{"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-scout","collected":27,"contributing":22,"admittedWithoutWeight":0,"excluded":5}],"observations":[{"id":"555d23d461c05d28e5affaad","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4885145006b9e6c516d4941f","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7581f3a2422117f43b197e4b","modelId":"llama-4-scout","configurationId":"llama-4-scout--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":"9353269ebd55ac03ed176358","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afc01f597c0079772acb9e3f","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d524b4da994ccf7a3136f46d","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ca6b818ad3095ba1fec0cf3","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"66c9c26050db4c0d8d41b4a8","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37634d64a31c01e3c55ac3eb","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab3e6dc6aee996774804be32","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b5c1e36e87698c0a87d0094","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7c19c636a0f224e332b9c1e","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebf48949184410fed6f20bb0","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2341b5314bd44225e9253b3","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"342b5de48406cc12a0d640cc","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"825b3abf9640fc95590a58b5","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"29b51ff314d8015f16d8fd73","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3e565fe11b60b81a60483f2","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ceeb86bffcbd0f7f1c1cb44","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7075f4c91bd36c49bbb5930","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe0a313c1be6171f1e933267","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7b21db2c6c9de33ab88deb3","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12f09ed4b289733513c29184","modelId":"llama-4-scout","configurationId":"llama-4-scout--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-MsXAXDEKP3xBKtiA7aTBBG","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-T3X5DeC47iqCaoRYXu5k8L","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"s-lmarena-llama-4-scout-465fe8c26c46","modelId":"llama-4-scout","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-scout-df03094a9acf","modelId":"llama-4-scout","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"}]}