{"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":"grok-4.3","collected":77,"contributing":72,"admittedWithoutWeight":0,"excluded":5}],"observations":[{"id":"3e148f07e65bd83da8552afc","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a28e521275a8117ae5ab73c","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"332cd4432559a24c1067763a","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab02bbad93d66a73317ac504","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3dd4ab978ed9081e7d2256b1","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"036d3a1334196c80a57915e1","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1326a222541d5fa16aa3d69f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8c5adb6e6a04bb44455088a","modelId":"grok-4.3","configurationId":"grok-4.3--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":"33d428149eacb23f8023a22f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90dc9f391ef590950102f348","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f551e9f045bc0b6ac729b202","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"281d1eb368851122cc17db8f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2f7b3ce100e19c3b23c1e5b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a58cdd26382eb8561a3891c9","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa53133f053c6453c3b57345","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f896ff4dbb8782a2ad6cd1ef","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76697b005c207eca60a37292","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9a055af1a46fc2841cb4811","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7193993644401ada0c561b94","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac16b72863ef9ad38f76746f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31d0696779501c33756e0d41","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7551c8c0295e481116b6da40","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87938cd53777003184b7326c","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a7ea11c3b23006d2057ffc6","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e22732096c5a7cb5e49a22c6","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"864db222a3748d2576b04d3b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68527a9aa6a80fe2b6b57d58","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48b6077c8917596c2ef7209d","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39e2717926fbad74a11cd28a","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87998076f09f0d9f3a6d9164","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"120cd61fa038594ff09377ed","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6a4bb91832505b0b6e788fd","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"324617d001eff6640ca1330e","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8c6fa9ba872894ea7ce1c90","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0348ca9a6bde4aa27112f9d8","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d16467e883bd502ba32d9e0a","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce4626bb5d5d94abcaddd1b0","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6729a1bc7854706665ff871","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b15b56bf252797d3b5d91e95","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"326e7b3889e629aeda2d9b20","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"abd3c444a2f68677d8e6225b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"723887484db7ec3fbb615c5c","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a3190a3f384ca2ebc31bb6d7","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b73b3714dde60636c917020","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82d2a580c6f40ae99a27fa94","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff80f12b5df368a65cf2f2b9","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02504f35bcbb21ae0c5af2ac","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0561533dc2911a9c3050e1f3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7221252780a4b1647f643270","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3240e8dff8e99f1feec0b685","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7a445e9105703a4a9140142","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1676bd960d1324c582d1bb4e","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"234fdc59aa263bb853ba0c5b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb11904c98e84a986b9588e1","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afd8125af880999aea9ef239","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17cbb7437ff01131c310bc9f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69351a9c04f817687a4d844e","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a316a3c001d815220879252c","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e3dea1bc0f28e76fd71c35fd","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f472a30aeb8eaf66deeba1b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a57b0612082bbbf111f35e20","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35daaac2931883507e622ad1","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3iRQkf5v7Wu7YuZhxa76Gg","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bdsZjrG4ayzP8NAJg5q586","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-fzoUFmy77NpEDtXyA6w6ap","modelId":"grok-4.3","configurationId":"grok-4.3--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-R9XpD2PaYpPiokjjSWnMYT","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Vw7spGUnJyf3vuzSjTcj2F","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Y39ZRp553ULpUDBV2XrBbc","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--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:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--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:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--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:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--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:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--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:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--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:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--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:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-lmarena-grok-4.3-465fe8c26c46","modelId":"grok-4.3","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"}]}