{"version":"configuration-source-6","evidencePolicy":"documented","snapshotId":"sha256-c4d5b67b1e1a60ef314523cbb3fbe44b06fde3a55f714385b8fb1a0db5291c0c","effortDatasetId":"sha256-f0563cf1c78be0f3bf27cf77e3a1300440bd5d253a3cbd7616a94c9b3d62133c+sha256-15ba631518c576c495104485510c5a32932cfc46cf3c8d26cf23c08067462a93+sha256-a64f8fddfa426be712c0faea67985ae67c3c39be4dfca6cf9ad11c4fa3c58bcc+sha256-6390b33ad243c40ef5f592e9e7b2df0061ed33f459d6038cb6f6aa31b1203a0f+sha256-81679b15ba83a7848fd115f457e04edf5e2d906b78dcd32e66cc9e629a0395e4+sha256-39abeb27d2f933f3c9f00199a97be2e223490737dc4d3bee10d559390fc65cb1+sha256-dc15922aea6f086a955a18e324406648f5119c442c98c1151f1f4b73519bddbe+sha256-263d96d7f6baf346071cc8607f01aa60ffb2d3337b9f9d6e36e3ba1b11cac3d3","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":"mistral-large-4","collected":62,"contributing":10,"admittedWithoutWeight":0,"excluded":52}],"observations":[{"id":"ebcdcc824b76bb636597988d","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92d9702142f2af68c10b4239","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f54cdec0a23286c1583ed6a","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f7541c0b8b1eedd20d04b1c","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bf963a14be34961a024621d","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65a26c1271ec36cab36439ca","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4bf80014cf8127d1186acee","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0eb64d0a4de068b9aa6ba652","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"530427155dcfa01e7115c354","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b28eb0bf4146edef49d664a1","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75d0b63baab906a80f8fef86","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"d3cacfd5ef49c303c25c3c00","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c150be94540718c3712937db","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-394dd3bdef92e8dcd0886faf","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-9d17bc866a773505d636d87b","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-8723236a70407e8aab03a7e1","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-495c60b884a90bb39ef8b8f5","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-881e35e28677c446d8b38378","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-ff03c9088659ae53d42267dd","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-0dc5b51301907163a7deaa45","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-3025e1d8b41e854f23a4f5af","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-5342d5279a0ed1a3e891243e","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-8ed268ed656d254b108ce78f","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-853412c6f0ef9c6d08529d83","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-3eff14e4aa41826f6862f62c","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-1601a1d64a7a9e15152dab7f","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-82eddc3d36552642e464eff7","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-f7389adfe8fd745b3a0404ca","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-129bf3385c08a43a5f9c9647","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-0790444be4f573a3aef2e87f","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-59b1300c9612863d90094bd2","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-c581cbeec9d119e11354fb42","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-b12381047fc8f7dc3d32a8f2","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-01811e82cd9297d95f6995b3","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"panel-1b5121c6aff4d3d27981001a","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://livebench.ai/","status":"excluded","reason":"LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-finance-agent-v2:mistralai/mistral-large-4","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-code-migration-v1:mistralai/mistral-large-4","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-legal-research-v1:mistralai/mistral-large-4","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-emb-v1:mistralai/mistral-large-4","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-vibe-code-bench-v1.1:mistralai/mistral-large-4","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-legal-agent-benchmark-v1:mistralai/mistral-large-4","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"vals-tax-agent-bench-v1:mistralai/mistral-large-4","modelId":"mistral-large-4","configurationId":"mistral-large-4--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench","status":"excluded","reason":"Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label."},{"id":"launch-mistral-large-4-launch-2600","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2601","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2602","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2603","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2604","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2605","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2606","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2607","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2608","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2609","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2610","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2611","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2612","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2613","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2614","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2615","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2616","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"launch-mistral-large-4-launch-2617","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://mistral.ai/news/mistral-large-4/","status":"excluded","reason":"Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission."},{"id":"s-automationbench-mistral-large-4-b150ea70b31e","modelId":"mistral-large-4","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-gdpval-mistral-large-4-a4a4781446fd","modelId":"mistral-large-4","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"}]}