{"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":"llama-4-maverick","collected":32,"contributing":23,"admittedWithoutWeight":0,"excluded":9}],"observations":[{"id":"77dc3e409687fdc4123e7382","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"faefecf4982a3c56261456c3","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31f2f561fab689277fa32daf","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--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":"cdf57f3e51751d8b1b206f3e","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45aff2671367df91ec82a00d","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1c45db0f194569fedcfab7e","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8570e13fa3402d4a1cf0ce49","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48fc8cf05f6cf5be1916a16f","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b3e6d11f2c08cecf4bbdf7b","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0faf4ea29ec7471f2ddc2575","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0496ddc71cb780c146897871","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc29361336c4897fbe3e986d","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39a00cb8aa14d4a8f1630392","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83ab2bc25f0bf5b24ca914e2","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29bc8ec0528066576e43067c","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9aa0ba713cbccb8900465da5","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7eec6f4e726f2ac2843e4d31","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f6678979dffdce85c6baa1a4","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d6139083fe99c0d47d89705","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d78fc2575a1485830285d7e8","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dac821c6aa9136a83d875bda","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"604481ef9f14e63577ee5fd8","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"354eb159671e8738012a81fa","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edfcc29c0deb58a191bb162d","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-arc2-llama-4-maverick-efebf61be277","modelId":"llama-4-maverick","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-gdpval-llama-4-maverick-58c478670eac","modelId":"llama-4-maverick","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-hle-llama-4-maverick-f549f30a8404","modelId":"llama-4-maverick","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-llama4-gpqa","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://ai.meta.com/blog/llama-4-multimodal-intelligence/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-llama4-lcb","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://ai.meta.com/blog/llama-4-multimodal-intelligence/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-lmarena-llama-4-maverick-465fe8c26c46","modelId":"llama-4-maverick","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-llama-4-maverick-df03094a9acf","modelId":"llama-4-maverick","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-llama-4-maverick-077d8c0cfcca","modelId":"llama-4-maverick","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"}]}