{"version":"configuration-source-6","evidencePolicy":"documented","snapshotId":"sha256-e384eba3603ee0338d26052e22db513e17d16719d2af7d2444a3f89e18cd1b99","effortDatasetId":"sha256-49305f3d640f7387a764d95d62f10bbce44aeff4a4012ddba973eddf1e57a707+sha256-443256461e035ccdee585c01fdbd68b4b26545d45e2bd6b2bd93e1e913a2d41a+sha256-32c6374f8a0cdb9cd64f17244f1a697dd35d31cff071002599f3e1226d1e027d+sha256-9b7bfe52f0cba33df0362a330cb12551ea2f5853bf843931b08dad98e5d8d15c+sha256-c4f243913106bee769c57849d3cb4662fee3097206d30d3c8d4d37d687f8e556+sha256-c6f9cb8b67b4289e79e621b65d529e5f57eee55d89d86915f397859092051dad+sha256-78cb5ce46bffe96a698a9a7117551eafb90b2c3d05066722f4a703be2680aa55+sha256-e34a2de55476481fa69ea734e4027620fbc14df27f896c3bcec6c07275b0da42","scope":"All collected observations, not a claim that every public result has been collected. Contributing means positive graph weight, not sufficient evidence for a rank.","models":[{"id":"gpt-6-luna","collected":192,"contributing":129,"admittedWithoutWeight":0,"excluded":63}],"observations":[{"id":"85cdbce7a287aedba059fbef","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6df099fcab3bc59df1a2848e","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e7bd695aa23bf06ff18d157","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecbc90fb7fe042e052ba1753","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07b2e07748cef846e9f0817f","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46d79399ee441894914a8f1a","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a82437d9f707352e49c5dda","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4add5bece4540a198cb2a579","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57dcd7df3e4da472eeb09e87","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8bf4ee9e05436bbf3c463c3","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d8566afcdef04eb1769a040","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7616e33171a1a060a1c26c5b","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eccd70ba4b9cd043c9a657a0","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c9b637c2631b2c8a3972ddc","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"818ef24865c84783fc39375b","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fcd6b9de9db634e2c4a9844b","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d93d178aa6105b5644b1587","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c4dcbe13c8ef2ffadfe1e89","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90b73130e61aba8283ac4c32","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52976d5bd4fd450f6e70bb8f","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"414447fbe6d878f1a0a8f204","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ee05767675070ace8ff4a10","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39c58ccfce992c4098e15db3","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be3e5d200a8ef22d2e7d908b","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"842bda61fdf4a03695e85fc0","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35037581a38fca7108a8ff15","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f166779c35e15578e2d20011","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e76d489e380fde49262e3e7a","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed69ba3033796ee33cfbba7f","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bdc20c361b224dd8d5ac840","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7e2e92d7df76f060438837a","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f9610d53f3227c80d1acc510","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1fc182b7287f42dad1a05465","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34f4c0efa1fd06fc30de9556","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e424a52bc46cd95f4a4008b3","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87b55df4b09954ea311ec452","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2324d8cba91fb427eed089e9","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c0b35ba0b0dea0d2ec65470","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dae9bf3e3d4b5670d3893f15","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16510b56f5d5fa75b2b71352","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86869e43d3ba2fd62a2efaa9","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f701423cfe5ba7df2b56aa37","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f20be376e35e699e68422716","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7fe3b1afa7a09cc26986c6c3","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d359d2dbc04c1e7574e2cf32","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92aeb221c4bb583e17bbc377","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69e7261a2f652eca41752cbc","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6daa4658a4816df33eb8a68","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22dc8988bd2fdbf4d396764a","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c5470194e5dd81e14991a33","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7970dfff3e9c437c790e082d","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"20e3ef7fbf64984566407e4e","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9ea2580ef691d710d9cc2dd5","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9f2ebaa525d1bf0a2dcd8fc9","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2f88e138bda31c9cfa8ab817","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"63298170bbb423389ae897e0","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f663cb94aed0c489b8cd081e","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2e7e07707092204b5dba5f48","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"235e213364000a65a590a20f","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97809e7f09d0767b3d0f6154","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b615d1750e6c87a9bf6f1db3","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"038cd005e04bbd9da5b2a39b","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd535b33980376b6b1b2cd33","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fa34aea17e35cf7ae3beeb9","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"2d547df4fe61b3c4b08abfc2","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"f4c807a7e3a01a657b5dca3d","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"12f4aaf84c8045b8e65eeaa1","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"7f3ec19d60fc54e1792d8e6a","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"d5d2b5f5d6082482db5e6acf","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"bad4886aa53b9782b1daf1f5","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminal-bench-science","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aae07df2a2545ea42cd10c66","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"59995116df23e68ce652da78","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e39763d3c72f894ba76fae2","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1accbba79c31b0f64fcc569","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae9cd41cfe460d23e2ba5708","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ce516f57cf7ad82a9643b56","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8d7dca0504bb948aeb158e3","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79c498606e7843c499358ae4","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4f0c67df2c799bb9967528e","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ddaf72bfd88bc1448399808c","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5849e34f56744250ee2ebc46","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-none","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"706ee66952f7ced5735443bf","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0181fe7a76a53fbd63e479e8","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"11e28af907b736a7ef5132e0","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12560fec6f79d44c90fd24c7","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a14e537a8a814fc2f9bc5d4","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33185b87fae17b44533c6d2f","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3c660a8ae862944a3486209b","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a70f6ffa3c870b89b0268d2","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-none","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bf518719461d570e3d4c0c6","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"71b1f4840ca9c0df3bc97975","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8078e6f76a0f6f0d4f6fd030","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"809502577a06f2501fb320bc","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"84d557cc7cf51b4c7f37d128","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87757bb60508b774963ad92d","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c5df9cae8b71015fb4ed7a5","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"968a6828c9b1cd6be6b406e5","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8e9f7152e70e6a96533cb76","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbfde4d573412eed7593e750","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e46aa5212aad528a859b9813","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecfb916e25d392c524f62e21","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8386742f94346ed03acace3","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-none","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa884927bb3db5f6e643e385","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fb309a77f991373cd200cb6f","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fb4c2a49491c2edb9bfecada","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-162244688f7fe4a357ea05af","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-130a9ddad8f163763bec2487","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b89337a7e3004fdcade93906","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d2a5a8202d5f6238cc578ece","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d3589d5cd927ea089932c917","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3909bf096095708a59780a61","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4c1f14f11ae12bd98a05bdf0","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a54e6a5bb487cd66b30504f9","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9a1afabb04048d30c0e13610","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1cc510640bb52a05cf58bcdd","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a9246dca57ff39f1de17943d","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eb0ce253202e2da98ce21572","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d074912e4b3edceef7ca746","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a2680a88d56e864a7c5930cf","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f8b05e805333b62ec847be0b","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c846f00e2443a2d618049b21","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-68616e51e7d88b4fb0f87fa9","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9beac39a82688739c9ddf636","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a13b21030b066f91d50782e5","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2c85953b28c28fb1b4a58458","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-05cb3f3d0fdc8582eb15db40","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-46a4ea2215cfd141be5cc823","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8a633eac0cf729f5cb0f32e4","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4uDz9b6SosxDSZf7swMD9D","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7F3QFMAkwnCV62HcvxP96q","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7n3HBUK684GmdT6Tkycu6m","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bAERV8wdmoHMLz2K4bZCSK","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-HX9sRVWJtZiNvneALnVzs8","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-iBQxysYR7zPxB6hxvJyTLc","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Jevnk9hi9oRBbGcFu2JxBC","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"vals-finance-agent-v2:openai/gpt-6-luna","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:openai/gpt-6-luna","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:openai/gpt-6-luna","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:openai/gpt-6-luna","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-6-luna","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-6-luna","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-tax-agent-bench-v1:openai/gpt-6-luna","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa-cyber-index-gpt-6-luna","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-cyber-index","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9a074a7174126349ffd8c560","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://surgehq.ai/benchmarks/dayjob-healthcare","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"a638443a7f29edaab94f9f5c","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://surgehq.ai/benchmarks/dayjob-finance","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"spireclimb-steambench-sts1-a20h-fc581bcaa7f17d12","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/spireclimb","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"spireclimb-steambench-sts2-a10-0e148062f8e47c4a","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/spireclimb","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"29ec421af5ec87c489812279","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://agents-last-exam.org/leaderboard","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"4e865ae63f79c95b4a197ebc","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://arena.ai/leaderboard/agent","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"0e78b9edbdbf167341a3174a","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://labs.scale.com/leaderboard/hss","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"launch-openai-gpt6-sol-luna-launch-2306","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2307","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2308","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2309","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2310","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2316","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2317","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2318","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2319","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2320","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2326","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2327","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2328","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2329","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2330","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2336","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2337","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2338","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2339","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2340","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2346","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-low","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2347","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-medium","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2348","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-high","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2349","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt6-sol-luna-launch-2350","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","status":"excluded","reason":"Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison."},{"id":"launch-openai-gpt61-sol-launch-2461","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://openai.com/index/introducing-gpt-6-1-sol/","status":"excluded","reason":"Safety failure behavior is not a capability or intelligence score."},{"id":"launch-openai-gpt61-sol-launch-2464","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://openai.com/index/introducing-gpt-6-1-sol/","status":"excluded","reason":"Safety failure behavior is not a capability or intelligence score."},{"id":"launch-openai-gpt61-sol-launch-2468","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-max","sourceUrl":"https://openai.com/index/introducing-gpt-6-1-sol/","status":"excluded","reason":"Safety failure behavior is not a capability or intelligence score."},{"id":"launch-openai-gpt61-sol-launch-2472","modelId":"gpt-6-luna","configurationId":"gpt-6-luna--effort-xhigh","sourceUrl":"https://openai.com/index/introducing-gpt-6-1-sol/","status":"excluded","reason":"Safety failure behavior is not a capability or intelligence score."},{"id":"s-aa-cyber-index-gpt-6-luna-max-5bad0b7a850c","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-cyber-index","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-ale-gpt-6-luna-codex-a80c8a081616","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://agents-last-exam.org/leaderboard","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-arc2-gpt-6-luna-cc6b7f594282","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-automationbench-gpt-6-luna-aeb8c17003ec","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-bughunt-gpt-6-luna-max-c55a0ce03665","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://bughunt.productcompass.pm/?preset=featured","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-bughunt-gpt-6-luna-xhigh-e9508044cc88","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://bughunt.productcompass.pm/?preset=featured","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-dayjob-dayjob-finance-gpt-6-luna-max-b39a42ab8742","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://surgehq.ai/benchmarks/dayjob-finance","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-dayjob-dayjob-healthcare-gpt-6-luna-max-b39a42ab8742","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://surgehq.ai/benchmarks/dayjob-healthcare","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-hss-gpt-6-luna-max-8bb7442ceaba","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://labs.scale.com/leaderboard/hss","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-lmarena-agent-gpt-6-luna-max-c750d8bd5563","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://arena.ai/leaderboard/agent","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-spireclimb-gpt-6-luna-spireclimb-sts1-a20h-9111cc1dde7a","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://epoch.ai/benchmarks/spireclimb","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-spireclimb-gpt-6-luna-spireclimb-sts2-a10-9111cc1dde7a","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://epoch.ai/benchmarks/spireclimb","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-tb40-gpt-6-luna-439f188e558c","modelId":"gpt-6-luna","configurationId":null,"sourceUrl":"https://www.tbench.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}