{"version":"configuration-source-5","evidencePolicy":"documented","snapshotId":"sha256-df858793dcb753b0f77beb223fce04e1de99a2c08f2c7b5f14534efcafa8c7c5","effortDatasetId":"sha256-1f186994047883a45f76e96fbce2f07320baf4f104506414be2bba69a334a02f+sha256-2bc644d4e2fb34bd4fecd1ef0a2a50302a9d18f3b8cd3aa0e6dfc487669f5146+sha256-b6d2e58f71798704ee9f3e6b341e3627e6b0dc1caef890fc1e08b62a226e3f36+sha256-7a7d95c40c608cc28483fb5cef9007da8c102f1e7278882ccbcc02a16078607d+sha256-99e5ccb2eac4abb63cc6d9823b591f2ffac992cdee03ac725f66bd8a5ec086a3+sha256-9fbe9729fecc9cf9232f3292684307ba1a85d69beff3920a2a7ed9e2c77bf7ef+sha256-7e00d90a437b5a33e79607a04b57b10dc14322bbaa63ce8bbe9ce1338eaf26f5","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":"gemini-2.5-pro","collected":55,"contributing":26,"admittedWithoutWeight":0,"excluded":29}],"observations":[{"id":"a2baacd01517ef45b2eceb1d","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"487059beacefde1e01685e8d","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5604a1b3b4ab8c68dc8d01bc","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe94c818a9ad0ca7d39e39ef","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9aec0db3dacd7fcf771012a9","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a2fff8b12d3d37901295fdf","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88d422808c7de7f23d709556","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"defe800b4fa5856397240d2e","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0780118e8e66b234eca4b2a4","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb4e80a7918d6b9057e3deed","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f077b068853bedaf080c341f","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5a906c034fd39fe365ed813","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69605a228871fa6d6a1fe38d","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"effe61acb1f2ecd3194c56be","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f2d5e3be696b0d89edeb2fc","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fed8f4ab77fcd5d31da67c95","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cf0ed4c7679f5831c0151b93","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b346e2f4d8c39e5b6a8796ce","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5336414aba2be78f3187de97","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"80b93729bec1b12b13fec2bd","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe7921ca6643b00dc3e8c896","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f6648f08f82d8663f02b246","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9861b3363626336b8e1278dd","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53fc9ec1dee0accada2433b0","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-thinking-8k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6cc85ba2b198bd02c85a961a","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-thinking-16k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"85789420efbd10e4bf8e8a0f","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-thinking-1k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1746e4a5f84cad00df32d6b","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-thinking-32k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-2z7kL9DpfvY44T9Wo99FYx","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-cqUZ6gcq2HBnShFRWvKjGr","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-FkywQ2KS4AkLPzjSPmhHcS","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-mQ3UwD6hUioWSp2s2oELY4","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"launch-amazon-1545","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1546","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1547","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1548","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1549","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1550","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1595","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1596","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1597","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1598","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1599","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1647","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1648","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1649","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1650","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1651","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1684","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1685","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1686","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1687","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gemini-2.5-pro-58c478670eac","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemini-2.5-pro-465fe8c26c46","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemini-2.5-pro-df03094a9acf","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-gemini-2.5-pro-077d8c0cfcca","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}