953fa","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"46.3%","value":"46.3","display":"46.3%"}},"20009":{"result_key":"a414b0ee6a953cec6a5d44b4c330e83a01c5cba5a47f9abc4c8808e9138c5fae","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=a414b0ee6a953cec6a5d44b4c330e83a01c5cba5a47f9abc4c8808e9138c5fae","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"43%","value":"43","display":"43.0%"}},"20010":{"result_key":"359a11046d2d4503572025c18a9989224fa3614080f9fb7df3a7098f0a08ecf6","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=359a11046d2d4503572025c18a9989224fa3614080f9fb7df3a7098f0a08ecf6","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"49.2%","value":"49.2","display":"49.2%"}},"20011":{"result_key":"46f96d4df916b76aab6a034f4dc395c078e959afdab08421a4c8bcfea741274a","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=46f96d4df916b76aab6a034f4dc395c078e959afdab08421a4c8bcfea741274a","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"48.9%","value":"48.9","display":"48.9%"}},"20012":{"result_key":"afffdc944ba4b1a3f32cb616f6e6de5e6c22a44c542726055de335bdb6c73de2","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=afffdc944ba4b1a3f32cb616f6e6de5e6c22a44c542726055de335bdb6c73de2","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"63.6%","value":"63.6","display":"63.6%"}},"20013":{"result_key":"219f8197d662af80885f42c3df3e5cc8cdd70710671b7e7f7cac016f44f592b7","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=219f8197d662af80885f42c3df3e5cc8cdd70710671b7e7f7cac016f44f592b7","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"54.5%","value":"54.5","display":"54.5%"}},"20014":{"result_key":"74b076c210e879bcfaa78eff82aeb64af676b1a7569bb5338647b0a9bbea8815","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=74b076c210e879bcfaa78eff82aeb64af676b1a7569bb5338647b0a9bbea8815","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"65.8%","value":"65.8","display":"65.8%"}},"20015":{"result_key":"93540249c842aaeba171afb87a5fbe9dbc424fa4d5d7013335c9f099cb4cb572","exact_result_href":null,"benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"73.5%","value":"73.5","display":"73.5%"}},"20016":{"result_key":"dc044df80e3c6459d32765389b3c8d20577d3bca17a38c5bde080a3a4df49816","exact_result_href":null,"benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"75.5%","value":"75.5","display":"75.5%"}},"20017":{"result_key":"81b2695afbea140f81e8bb3860e123ee73c39d7a4c5ae09f83315f6863fa6213","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=81b2695afbea140f81e8bb3860e123ee73c39d7a4c5ae09f83315f6863fa6213","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.7323232323232324","value":"73.23232323232324","display":"73.2%"}},"20018":{"result_key":"52f0d40d1f3690e84f38bed430bdd74f966db54e3dcade50e35fd3c2800817a1","exact_result_href":null,"benchmark":{"name":"CursorBench","slug":"cursorbench","aliases":[]},"benchmark_version":"4.0","benchmark_version_slug":"4-0","reasoning_level":"high","score":{"raw":"42.3%","value":"42.3","display":"42.3%"}},"30001":{"result_key":"0ef155d9e46b00f9e3cf2642655e5f3bed12648320819a750f8303d000d7b98e","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=0ef155d9e46b00f9e3cf2642655e5f3bed12648320819a750f8303d000d7b98e","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.6414141414141414","value":"64.14141414141414","display":"64.1%"}},"30002":{"result_key":"e0a838dd30b259ef5d5e9c375d6ec18d33968bcd24795b5e358cd7af52631cc7","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=e0a838dd30b259ef5d5e9c375d6ec18d33968bcd24795b5e358cd7af52631cc7","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.8383838383838383","value":"83.83838383838383","display":"83.8%"}},"30003":{"result_key":"7412041edf191597bdc523fcf59849e3374f92cba56dfe1b96422f8842b978f3","exact_result_href":"/benchmarks/humanitys-last-exam/text-only-scale-ai?view=history&result=7412041edf191597bdc523fcf59849e3374f92cba56dfe1b96422f8842b978f3","benchmark":{"name":"Humanity's Last Exam","slug":"humanitys-last-exam","aliases":["HLE"]},"benchmark_version":"Text only — Scale AI evaluation","benchmark_version_slug":"text-only-scale-ai","reasoning_level":null,"score":{"raw":"12.58","value":"12.58","display":"12.6%"}},"30004":{"result_key":"8320903fb691741970ccdee6f9b96b895586e0867d5842fdbd6e3e5683bd0ed2","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=8320903fb691741970ccdee6f9b96b895586e0867d5842fdbd6e3e5683bd0ed2","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"64.3%","value":"64.3","display":"64.3%"}},"30005":{"result_key":"40ad969ce0ee620a4d765d77082ffe5006e9f8b1cd3809d1b0e86639f94784e3","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=40ad969ce0ee620a4d765d77082ffe5006e9f8b1cd3809d1b0e86639f94784e3","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"35.3%","value":"35.3","display":"35.3%"}},"30006":{"result_key":"7cc3e51b1e0b45f637291621d870b84b45a91d9c360e751753f028fa6b11f51a","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=7cc3e51b1e0b45f637291621d870b84b45a91d9c360e751753f028fa6b11f51a","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"27.5%","value":"27.5","display":"27.5%"}},"30007":{"result_key":"3cb3cda9c0e9dde152276e43d87afffcdc19738b2de31aeeb5c3ce7df76eaf21","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=3cb3cda9c0e9dde152276e43d87afffcdc19738b2de31aeeb5c3ce7df76eaf21","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"46.9%","value":"46.9","display":"46.9%"}},"30008":{"result_key":"b15b59f4ce22c1154e1ec777be89ad8710b4b9068e4a3c800f0e5b7e42dfba6b","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=b15b59f4ce22c1154e1ec777be89ad8710b4b9068e4a3c800f0e5b7e42dfba6b","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.9261363636363636","value":"92.61363636363636","display":"92.6%"}},"30009":{"result_key":"7264f858b59e739f35451be1e81fa1edbf77ac918d732d6b945827407a60437c","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.8320707070707071","value":"83.20707070707071","display":"83.2%"}},"30010":{"result_key":"bffb7a6afb712e5fc0102105da2680ffd093325feda35bbb068cbf2df2353754","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=bffb7a6afb712e5fc0102105da2680ffd093325feda35bbb068cbf2df2353754","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"67.8%","value":"67.8","display":"67.8%"}},"30011":{"result_key":"710bea77c9c105cd4bf505cba294ffd06ba40c1214f3288348067a8a0664a548","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=710bea77c9c105cd4bf505cba294ffd06ba40c1214f3288348067a8a0664a548","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"82.4%","value":"82.4","display":"82.4%"}},"35001":{"result_key":"72e08f914521ee1aa4e5f6fdbe57b86ae56177361b8c302e74026e7bb77a690e","exact_result_href":"/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=72e08f914521ee1aa4e5f6fdbe57b86ae56177361b8c302e74026e7bb77a690e","benchmark":{"name":"BIG-Bench Extra Hard","slug":"big-bench-extra-hard","aliases":[]},"benchmark_version":"Original — micro average","benchmark_version_slug":"original-micro-average","reasoning_level":"thinking mode","score":{"raw":"64.8%","value":"64.8","display":"64.8%"}},"35002":{"result_key":"68467512be92e719a119c05773ac6dd794a4d3ac9275933df6cef3e215c138c7","exact_result_href":"/benchmarks/automationbench/1-0-6?view=history&result=68467512be92e719a119c05773ac6dd794a4d3ac9275933df6cef3e215c138c7","benchmark":{"name":"AutomationBench","slug":"automationbench","aliases":[]},"benchmark_version":"1.0.6","benchmark_version_slug":"1-0-6","reasoning_level":"max","score":{"raw":"1.7%","value":"1.7","display":"1.7%"}},"35003":{"result_key":"35e16878fd44f78f8307a611b4a1f77476e8843887b9acc7d1c87ea9bd3ad645","exact_result_href":"/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=35e16878fd44f78f8307a611b4a1f77476e8843887b9acc7d1c87ea9bd3ad645","benchmark":{"name":"BIG-Bench Extra Hard","slug":"big-bench-extra-hard","aliases":[]},"benchmark_version":"Original — micro average","benchmark_version_slug":"original-micro-average","reasoning_level":"thinking mode","score":{"raw":"21.9%","value":"21.9","display":"21.9%"}},"35004":{"result_key":"d2b97589860071506457aaa315c61b73d2780b8a67fac55c3371a0eb310d909d","exact_result_href":"/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=d2b97589860071506457aaa315c61b73d2780b8a67fac55c3371a0eb310d909d","benchmark":{"name":"BIG-Bench Extra Hard","slug":"big-bench-extra-hard","aliases":[]},"benchmark_version":"Original — micro average","benchmark_version_slug":"original-micro-average","reasoning_level":"thinking mode","score":{"raw":"33.1%","value":"33.1","display":"33.1%"}},"35005":{"result_key":"a03e35322783f9ed3ecdb5781501f8f9ec19e0644fb16a2b558c9130c582274b","exact_result_href":"/benchmarks/big-bench-extra-hard/original-micro-average?view=history&result=a03e35322783f9ed3ecdb5781501f8f9ec19e0644fb16a2b558c9130c582274b","benchmark":{"name":"BIG-Bench Extra Hard","slug":"big-bench-extra-hard","aliases":[]},"benchmark_version":"Original — micro average","benchmark_version_slug":"original-micro-average","reasoning_level":"thinking mode","score":{"raw":"53.0%","value":"53","display":"53.0%"}},"40001":{"result_key":"04d38d89864dc95565771c3257508dde9baacb7ecd9328e13812cd65d87da78e","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=04d38d89864dc95565771c3257508dde9baacb7ecd9328e13812cd65d87da78e","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"56.2%","value":"56.2","display":"56.2%"}},"40002":{"result_key":"bd730474d0883baf1f1de83f3ebcbcf17dffe7e9ce6ea7e584cf3ff5cf029f70","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=bd730474d0883baf1f1de83f3ebcbcf17dffe7e9ce6ea7e584cf3ff5cf029f70","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"xhigh","score":{"raw":"65.3%","value":"65.3","display":"65.3%"}},"40003":{"result_key":"e63a900403fc378e8f0b245bc0a2fd04cec179a2c540459d5634f523a981cb46","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=e63a900403fc378e8f0b245bc0a2fd04cec179a2c540459d5634f523a981cb46","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"xhigh","score":{"raw":"54.6%","value":"54.6","display":"54.6%"}},"40004":{"result_key":"7f0dc077557e1dfb38862f834e174a2d608194b1ef4fee7df7bbeae65b1e6f07","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=7f0dc077557e1dfb38862f834e174a2d608194b1ef4fee7df7bbeae65b1e6f07","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.87","value":"87","display":"87.0%"}},"50001":{"result_key":"092ffebb8d27ecff84e5d8181d7eac44ed5e9ca6bfd5daf5cf38ddeb35587348","exact_result_href":"/benchmarks/cursorbench/3.0?view=history&result=092ffebb8d27ecff84e5d8181d7eac44ed5e9ca6bfd5daf5cf38ddeb35587348","benchmark":{"name":"CursorBench","slug":"cursorbench","aliases":[]},"benchmark_version":"3.0","benchmark_version_slug":"3.0","reasoning_level":null,"score":{"raw":"38.0","value":"38","display":"38.0%"}},"50002":{"result_key":"cebc672dd52863198dd99ee2e38627df5d04f75f52e419cabd9621a5adfdbc80","exact_result_href":"/benchmarks/cursorbench/3.0?view=history&result=cebc672dd52863198dd99ee2e38627df5d04f75f52e419cabd9621a5adfdbc80","benchmark":{"name":"CursorBench","slug":"cursorbench","aliases":[]},"benchmark_version":"3.0","benchmark_version_slug":"3.0","reasoning_level":null,"score":{"raw":"44.2","value":"44.2","display":"44.2%"}},"50003":{"result_key":"41d72aecb1d78318b9652ceb09c04dbd5ea5bbe914904dea9fc2dd7e4d301a8a","exact_result_href":"/benchmarks/cursorbench/3.0?view=history&result=41d72aecb1d78318b9652ceb09c04dbd5ea5bbe914904dea9fc2dd7e4d301a8a","benchmark":{"name":"CursorBench","slug":"cursorbench","aliases":[]},"benchmark_version":"3.0","benchmark_version_slug":"3.0","reasoning_level":null,"score":{"raw":"61.3","value":"61.3","display":"61.3%"}},"50004":{"result_key":"3436a4366b940063b4fd95b2687c34631e2b15b560b9fe2d618442261e8e8752","exact_result_href":"/benchmarks/vibe-code-bench/1.1-cursor-cli-october-2026?view=history&result=3436a4366b940063b4fd95b2687c34631e2b15b560b9fe2d618442261e8e8752","benchmark":{"name":"Vibe Code Bench","slug":"vibe-code-bench","aliases":[]},"benchmark_version":"1.1 — Cursor CLI, October 2026 evaluation","benchmark_version_slug":"1.1-cursor-cli-october-2026","reasoning_level":null,"score":{"raw":"49.614","value":"49.614","display":"49.6%"}},"60001":{"result_key":"b302e33d290c162e41cb07e5b6431b794f04fc4c8f6e37b487262874bde7f59a","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond","benchmark_version_slug":"diamond","reasoning_level":"no-tools","score":{"raw":"73.0","value":"73","display":"73.0%"}},"60002":{"result_key":"4478fb160678286d296a6c2c5cd06df8088f90324cdcd69d0e00b8d6eb403643","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond","benchmark_version_slug":"diamond","reasoning_level":"no-tools","score":{"raw":"79.23","value":"79.23","display":"79.2%"}},"60003":{"result_key":"ff378e02e9833a0d302039f255cca5b6c8bb8b5e83a4ac36916476f0b8734fd0","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=ff378e02e9833a0d302039f255cca5b6c8bb8b5e83a4ac36916476f0b8734fd0","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"22.7%","value":"22.7","display":"22.7%"}},"70001":{"result_key":"388329803e62872d8e698ab6c54d71ea67eca5049c385f656ab4e212605d6181","exact_result_href":"/benchmarks/ai2d/test?view=history&result=388329803e62872d8e698ab6c54d71ea67eca5049c385f656ab4e212605d6181","benchmark":{"name":"AI2D","slug":"ai2d","aliases":[]},"benchmark_version":"TEST","benchmark_version_slug":"test","reasoning_level":"automatic think/nothink","score":{"raw":"84.8","value":"84.8","display":"84.8%"}},"70002":{"result_key":"a128e6abe943629f6e0ba1d5465006e8fd78ff30de1b41879a4128e393ad6265","exact_result_href":"/benchmarks/gpqa/diamond?view=history&result=a128e6abe943629f6e0ba1d5465006e8fd78ff30de1b41879a4128e393ad6265","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond","benchmark_version_slug":"diamond","reasoning_level":null,"score":{"raw":"84.6","value":"84.6","display":"84.6%"}},"70003":{"result_key":"76d6bf1df52bf5baac1c2056138bdcceb6c475a8e21fac6432a4d4e8dd1377bf","exact_result_href":"/benchmarks/riemann-bench/october-2026?view=history&result=76d6bf1df52bf5baac1c2056138bdcceb6c475a8e21fac6432a4d4e8dd1377bf","benchmark":{"name":"Riemann-bench","slug":"riemann-bench","aliases":["RiemannBench"]},"benchmark_version":"October 2026 leaderboard","benchmark_version_slug":"october-2026","reasoning_level":null,"score":{"raw":"4.8%","value":"4.8","display":"4.8%"}},"80001":{"result_key":"60cd560ef8584fb1714ce0cab025412ed643a64684ec27bf27f418e759013a19","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=60cd560ef8584fb1714ce0cab025412ed643a64684ec27bf27f418e759013a19","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.898","value":"89.8","display":"89.8%"}},"80002":{"result_key":"bf2c0549f2f77472deaafb89be6c9e1008d1af03bf7d3a9368521db5b2d8a285","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=bf2c0549f2f77472deaafb89be6c9e1008d1af03bf7d3a9368521db5b2d8a285","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"xhigh","score":{"raw":"31.8%","value":"31.8","display":"31.8%"}},"80003":{"result_key":"90a329cbb01ef23f737f60ceae66f767caf09c16170ca78c3a6745e72839a62c","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=90a329cbb01ef23f737f60ceae66f767caf09c16170ca78c3a6745e72839a62c","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"xhigh","score":{"raw":"36.4%","value":"36.4","display":"36.4%"}},"80004":{"result_key":"eb6f0af9b733fe5e4adbc79583c1f2c2a80cefd8d4b4166e119e319fe1aa5df7","exact_result_href":"/benchmarks/chartography/october-2026?view=history&result=eb6f0af9b733fe5e4adbc79583c1f2c2a80cefd8d4b4166e119e319fe1aa5df7","benchmark":{"name":"Chartography","slug":"chartography","aliases":[]},"benchmark_version":"October 2026 leaderboard","benchmark_version_slug":"october-2026","reasoning_level":"xHigh","score":{"raw":"17.2%","value":"17.2","display":"17.2%"}},"80005":{"result_key":"41e5a07303d71f68a32ac15e99acdb7dd513a69adf62427440c1eedeec65a6af","exact_result_href":null,"benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"47.6%","value":"47.6","display":"47.6%"}},"90001":{"result_key":"cb55934f352466ead552678aedc3fb65c115e01ba405c6d8f388e79890b3e0f6","exact_result_href":"/benchmarks/chartography/october-2026?view=history&result=cb55934f352466ead552678aedc3fb65c115e01ba405c6d8f388e79890b3e0f6","benchmark":{"name":"Chartography","slug":"chartography","aliases":[]},"benchmark_version":"October 2026 leaderboard","benchmark_version_slug":"october-2026","reasoning_level":null,"score":{"raw":"9%","value":"9","display":"9.0%"}},"90002":{"result_key":"b5889e5dd4a2c88490cea8711f510d3caeea0c1f4162fbc9a196f6f265c5bd45","exact_result_href":"/benchmarks/swe-bench/verified-vals-ai-mini-swe-agent?view=history&result=b5889e5dd4a2c88490cea8711f510d3caeea0c1f4162fbc9a196f6f265c5bd45","benchmark":{"name":"SWE-bench","slug":"swe-bench","aliases":[]},"benchmark_version":"Verified — Vals AI mini-swe-agent","benchmark_version_slug":"verified-vals-ai-mini-swe-agent","reasoning_level":null,"score":{"raw":"62.8","value":"62.8","display":"62.8%"}},"90003":{"result_key":"477a6430e83f17837f3083ad885a2dd6c97ffcf9a75cb471652a083617717d24","exact_result_href":"/benchmarks/swe-bench/multilingual?view=history&result=477a6430e83f17837f3083ad885a2dd6c97ffcf9a75cb471652a083617717d24","benchmark":{"name":"SWE-bench","slug":"swe-bench","aliases":[]},"benchmark_version":"Multilingual","benchmark_version_slug":"multilingual","reasoning_level":null,"score":{"raw":"55.7%","value":"55.7","display":"55.7%"}},"90004":{"result_key":"88444d0f1ad270f38401ed61ddb4d102039d3612ef50aa73b9ec2d36dac07188","exact_result_href":"/benchmarks/vibe-code-bench/1.1-openhands-october-2026?view=history&result=88444d0f1ad270f38401ed61ddb4d102039d3612ef50aa73b9ec2d36dac07188","benchmark":{"name":"Vibe Code Bench","slug":"vibe-code-bench","aliases":[]},"benchmark_version":"1.1 — OpenHands, October 2026 evaluation","benchmark_version_slug":"1.1-openhands-october-2026","reasoning_level":"high","score":{"raw":"0.0","value":"0","display":"0.0%"}},"90005":{"result_key":"69eb15f1655d27c5aae65f3da8434e195a176cebdfa0bc59bb77dbe5f9b53849","exact_result_href":"/benchmarks/finance-agent/2-october-2026?view=history&result=69eb15f1655d27c5aae65f3da8434e195a176cebdfa0bc59bb77dbe5f9b53849","benchmark":{"name":"Finance Agent Benchmark","slug":"finance-agent","aliases":["Vals Finance Agent"]},"benchmark_version":"2 — October 2026 evaluation","benchmark_version_slug":"2-october-2026","reasoning_level":"high","score":{"raw":"32.103","value":"32.103","display":"32.1%"}},"110001":{"result_key":"9b353668d44451d691dcdff686195cdf3ee07fdde8edd905b8b6ab7f4021725b","exact_result_href":"/benchmarks/automationbench/1-0-6?view=history&result=9b353668d44451d691dcdff686195cdf3ee07fdde8edd905b8b6ab7f4021725b","benchmark":{"name":"AutomationBench","slug":"automationbench","aliases":[]},"benchmark_version":"1.0.6","benchmark_version_slug":"1-0-6","reasoning_level":"max","score":{"raw":"18.11%","value":"18.11","display":"18.1%"}},"110002":{"result_key":"d3ee644101a061f8525e19e6ed4d2fde501ae2c8877efd49b262b4c939df8b83","exact_result_href":"/benchmarks/browsecomp/130-question-subset-mercor?view=history&result=d3ee644101a061f8525e19e6ed4d2fde501ae2c8877efd49b262b4c939df8b83","benchmark":{"name":"BrowseComp","slug":"browsecomp","aliases":[]},"benchmark_version":"130-question subset — Mercor web research agent","benchmark_version_slug":"130-question-subset-mercor","reasoning_level":"max","score":{"raw":"62.3%","value":"62.3","display":"62.3%"}},"110003":{"result_key":"c4864d4e5ae6efd322d3dd01bbf9d4646c8b0645b26f58b7c9bd15709c93d00b","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=c4864d4e5ae6efd322d3dd01bbf9d4646c8b0645b26f58b7c9bd15709c93d00b","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":null,"score":{"raw":"21.3%","value":"21.3","display":"21.3%"}},"120001":{"result_key":"13246de8447303b79a0a6b0a51fbe8664c9ffaba6982c74ddc091073823118e3","exact_result_href":"/benchmarks/chartography/october-2026?view=history&result=13246de8447303b79a0a6b0a51fbe8664c9ffaba6982c74ddc091073823118e3","benchmark":{"name":"Chartography","slug":"chartography","aliases":[]},"benchmark_version":"October 2026 leaderboard","benchmark_version_slug":"october-2026","reasoning_level":"Thinking on","score":{"raw":"12.6%","value":"12.6","display":"12.6%"}},"120002":{"result_key":"279ef0c629660a745605a1692750b57c25861b66afcd6cec0bc523d304e3eb0f","exact_result_href":"/benchmarks/automationbench/1-0-6?view=history&result=279ef0c629660a745605a1692750b57c25861b66afcd6cec0bc523d304e3eb0f","benchmark":{"name":"AutomationBench","slug":"automationbench","aliases":[]},"benchmark_version":"1.0.6","benchmark_version_slug":"1-0-6","reasoning_level":null,"score":{"raw":"2.59%","value":"2.59","display":"2.6%"}},"120003":{"result_key":"51d56ce37dca45223e976c81698f2ba19480a84e57848019ec81aa2f0d4b25a5","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=51d56ce37dca45223e976c81698f2ba19480a84e57848019ec81aa2f0d4b25a5","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"50.6%","value":"50.6","display":"50.6%"}},"130001":{"result_key":"360e12d23f1aa69e39b3b7db5ea5e3a4115fda7893342a558f7c55e0745dd56e","exact_result_href":"/benchmarks/swe-bench/verified?view=history&result=360e12d23f1aa69e39b3b7db5ea5e3a4115fda7893342a558f7c55e0745dd56e","benchmark":{"name":"SWE-bench","slug":"swe-bench","aliases":[]},"benchmark_version":"Verified","benchmark_version_slug":"verified","reasoning_level":null,"score":{"raw":"69.6","value":"69.6","display":"69.6%"}},"130002":{"result_key":"40171be0641e1ed239241977f90f3a7c121be2162c23e6079ca4a2617d371b0f","exact_result_href":"/benchmarks/gpqa/diamond-vals-ai?view=history&result=40171be0641e1ed239241977f90f3a7c121be2162c23e6079ca4a2617d371b0f","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Vals AI harness","benchmark_version_slug":"diamond-vals-ai","reasoning_level":null,"score":{"raw":"84.848","value":"84.848","display":"84.8%"}},"130003":{"result_key":"9e79137d80c4be372ac2632dccd784afb355c10e1c7dde1be283725cd0ab99aa","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=9e79137d80c4be372ac2632dccd784afb355c10e1c7dde1be283725cd0ab99aa","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":null,"score":{"raw":"24.9%","value":"24.9","display":"24.9%"}},"130004":{"result_key":"3b8e5eb21f709ba80eb191c68e519c01dcd59ad3dd9f18831931e8fa9555acdd","exact_result_href":"/benchmarks/automationbench/1-0-6?view=history&result=3b8e5eb21f709ba80eb191c68e519c01dcd59ad3dd9f18831931e8fa9555acdd","benchmark":{"name":"AutomationBench","slug":"automationbench","aliases":[]},"benchmark_version":"1.0.6","benchmark_version_slug":"1-0-6","reasoning_level":"high","score":{"raw":"4.3%","value":"4.3","display":"4.3%"}},"130005":{"result_key":"abbb7440f0a0d9674578c0c8fdd863b4f4ec4d201545d74bf0f8aaf63e7abc8d","exact_result_href":null,"benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.8383838383838383","value":"83.83838383838383","display":"83.8%"}},"130006":{"result_key":"1b8d685ec179d808612956a1ff9ac3facb557878c6bab1728081da89a5058a72","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=1b8d685ec179d808612956a1ff9ac3facb557878c6bab1728081da89a5058a72","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.9090909090909091","value":"90.90909090909091","display":"90.9%"}},"130007":{"result_key":"930b78caeed0591a0a6bc2c004131482f6f2dddcd8b595fac9174acc84726969","exact_result_href":"/benchmarks/automationbench/1-0-6?view=history&result=930b78caeed0591a0a6bc2c004131482f6f2dddcd8b595fac9174acc84726969","benchmark":{"name":"AutomationBench","slug":"automationbench","aliases":[]},"benchmark_version":"1.0.6","benchmark_version_slug":"1-0-6","reasoning_level":null,"score":{"raw":"3.7%","value":"3.7","display":"3.7%"}},"130008":{"result_key":"ec624118cf3bdc781436e3d761a63fe732d907801baa889f3ecb9a19a5a8afe8","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=ec624118cf3bdc781436e3d761a63fe732d907801baa889f3ecb9a19a5a8afe8","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"xhigh","score":{"raw":"63.3%","value":"63.3","display":"63.3%"}},"140001":{"result_key":"9246711262de7b8bf7c0be5875d438025560e7663cbed34ac09b49237c983bdc","exact_result_href":"/benchmarks/swe-atlas/codebase-qna-public-mini-swe-agent?view=history&result=9246711262de7b8bf7c0be5875d438025560e7663cbed34ac09b49237c983bdc","benchmark":{"name":"SWE Atlas","slug":"swe-atlas","aliases":[]},"benchmark_version":"Codebase QnA — Public; mini-swe-agent","benchmark_version_slug":"codebase-qna-public-mini-swe-agent","reasoning_level":null,"score":{"raw":"10.3","value":"10.3","display":"10.3%"}},"140002":{"result_key":"f305499563e05a61efa7a1787531dc5b2136c4e8837addb293b1f7e216abe8c2","exact_result_href":"/benchmarks/automationbench/1-0-6?view=history&result=f305499563e05a61efa7a1787531dc5b2136c4e8837addb293b1f7e216abe8c2","benchmark":{"name":"AutomationBench","slug":"automationbench","aliases":[]},"benchmark_version":"1.0.6","benchmark_version_slug":"1-0-6","reasoning_level":"high","score":{"raw":"0.46%","value":"0.46","display":"0.5%"}},"140003":{"result_key":"30e9b9bcbaa2a299039f8ed9e00d2033212ddc40ac0a3c781f6d0f0f333592a9","exact_result_href":null,"benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"37.7%","value":"37.7","display":"37.7%"}},"140004":{"result_key":"c8648734843eb9d2084acf5cd4935b09b97fd67a8d9dbf8d5b6c83304bc7a11a","exact_result_href":"/benchmarks/swe-bench/verified-mini-swe-agent?view=history&result=c8648734843eb9d2084acf5cd4935b09b97fd67a8d9dbf8d5b6c83304bc7a11a","benchmark":{"name":"SWE-bench","slug":"swe-bench","aliases":[]},"benchmark_version":"Verified — mini-swe-agent","benchmark_version_slug":"verified-mini-swe-agent","reasoning_level":null,"score":{"raw":"61.0","value":"61","display":"61.0%"}},"150001":{"result_key":"6ad676996df5218d746a77d846fbffced2e01979c6c93d371af2bc8f9e3f72bc","exact_result_href":"/benchmarks/gpqa/diamond-epoch-ai?view=history&result=6ad676996df5218d746a77d846fbffced2e01979c6c93d371af2bc8f9e3f72bc","benchmark":{"name":"Graduate-Level Google-Proof Q&A","slug":"gpqa","aliases":["GPQA"]},"benchmark_version":"Diamond — Epoch AI harness","benchmark_version_slug":"diamond-epoch-ai","reasoning_level":null,"score":{"raw":"0.8333333333333334","value":"83.33333333333334","display":"83.3%"}},"150002":{"result_key":"65b7f96937c48e2ef57f3eda0b2f2056c717d60dbe1ea680e9e731edfcb4d59d","exact_result_href":"/benchmarks/deep-swe/1.1-mercor-mini-swe-agent?view=history&result=65b7f96937c48e2ef57f3eda0b2f2056c717d60dbe1ea680e9e731edfcb4d59d","benchmark":{"name":"DeepSWE","slug":"deep-swe","aliases":[]},"benchmark_version":"1.1 — Mercor mini-swe-agent, 500 steps","benchmark_version_slug":"1.1-mercor-mini-swe-agent","reasoning_level":null,"score":{"raw":"2.1%","value":"2.1","display":"2.1%"}},"150003":{"result_key":"3bcd2c8c696b3a9f80985f24a46de904db56e0545d5ee1b6dc69978a18792fd1","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=3bcd2c8c696b3a9f80985f24a46de904db56e0545d5ee1b6dc69978a18792fd1","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":null,"score":{"raw":"40.9%","value":"40.9","display":"40.9%"}},"150004":{"result_key":"b965d0437b2c4b546dedac25adedc160edff869c016d74b841241be58cad6d3f","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=b965d0437b2c4b546dedac25adedc160edff869c016d74b841241be58cad6d3f","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"45.2%","value":"45.2","display":"45.2%"}},"150005":{"result_key":"048f793a3786ed20bd964660dfe2fea56aa0b2e180479b2337e84eebf2bf0359","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=048f793a3786ed20bd964660dfe2fea56aa0b2e180479b2337e84eebf2bf0359","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"56.6%","value":"56.6","display":"56.6%"}},"150006":{"result_key":"dd59b67ea76680dfe9df4164a4ffc077cb20de6f57968aa7dd307030f7e57f36","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=dd59b67ea76680dfe9df4164a4ffc077cb20de6f57968aa7dd307030f7e57f36","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"max","score":{"raw":"52.8%","value":"52.8","display":"52.8%"}},"150007":{"result_key":"7e8754366359481642fa4ad15e494558d87859111187c289c6aa0a1fd9567569","exact_result_href":"/benchmarks/humanitys-last-exam/text-only-scale-ai?view=history&result=7e8754366359481642fa4ad15e494558d87859111187c289c6aa0a1fd9567569","benchmark":{"name":"Humanity's Last Exam","slug":"humanitys-last-exam","aliases":["HLE"]},"benchmark_version":"Text only — Scale AI evaluation","benchmark_version_slug":"text-only-scale-ai","reasoning_level":null,"score":{"raw":"9.64","value":"9.64","display":"9.6%"}},"150008":{"result_key":"09630ee3dbad41e52305e7928c675728f26cca6a6f40d134621b585f930ad419","exact_result_href":"/benchmarks/humanitys-last-exam/text-only-scale-ai?view=history&result=09630ee3dbad41e52305e7928c675728f26cca6a6f40d134621b585f930ad419","benchmark":{"name":"Humanity's Last Exam","slug":"humanitys-last-exam","aliases":["HLE"]},"benchmark_version":"Text only — Scale AI evaluation","benchmark_version_slug":"text-only-scale-ai","reasoning_level":null,"score":{"raw":"9.41","value":"9.41","display":"9.4%"}},"150009":{"result_key":"97ec2b4d352859867a401908d15c341a1b8fb0d199972411a6a1bea8d84597b6","exact_result_href":"/benchmarks/swe-bench-pro/public-scale-ai-swe-agent?view=history&result=97ec2b4d352859867a401908d15c341a1b8fb0d199972411a6a1bea8d84597b6","benchmark":{"name":"SWE-bench Pro","slug":"swe-bench-pro","aliases":[]},"benchmark_version":"Public — Scale AI SWE-Agent","benchmark_version_slug":"public-scale-ai-swe-agent","reasoning_level":null,"score":{"raw":"9.67","value":"9.67","display":"9.7%"}},"160001":{"result_key":"f8410a1c0f29d94eca07356f294e20bb6c09a3330ff71b1e8faef78b49db815f","exact_result_href":"/benchmarks/apex-agents/original?view=history&result=f8410a1c0f29d94eca07356f294e20bb6c09a3330ff71b1e8faef78b49db815f","benchmark":{"name":"APEX-Agents","slug":"apex-agents","aliases":[]},"benchmark_version":"Original","benchmark_version_slug":"original","reasoning_level":"high","score":{"raw":"33.8%","value":"33.8","display":"33.8%"}},"160002":{"result_key":"6a3937336e5e62e6436bdd601c9f7428d682e75ff84d7b9ae0d746ffe14ef737","exact_result_href":"/benchmarks/chartography/october-2026?view=history&result=6a3937336e5e62e6436bdd601c9f7428d682e75ff84d7b9ae0d746ffe14ef737","benchmark":{"name":"Chartography","slug":"chartography","aliases":[]},"benchmark_version":"October 2026 leaderboard","benchmark_version_slug":"october-2026","reasoning_level":"xHigh","score":{"raw":"9.1%","value":"9.1","display":"9.1%"}}}}