{"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":"claude-opus-4-8","collected":248,"contributing":103,"admittedWithoutWeight":0,"excluded":145}],"observations":[{"id":"38bd39336f87942a65930af7","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96e07d2acdac72606809adc6","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"396c304045bfd21fed6494cd","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"55ab6f2bb1306e9de5b5cf55","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9baeb1c807742dfa60b68f32","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbd34afbb3a236f1e52c05d8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67f24e326dc157af68bba59f","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d430d708739c1838a86ee01","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19d5c01029e87cfc22eb0792","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e9513aec83ed5c426771c7a","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"837eed14d5abe653526f9c1e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f68d5f7125d6078981d1cdc8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4440269bce8cda5310d406c","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2f0cc5a86febfa51defe5db","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"1e3ca5abae432a2e5870be34","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa9718cf977935383075b2e2","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e87020b9d0c264608d5c3e5","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02cceeaa14a76c764ac377f1","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ee92943d34643e7c8109127","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09b44ba8a082ec541fdf76c6","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6bc38ad1655069ba484c206","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5c453e45d5a65111bf8c8fc","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7609122fbb5f21e0336fd79d","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"099afb744367e0027cb4beb0","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ed225cfbd8da4a68cb773eb","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6529363c938719d7a1e4c752","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8158b49aa1444c7311339716","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"excluded","reason":"Incomplete task coverage: 111 of 113 tasks. A common task set is required for ranking."},{"id":"00b724564a3c562424e7d7ee","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0c9ff5a707bf93dda7c0ef5","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--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":"766dde2b58473794011e3786","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1cf1455535fc32710e1965cf","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47d55be1dd81aa1bf4bf5a74","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"541e90621a96734aecdd8834","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ce108c441495c34dbedea2f","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b56938a2e49c9671f1657923","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba8ff35e294d29a743fa5c65","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c16b09ec865ee083d20ed15f","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7981128f2cb3799b53b66ec","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2c3b944130f3a5e4b806d94","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1edd38ed72382bd57766812","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd19565d5d4088b6dfc79064","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8141013d16a793653a973079","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/enigma_eval","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba265c887f15f603db7f5f80","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d11e9cc7b5eb05e0e97dbb6d","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c2408725a1995f2f76a38c0a","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-335d542464864769d1ca1bdf","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e79c5684c29cd6b303b8c12e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-de5882ae22989b74ec6dc0e7","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dd863a0d16624af984380aa0","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5610f87659e4a35f39fc8224","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-af8e1e7afb22e13a8161b804","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c3668fe9c1af9e1f815034dc","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3dd977ca39f5c684439cf98e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-141f8c45edac9dc4154ac08a","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d1b3a97faa4ffcecfd7ad8f3","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4ed8370e5706671ee5d2dd82","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-75a12802fa02fbeea400c4cb","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-69f8e076de1d08be8612d652","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c8c35a24dc4b0f79d4adbb2f","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f24c3abaf143433907c54872","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-520b3b60cfad57f258de5139","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e90fea5b53cba5c187c6980e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-502f63677ac7031d9e46c35a","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f91ef1733b24ae4b57da78dc","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-56a4d57c73bfc7aaac0a1a33","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5317018cf4f7cd8ae532c388","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7aab7aefea402a837eb331c7","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-aa3ee5d91a696499570b9479","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-59f0399257b1743a621e4448","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-37pJqPpXTE6ia9ikmmGPJ4","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3ZnPtGRJkvqHk8wvWWRgCe","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-5u3LkMVq4Dy8CfiwA2EAVr","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-adGE8rXdNuUFs96ioppbc5","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bwak5Cq3LBthfoboicGZUo","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ckbZdkrXPwbFdjn6bmUQsi","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-dqgqP2uEPswfECCVj2Kbr9","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-GThtce6GAmRAS8srQyGQoA","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GVmgtgKMwEqc54f3jA7auP","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JiqgqBTfkGx797uowZgJbk","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-MEhV5sh6nbM8cKJGQ6HzcS","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-oU38rqq2TvJTxvvPsnEQsH","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Q3WpHdurYNvawj6ycXyj6e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ViC6pxQZUVS3E9M9iEubF7","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--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:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--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:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--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:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","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:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","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:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--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:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-deepseek-1144","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1145","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1152","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1157","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1161","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1167","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1173","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1179","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1184","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1190","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1196","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-705","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-711","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-717","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-726","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-727","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-733","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-739","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-745","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-751","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-757","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-763","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-769","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-775","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-781","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-787","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Anthropic or OpenAI release reports; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-791","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-794","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-800","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-806","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-812","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-817","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-823","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-829","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-835","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-841","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-847","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-853","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-859","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-865","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-870","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-874","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-879","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-885","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-891","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-897","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-903","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-909","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-914","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-919","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-923","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-927","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-932","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-940","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-941","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-950","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-951","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-960","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-961","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-970","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-971","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1877","modelId":"claude-opus-4-8","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-1881","modelId":"claude-opus-4-8","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-1888","modelId":"claude-opus-4-8","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-1892","modelId":"claude-opus-4-8","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-1896","modelId":"claude-opus-4-8","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-1900","modelId":"claude-opus-4-8","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-1904","modelId":"claude-opus-4-8","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-1908","modelId":"claude-opus-4-8","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-1912","modelId":"claude-opus-4-8","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-1916","modelId":"claude-opus-4-8","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-1920","modelId":"claude-opus-4-8","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-1924","modelId":"claude-opus-4-8","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-1928","modelId":"claude-opus-4-8","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-1932","modelId":"claude-opus-4-8","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-1936","modelId":"claude-opus-4-8","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-1940","modelId":"claude-opus-4-8","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-1944","modelId":"claude-opus-4-8","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-1948","modelId":"claude-opus-4-8","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-openai-sol-launch-274","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-281","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-289","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-295","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-301","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-309","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-316","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-323","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-331","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-337","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-344","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-354","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-359","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-365","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-371","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-376","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-390","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-429","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-436","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-443","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-450","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-456","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-463","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-477","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-482","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-487","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-qwen-551","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation."},{"id":"launch-qwen-556","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-561","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-566","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-569","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-573","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-578","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-583","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-588","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-593","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-598","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-603","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-608","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-613","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-618","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-623","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-628","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-629","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-636","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-641","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-646","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-650","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-655","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-660","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-665","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-670","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-675","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-679","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-684","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-689","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-694","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-698","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1203","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1209","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1217","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1225","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1230","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1235","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1240","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1246","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1254","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1265","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1266","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1275","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1283","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1291","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1299","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1307","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1315","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"s-arc2-claude-opus-4-8-efebf61be277","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-claude-opus-4-8-eb88d1c756c0","modelId":"claude-opus-4-8","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-claude-opus-4-8-465fe8c26c46","modelId":"claude-opus-4-8","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"}]}