{"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":"muse-spark-1.2","collected":68,"contributing":52,"admittedWithoutWeight":0,"excluded":16}],"observations":[{"id":"5a5c40dc8bfa7420c7a73337","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f054375dfae2880d425145e","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"545c640a1e97c757398c4c09","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77a5b3ed91707a9a184b6c15","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0c29d3596152a94d0cb8ed7","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41b9ba5b3cc128b9746727fe","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"536612d6ef75df4fe26d8799","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b798a8a82c6bbbfe0f4543fe","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1598edcef4c4dc72d168db18","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"900af26141c1715a5245156e","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ae131704ad1ec5583eb3702","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7778904266b2d0dafc5de1c3","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1ae73029fc1423754ddc150","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a4630ffdeb77234b578ed4c","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2150abdc6bed127d186f4fb9","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e8ebf2449ddbb9b4d37ddf99","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1585a41209b88f2db63e82f8","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b7ece23e8756e740abb6e39","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"970bc242697fc80101d9ac17","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-high","sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"c5e80648923e0576c68a9c39","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"panel-5db4666fe0d22748d017fabf","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-31199fc389abf8c37e97a1ef","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-90609ba61b59695b58129751","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bbd53ca4e345a1af051f9838","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dbe6aa071a22ccaa40e097c9","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-939b2284f37f61d8eb5f67b6","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c37413eeb9c7e46ddfc253d2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4a402a6edf729fb609faca1b","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b4abe05d293dd2f434bf065b","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d6cb0c0f64f505b9a71b6ff","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d10f6d2cdabb5ddb7e4899d2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b100b1155d4fad7945551d5b","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1c622171ac4a61c0905126a8","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c5de3c6d1577f440b4c8c784","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-315c13eaf06cba3126de4186","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6e422918805d22eb5f088d67","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9e2379b2378edc420ca56706","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a4fc6c6ff3adc5d9f63e5f13","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-860ece53551bde0e2391fb57","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2e9188c4762961d8b305cb9d","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7c980646387d7ffe0fbb8f07","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ca5efb697bbdbfd817a0dc54","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5924987a533b33a47f789e7e","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mLLmVVvo6t23MM5yxq7ryW","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","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_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","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_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","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_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","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:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","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:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","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_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-1986","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Secondary GDPval-AA v2 leaderboard report; the original evaluator already supplies this exact configuration. Reprinted or rerated board snapshots are not additional evaluation evidence."},{"id":"launch-meta-muse-1-3-report-1991","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-1996","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-meta-muse-1-3-report-2001","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-meta-muse-1-3-report-2006","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2011","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2016","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2021","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2025","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2028","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-meta-muse-1-3-report-2032","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2037","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Different native coding harnesses are mixed; exact shared agent configuration is not established."},{"id":"s-deepswe-muse-spark-1.2-eb88d1c756c0","modelId":"muse-spark-1.2","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-vulcanbench-muse-spark-1.2-19-musespark-effort-high-2f58434bbe3d","modelId":"muse-spark-1.2","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-muse-spark-1.2-19-musespark-effort-low-2f58434bbe3d","modelId":"muse-spark-1.2","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-muse-spark-1.2-19-musespark-effort-xhigh-2f58434bbe3d","modelId":"muse-spark-1.2","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"}]}