{"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-3.1-pro","collected":184,"contributing":71,"admittedWithoutWeight":0,"excluded":113}],"observations":[{"id":"7c7f774514f7fa2297208e0f","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b06e9c41fbb683c7a2f4f192","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37687afd20028c6089e77920","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f4e475d1f8d57db24bcb7a6","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-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":"db8f74e2e14e95ffdcaeb92d","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa3f112c9b6e79acc46b504f","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93374c1590601b233140cd4a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8063177a2a63d1be8648e2f8","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"369dcfed5847bd7a41289d20","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39bf8cf4de7d4ae5d9295e26","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3fd1ba1d2b182c00683d93b","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f119405d93465a62350dc255","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3631e2d668ca3ff2ebfe823","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9aa04e6ff77c61f9b93c9290","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c7f8cd7187c61c11375f19b","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"208c2682d2e878ad0bfc59b4","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45e4f876ba3f9fcf04c8c5fa","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a904d86ad7c12c3aac7713b","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"24d00d3350012cb696297151","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72fd11da3d45e05f88f9fba5","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d824de33344d5f7c900a32c","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d20dfb2c84bb4190f7edf29","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f78b4be38ed10e8ddcd80664","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"154ebcd0575e2428b67b2398","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd2e6ea2003857920a1bdfcf","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db901e8199046d5c8d479ba0","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f6dd87d3bec8be094065e59","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/swe_bench_pro_public","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09a429372313877fb69d9077","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"a01dc047adae16bf8c7acb63","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cbc2db363833abfb6c9f650d","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da0ddcdb318167ad7f56f77a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/enigma_eval","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f621460ea8cfcfd9a6843901","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9ee205c15ad677241207d058","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d3127514aeabe252e43231e1","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2d4783c770d432f985707cfd","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6fb4bc1b60f839623c5d4381","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b70f7219a2898aed69af5a1b","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4f12ebc87581a8b3fead6ca5","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-58aac2c2dde4fbb0c2408d75","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4d524cc2ad780da119be2cf9","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dd35ef007b87680fc5d395d0","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8272dd6e6a4ec9a8e6cbdc9f","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6730b76b0480a9ddba9ceb60","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0662502669451fa91c907b36","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-728ecc9a397966fe315b4b0a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0e57c643f0410832cbc9fb48","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6af50c99811132886f95297a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1daa1fc476d17b814e17715a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0ae689afa56fc1952d84c292","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-35844166e61bc0d5a71876d2","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d205d81c52a64897f3ddf2c","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6f887f9f34bf0ced09693be5","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-da04aa901faef5abb22913ce","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ecfd0cf5293ccba5bfd04b78","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-67097dc7f9543964f1eb66f1","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4a3M8rRWUoPphCSr2dguXH","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4mzBGLow3HkS8BmAYCzGTR","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4QfM9qyeWGqNc8YTcQNV76","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Run-specific qualification requires review: In the initial run, 53 samples did not complete. These were rerun until 51 of them completed. The remaining samples are scored as incorrect."},{"id":"epoch-run-BgmrBFsbsaD8rNpebv49Da","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bXgZZgzRE3wXoSRUgrbsVf","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Run-specific qualification requires review: In the initial run, no epochs completed for 2/45 samples. Despite several re-runs of these two samples, no epochs completed. All epochs for the other 43/45 samples were correct. The model's score was edited to be 43/45."},{"id":"epoch-run-eXVWr3RBeSsWy5DAU8ed46","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-g4bbCaiFDqw2YYNDAcmn2a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hVifTUdQZrFEYabgCRu8Qq","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-kR9F3oHBCnwQW4AiTPKwpd","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Run-specific qualification requires review: In the initial run, 3% of samples failed to complete. Inspect defaults to not scoring these at all, but we override this behavior when >2% of epochs fail. For each sample, we average the score of the epochs that did complete for that sample. If none completed, we assign the random baseline of 25%. Then we average these scores across all samples. In this case, the resulting difference is very small: 94.1% modified vs. 94.4% original."},{"id":"epoch-run-nhim2QCRgpir5cZdqrmUz3","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VGeF8Xac4WcSAGgSXVdEBi","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-WueZbBM3NwMUZPveuagrZo","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","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:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2109","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2113","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2117","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2121","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2125","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2130","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2134","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2138","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2142","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2146","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2153","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2157","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2160","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2163","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2167","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2170","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2173","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2177","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2181","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2185","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2189","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2193","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2197","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2201","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2205","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2209","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2213","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2217","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2221","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2225","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2229","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1876","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1880","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1884","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1887","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1891","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1895","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1899","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1903","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1907","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1911","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1915","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1919","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1923","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1927","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1931","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1935","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1939","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1943","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1947","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1696","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1703","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1710","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"MiniMax cites this comparator from the official Terminal-Bench leaderboard; a common protocol with its internal Terminus 2 run is not established. See MiniMax M3 benchmark figure, Terminal-bench 2.1 methodology."},{"id":"launch-minimax-1717","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1723","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1730","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1736","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1741","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1746","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1751","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1759","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1767","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1772","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1777","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1782","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1794","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1802","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1806","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1811","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1820","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1828","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1833","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1840","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1846","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1851","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1857","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1860","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1865","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1870","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1874","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-275","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-282","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-290","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-302","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-310","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-317","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-324","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-332","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-338","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-366","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-419","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-430","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-437","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-444","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-464","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-488","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gemini-3.1-pro-efebf61be277","modelId":"gemini-3.1-pro","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-deepswe-gemini-3.1-pro-eb88d1c756c0","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gemini-3.1-pro-58c478670eac","modelId":"gemini-3.1-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-gem31-aa","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/articles/artificial-analysis-intelligence-index-v4-1","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-gem31-browse","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://deepmind.google/models/model-cards/gemini-3-1-pro/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gem31-swev","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://deepmind.google/models/model-cards/gemini-3-1-pro/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gem31-tau2","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://deepmind.google/models/model-cards/gemini-3-1-pro/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-gpqa-gemini-3.1-pro-41e862296ea6","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-hle-gemini-3.1-pro-f549f30a8404","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemini-3.1-pro-465fe8c26c46","modelId":"gemini-3.1-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-3.1-pro-df03094a9acf","modelId":"gemini-3.1-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-swepro-gemini-3.1-pro-6112d01393e8","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-tb21-gemini-3.1-pro-a98710a64150","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://www.tbench.ai/?version=2.1","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}