{"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-1.1","collected":73,"contributing":46,"admittedWithoutWeight":0,"excluded":27}],"observations":[{"id":"3d28104ab178b34670aa619c","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0c09f33ec395a21dfca2ae2","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90f826dbdab369b8d36e712e","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3db9f37231f6969e5af916c8","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6099fc5a6c629d98c4017a6a","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77cb0921403bb8eea32f98e2","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"674c189b99daf251023acc62","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69c92bbf50967acf2ddea1e6","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1155696d61f97ace1c6685cb","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e482487bec614ab5161ed411","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d5c35ac642c8328a56d2cb1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"51ae435e2accf7c476e8b700","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2ce1bb7d2f24ac399b6dd2e","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa4da6d45fc3c9e23c5e0a1d","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fa6b5f2d5612bc7ff3ca112","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--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":"4db8c7b47a313e0e8d926986","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"6c79741b5a7ecef0ff4d0346","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"8154d53aea81c7edfd9708c9","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d1592c494c0bc37b96c4b13e","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7e01c14d29d1b99014cf62ea","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6baf6c794bf4aaf644c7b7c3","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1cba090af30c55faf508a232","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b0e641583182f918dc7c7607","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ff7deaad8514a735c60215cd","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6bdc2206bd256d34c7fd7650","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eb8e759c8756c57a6678b38c","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9a71dad62d416416d1786c72","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5f2ebc6018d88a7989407282","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-64d9137045cdef710bd3ca92","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3cfdcdd691354a0a5029cdd2","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cb4d12433d4ef2158a779de3","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fd205044a78778402333b4ab","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-79c0b925029bc6018d77d2de","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-643a2b102ca96cc1c855d0d9","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-87b456d84438ff05a853f952","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-378ce00ff970314e97d7c872","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5f71b89ede220ebd20a0c531","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a3b33640a7470089412d387c","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ed41d716690c2b0b08f4b261","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-607ac2b71c6861f6dfcf5271","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3ca3b50afff257eb11c4cb04","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bCdwpRXgZtvQLYC4wA9JXr","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--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_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--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_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--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_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--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_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--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_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--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_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--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_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-1875","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1879","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1883","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1886","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1890","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1894","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1898","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1902","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1906","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1910","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1914","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1918","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1922","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1926","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1930","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1934","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1938","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1942","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1946","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-deepswe-muse-spark-1.1-eb88d1c756c0","modelId":"muse-spark-1.1","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-lmarena-muse-spark-1.1-465fe8c26c46","modelId":"muse-spark-1.1","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-osworld-muse-spark-1.1-42c386263956","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://os-world.github.io/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swepro-muse-spark-1.1-6112d01393e8","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}