{"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-flash","collected":52,"contributing":28,"admittedWithoutWeight":0,"excluded":24}],"observations":[{"id":"778a476fac3a54bc26ad1bdc","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25e8b81f8b05ec46c5e80257","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c843963587d72d6e7fa6ab2b","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--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":"d1e35c9dfd5a9177d6520490","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fbe3f48f7d31ed271a50ddf","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"03903b802c05359369266f36","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae60d7a4d3b3a85a296b38ab","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a919ff134ab8dd622151ef8","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0508741ce4e4c770a963f3a4","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29c12307a2fa27b9adfab4e4","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad52dd4994d43cfb7388537b","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"615f11f6104fbdbc6397c19a","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2274f10c01fd49af34cc8c7","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a32eda887ff803501ac260c2","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2a790a25cbcf597773c9220","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3ffd498b7959470e367bd26","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e548cc9df3852affb6827c7","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9a8955bfe6f14e6cc47c6be","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5513fb39e65010cbd84258eb","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa36fae3bef0b68268249bfe","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4871389cdfa8311f33acc44c","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8810b2fe580ca34e86a3b029","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6ea19c704d0cd6d45804ad9","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"94436d1283ceade19a098e93","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"89031d6f4b0b9da5cd80cf55","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be837d02ebf79658b1d356cf","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b82146057c975a009a40f506","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6896924c93716199a8e8b23","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b1b7e45360ba1982d470496","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6d86a700f4535aa3b842c46","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-amazon-1506","modelId":"gemini-2.5-flash","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-1507","modelId":"gemini-2.5-flash","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-1508","modelId":"gemini-2.5-flash","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-1509","modelId":"gemini-2.5-flash","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-1510","modelId":"gemini-2.5-flash","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-1511","modelId":"gemini-2.5-flash","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-1568","modelId":"gemini-2.5-flash","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-1569","modelId":"gemini-2.5-flash","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-1570","modelId":"gemini-2.5-flash","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-1571","modelId":"gemini-2.5-flash","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-1616","modelId":"gemini-2.5-flash","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-1617","modelId":"gemini-2.5-flash","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-1618","modelId":"gemini-2.5-flash","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-1619","modelId":"gemini-2.5-flash","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-1620","modelId":"gemini-2.5-flash","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-1663","modelId":"gemini-2.5-flash","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-1664","modelId":"gemini-2.5-flash","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-1665","modelId":"gemini-2.5-flash","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-1666","modelId":"gemini-2.5-flash","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-arc2-gemini-2.5-flash-efebf61be277","modelId":"gemini-2.5-flash","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-lmarena-gemini-2.5-flash-465fe8c26c46","modelId":"gemini-2.5-flash","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-swev-gemini-2.5-flash-077d8c0cfcca","modelId":"gemini-2.5-flash","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"}]}