{"version":"configuration-source-6","evidencePolicy":"documented","snapshotId":"sha256-e384eba3603ee0338d26052e22db513e17d16719d2af7d2444a3f89e18cd1b99","effortDatasetId":"sha256-49305f3d640f7387a764d95d62f10bbce44aeff4a4012ddba973eddf1e57a707+sha256-443256461e035ccdee585c01fdbd68b4b26545d45e2bd6b2bd93e1e913a2d41a+sha256-32c6374f8a0cdb9cd64f17244f1a697dd35d31cff071002599f3e1226d1e027d+sha256-9b7bfe52f0cba33df0362a330cb12551ea2f5853bf843931b08dad98e5d8d15c+sha256-c4f243913106bee769c57849d3cb4662fee3097206d30d3c8d4d37d687f8e556+sha256-c6f9cb8b67b4289e79e621b65d529e5f57eee55d89d86915f397859092051dad+sha256-78cb5ce46bffe96a698a9a7117551eafb90b2c3d05066722f4a703be2680aa55+sha256-e34a2de55476481fa69ea734e4027620fbc14df27f896c3bcec6c07275b0da42","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":"muse-wonder-full","collected":20,"contributing":17,"admittedWithoutWeight":0,"excluded":3}],"observations":[{"id":"4447279d9098afb439d91f31","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd1c73523af0a64b020f6d7c","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44b450aa27027808b9e57eb5","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89cf6157d93f8c2efc2ad7f9","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6121843833838096234efb94","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b52ede219ffa5fc33ccd26c1","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ce197385cfe06e9ee349cd6","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ad56bef5143cd852c7e0a23","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54b82abd2705526e243350f3","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c95e0955619a34d31cb1413e","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9841a8670fe760a5c96f4521","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","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":"0b29c27c06286dae67a3281d","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:meta/muse-wonder-full","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:meta/muse-wonder-full","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:meta/muse-wonder-full","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:meta/muse-wonder-full","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:meta/muse-wonder-full","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","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:meta/muse-wonder-full","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-tax-agent-bench-v1:meta/muse-wonder-full","modelId":"muse-wonder-full","configurationId":"muse-wonder-full--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-automationbench-muse-wonder-full-aeb8c17003ec","modelId":"muse-wonder-full","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"}]}