{"columns":["sourceKey","sourceId","dataArea","title","publisher","url","sourceType","authority","status","evidenceRole","publishedAt","retrievedAt","checkedAt","sourceRevision","responseHash","licence","attribution","redistributionStatus","verificationStatus","failurePolicy","refreshCadence","notes"],"generatedAt":"2026-09-01","ledgerSchemaVersion":"1.0.0","projection":"public","recordCount":873,"rows":[["production::aa-lcr-leaderboard","aa-lcr-leaderboard","AA-LCR accuracy","AA Long Context Reasoning Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","independent-lab","independent-lab","source-checked","AA-LCR accuracy","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::terminal-bench-21","terminal-bench-21","accuracy|agent scaffold|reasoning setting|evaluation cost|result date","Terminal-Bench 2.1 leaderboard","Terminal-Bench","https://www.tbench.ai/leaderboard/terminal-bench/2.1","official-leaderboard","official-leaderboard","source-checked","accuracy|agent scaffold|reasoning setting|evaluation cost|result date",null,null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::aa-briefcase","aa-briefcase","agentic knowledge work Elo","AA-Briefcase evaluation leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/aa-briefcase","independent-lab","independent-lab","source-checked","agentic knowledge work Elo",null,null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::meta-muse-glimmer-30b-huggingface-f84ecc3a","meta-muse-glimmer-30b-huggingface-f84ecc3a","Apache-2.0 licence|29.6B parameters|131,072+ context|text and image input|text output|tool use|supported reasoning strengths|benchmark table","Muse Glimmer-30B model card at immutable revision f84ecc3a","Meta Superintelligence Lab","https://huggingface.co/meta-models/Muse-Glimmer-30B/blob/f84ecc3a0ea984a4c04542a84269e3d065350a6e/README.md","official-model-card","official-model-card","source-checked","Apache-2.0 licence|29.6B parameters|131,072+ context|text and image input|text output|tool use|supported reasoning strengths|benchmark table","2026-08-10",null,"2026-08-10","f84ecc3a0ea984a4c04542a84269e3d065350a6e","1647ac8916f9c3c7c8ad508f6509d79f0c61d434b03b73f57ec6ad629b6adc13","Apache-2.0","Meta Superintelligence Lab, Muse Glimmer-30B model card","metadata-only","source-checked",null,null,"README bytes resolved from the exact Hugging Face commit and SHA-256 checked on 2026-08-10."],["production::aa-apex-agents","aa-apex-agents","APEX-Agents success","APEX-Agents-AA Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/apex-agents-aa","independent-lab","independent-lab","source-checked","APEX-Agents success","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::anthropic-claude-opus-5-docs","anthropic-claude-opus-5-docs","API model ID|context window|max output tokens|effort ladder including max|thinking defaults|pricing|availability","What's new in Claude Opus 5","Anthropic","https://platform.claude.com/docs/en/about-claude/models/whats-new-opus-5","official-docs","official-docs","source-checked","API model ID|context window|max output tokens|effort ladder including max|thinking defaults|pricing|availability","2026-07-24",null,"2026-07-24",null,null,null,null,null,"source-checked",null,null,null],["production::llm-stats-arena-hard","llm-stats-arena-hard","Arena-Hard score","Arena-Hard scores via LLM Stats","LLM Stats","https://llm-stats.com/benchmarks/arena-hard","independent-lab","independent-lab","source-checked","Arena-Hard score","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::refresh-aa-image-providers","refresh-aa-image-providers","availability|pricing|media","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/image/providers","independent-lab","independent-lab","source-checked","availability|pricing|media",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-image-providers-reviewed-html@2.0.0; role manual-review."],["production::refresh-aa-video-providers","refresh-aa-video-providers","availability|pricing|media","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/video/providers","independent-lab","independent-lab","source-checked","availability|pricing|media",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-video-providers-reviewed-html@2.0.0; role manual-review."],["production::registry-balrog","registry-balrog","benchmark definition","BALROG","BALROG","https://balrogai.com/","official-leaderboard","official-leaderboard","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-bfcl-v4","registry-bfcl-v4","benchmark definition","Berkeley Function Calling Leaderboard","Berkeley","https://gorilla.cs.berkeley.edu/leaderboard.html","official-leaderboard","official-leaderboard","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-browsecomp-plus","registry-browsecomp-plus","benchmark definition","BrowseComp","BrowseComp","https://github.com/texttron/BrowseComp-Plus","official-repository","official-repository","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-mask","registry-mask","benchmark definition","MASK benchmark","Center for AI Safety","https://www.mask-benchmark.ai/","official-leaderboard","official-leaderboard","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-eq-bench","registry-eq-bench","benchmark definition","EQ-Bench","EQ-Bench","https://eqbench.com/","official-leaderboard","official-leaderboard","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-factorio-learning-env","registry-factorio-learning-env","benchmark definition","Factorio Learning Environment","Jack Hopkins et al.","https://jackhopkins.github.io/factorio-learning-environment/","official-leaderboard","official-leaderboard","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-arena-hard-v2","registry-arena-hard-v2","benchmark definition","Arena-Hard-Auto","LMSYS","https://github.com/lmarena/arena-hard-auto","official-repository","official-repository","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-swe-lancer","registry-swe-lancer","benchmark definition","SWE-Lancer","OpenAI","https://openai.com/index/swe-lancer/","official-docs","official-docs","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-spider2","registry-spider2","benchmark definition","Spider 2.0","Spider","https://spider2-sql.github.io/","official-leaderboard","official-leaderboard","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-the-agent-company","registry-the-agent-company","benchmark definition","TheAgentCompany","TheAgentCompany","https://the-agent-company.com/","official-leaderboard","official-leaderboard","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-factscore","registry-factscore","benchmark definition","FActScore","University of Washington","https://github.com/shmsw25/FActScore","official-repository","official-repository","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::registry-zerobench","registry-zerobench","benchmark definition","ZeroBench","ZeroBench","https://zerobench.github.io/","official-leaderboard","official-leaderboard","source-checked","benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::openai-mle-bench","openai-mle-bench","benchmark definition|Partial-30 protocol","MLE-Bench official repository","OpenAI","https://github.com/openai/mle-bench","official-repository","official-repository","source-checked","benchmark definition|Partial-30 protocol",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-claude-4-5-haiku-evals","aa-claude-4-5-haiku-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for claude-4-5-haiku","Artificial Analysis","https://artificialanalysis.ai/models/claude-4-5-haiku","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-claude-fable-5-evals","aa-claude-fable-5-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for claude-fable-5","Artificial Analysis","https://artificialanalysis.ai/models/claude-fable-5","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-claude-opus-4-8-evals","aa-claude-opus-4-8-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for claude-opus-4-8","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-4-8","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-claude-sonnet-5-evals","aa-claude-sonnet-5-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for claude-sonnet-5","Artificial Analysis","https://artificialanalysis.ai/models/claude-sonnet-5","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-deepseek-v4-flash-evals","aa-deepseek-v4-flash-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for deepseek-v4-flash","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v4-flash","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-deepseek-v4-pro-evals","aa-deepseek-v4-pro-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for deepseek-v4-pro","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v4-pro","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gemini-3-1-pro-preview-evals","aa-gemini-3-1-pro-preview-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for gemini-3-1-pro-preview","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-1-pro-preview","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gemini-3-5-flash-medium-evals","aa-gemini-3-5-flash-medium-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for gemini-3-5-flash-medium","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-5-flash-medium","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-3-codex-evals","aa-gpt-5-3-codex-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for gpt-5-3-codex","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-3-codex","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-4-evals","aa-gpt-5-4-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for gpt-5-4","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-4","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-5-evals","aa-gpt-5-5-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for gpt-5-5","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-5","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-6-luna-evals","aa-gpt-5-6-luna-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for gpt-5-6-luna","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-luna","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-6-sol-evals","aa-gpt-5-6-sol-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for gpt-5-6-sol","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-sol","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-6-terra-evals","aa-gpt-5-6-terra-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for gpt-5-6-terra","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-terra","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-grok-4-3-evals","aa-grok-4-3-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for grok-4-3","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-3","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-grok-4-5-evals","aa-grok-4-5-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for grok-4-5","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-5","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-minimax-m3-evals","aa-minimax-m3-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for minimax-m3","Artificial Analysis","https://artificialanalysis.ai/models/minimax-m3","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-mistral-large-3-evals","aa-mistral-large-3-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for mistral-large-3","Artificial Analysis","https://artificialanalysis.ai/models/mistral-large-3","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-mistral-medium-3-5-evals","aa-mistral-medium-3-5-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for mistral-medium-3-5","Artificial Analysis","https://artificialanalysis.ai/models/mistral-medium-3-5","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-mistral-small-4-evals","aa-mistral-small-4-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for mistral-small-4","Artificial Analysis","https://artificialanalysis.ai/models/mistral-small-4","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-qwen3-7-max-evals","aa-qwen3-7-max-evals","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench","Artificial Analysis evaluations for qwen3-7-max","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-7-max","independent-lab","independent-lab","source-checked","benchmark evaluations|HLE|GPQA|MMMU-Pro|Terminal-Bench",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::benchlm-public-benchmarks","benchlm-public-benchmarks","benchmark leaderboard scores|model rankings","BenchLM public benchmark leaderboards","BenchLM","https://benchlm.ai/benchmarks","independent-lab","independent-lab","source-checked","benchmark leaderboard scores|model rankings","2026-07-15",null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,"Scores mirrored from BenchLM public benchmark pages for exact model variants in the LuminaBench cohort."],["production::meta-muse-spark-1-1-eval","meta-muse-spark-1-1-eval","benchmark result table|model configuration","Meta AI Muse Spark 1.1 evaluation report","Meta","https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report","official-provider-evaluation","official-provider-evaluation","source-checked","benchmark result table|model configuration","2026-07-09",null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::google-gemini-35-model-card","google-gemini-35-model-card","benchmark result table|model configuration|benchmark versions","Gemini 3.5 Flash model card","Google DeepMind","https://deepmind.google/models/model-cards/gemini-3-5-flash/","official-provider-evaluation","official-provider-evaluation","source-checked","benchmark result table|model configuration|benchmark versions","2026-05-19",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-claude-opus-4","aa-model-claude-opus-4","benchmark scores|pricing|context window","Claude Opus 4 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-4-opus-thinking","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-claude-opus-4-1","aa-model-claude-opus-4-1","benchmark scores|pricing|context window","Claude Opus 4.1 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-4-1-opus-thinking","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-claude-sonnet-3-7","aa-model-claude-sonnet-3-7","benchmark scores|pricing|context window","Claude Sonnet 3.7 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-3-7-sonnet-thinking","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-claude-sonnet-4","aa-model-claude-sonnet-4","benchmark scores|pricing|context window","Claude Sonnet 4 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-4-sonnet-thinking","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-claude-sonnet-4-5","aa-model-claude-sonnet-4-5","benchmark scores|pricing|context window","Claude Sonnet 4.5 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-command-a-plus","aa-model-command-a-plus","benchmark scores|pricing|context window","Command A+ | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/command-a-plus","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-deepseek-v3-1-terminus","aa-model-deepseek-v3-1-terminus","benchmark scores|pricing|context window","DeepSeek V3.1 Terminus | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v3-1-terminus-reasoning","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-deepseek-v3-2","aa-model-deepseek-v3-2","benchmark scores|pricing|context window","DeepSeek V3.2 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gemini-2-5-flash","aa-model-gemini-2-5-flash","benchmark scores|pricing|context window","Gemini 2.5 Flash | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gemini-2-5-flash-preview-09-2025-reasoning","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gemini-2-5-pro","aa-model-gemini-2-5-pro","benchmark scores|pricing|context window","Gemini 2.5 Pro | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gemini-2-5-pro","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gemma-4-12b","aa-model-gemma-4-12b","benchmark scores|pricing|context window","Gemma 4 12B | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gemma-4-12b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gemma-4-26b","aa-model-gemma-4-26b","benchmark scores|pricing|context window","Gemma 4 26B | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gemma-4-26b-a4b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-glm-4-6","aa-model-glm-4-6","benchmark scores|pricing|context window","GLM-4.6 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/glm-4-6-reasoning","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-glm-4-7","aa-model-glm-4-7","benchmark scores|pricing|context window","GLM-4.7 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/glm-4-7","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gpt-5","aa-model-gpt-5","benchmark scores|pricing|context window","GPT-5 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gpt-5-codex","aa-model-gpt-5-codex","benchmark scores|pricing|context window","GPT-5 Codex | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-codex","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gpt-5-mini","aa-model-gpt-5-mini","benchmark scores|pricing|context window","GPT-5 mini | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-mini-medium","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gpt-5-2","aa-model-gpt-5-2","benchmark scores|pricing|context window","GPT-5.2 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-2","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gpt-5-2-codex","aa-model-gpt-5-2-codex","benchmark scores|pricing|context window","GPT-5.2 Codex | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-2-codex","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-gpt-5-4-mini","aa-model-gpt-5-4-mini","benchmark scores|pricing|context window","GPT-5.4 mini | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-4-mini","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-grok-3-mini","aa-model-grok-3-mini","benchmark scores|pricing|context window","Grok 3 mini | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/grok-3-mini-reasoning","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-grok-4","aa-model-grok-4","benchmark scores|pricing|context window","Grok 4 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/grok-4","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-grok-4-fast","aa-model-grok-4-fast","benchmark scores|pricing|context window","Grok 4 Fast | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-fast-reasoning","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-grok-4-20","aa-model-grok-4-20","benchmark scores|pricing|context window","Grok 4.20 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-20","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-grok-code-fast-1","aa-model-grok-code-fast-1","benchmark scores|pricing|context window","Grok Code Fast 1 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/grok-code-fast-1","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-kimi-k2-0905","aa-model-kimi-k2-0905","benchmark scores|pricing|context window","Kimi K2 0905 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/kimi-k2-0905","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-kimi-k2-thinking","aa-model-kimi-k2-thinking","benchmark scores|pricing|context window","Kimi K2 Thinking | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/kimi-k2-thinking","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-kimi-k2-6","aa-model-kimi-k2-6","benchmark scores|pricing|context window","Kimi K2.6 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/kimi-k2-6","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-kimi-k2-7-code","aa-model-kimi-k2-7-code","benchmark scores|pricing|context window","Kimi K2.7 Code | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/kimi-k2-7-code","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-ling-2-6-1t","aa-model-ling-2-6-1t","benchmark scores|pricing|context window","Ling 2.6 1T | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/ling-2-6-1t","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-mimo-v2-flash","aa-model-mimo-v2-flash","benchmark scores|pricing|context window","MiMo-V2-Flash | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-mimo-v2-5","aa-model-mimo-v2-5","benchmark scores|pricing|context window","MiMo-V2.5 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/mimo-v2-5-0424","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-minimax-m2","aa-model-minimax-m2","benchmark scores|pricing|context window","MiniMax M2 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/minimax-m2","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-minimax-m2-1","aa-model-minimax-m2-1","benchmark scores|pricing|context window","MiniMax M2.1 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/minimax-m2-1","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-minimax-m2-5","aa-model-minimax-m2-5","benchmark scores|pricing|context window","MiniMax M2.5 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/minimax-m2-5","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-nemotron-3-super","aa-model-nemotron-3-super","benchmark scores|pricing|context window","Nemotron 3 Super | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-nemotron-3-ultra","aa-model-nemotron-3-ultra","benchmark scores|pricing|context window","Nemotron 3 Ultra | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-nova-2-pro","aa-model-nova-2-pro","benchmark scores|pricing|context window","Nova 2 Pro | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-o1","aa-model-o1","benchmark scores|pricing|context window","o1 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/o1","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-o3","aa-model-o3","benchmark scores|pricing|context window","o3 | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/o3","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-o3-pro","aa-model-o3-pro","benchmark scores|pricing|context window","o3-pro | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/o3-pro","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-o4-mini","aa-model-o4-mini","benchmark scores|pricing|context window","o4-mini | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/o4-mini","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-qwen3-max","aa-model-qwen3-max","benchmark scores|pricing|context window","Qwen3 Max | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-max-thinking","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-qwen3-5-122b","aa-model-qwen3-5-122b","benchmark scores|pricing|context window","Qwen3.5 122B | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-5-122b-a10b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-qwen3-5-27b","aa-model-qwen3-5-27b","benchmark scores|pricing|context window","Qwen3.5 27B | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-5-27b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-qwen3-5-35b","aa-model-qwen3-5-35b","benchmark scores|pricing|context window","Qwen3.5 35B | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-5-35b-a3b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-qwen3-5-397b","aa-model-qwen3-5-397b","benchmark scores|pricing|context window","Qwen3.5 397B | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-5-397b-a17b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-qwen3-5-omni-plus","aa-model-qwen3-5-omni-plus","benchmark scores|pricing|context window","Qwen3.5 Omni Plus | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-5-omni-plus","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-qwen3-6-27b","aa-model-qwen3-6-27b","benchmark scores|pricing|context window","Qwen3.6 27B | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-6-27b","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-qwen3-6-max","aa-model-qwen3-6-max","benchmark scores|pricing|context window","Qwen3.6 Max | Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-6-max","independent-lab","independent-lab","source-checked","benchmark scores|pricing|context window","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::google-gemini-36-blog","google-gemini-36-blog","benchmark scores|pricing|release status|token efficiency","Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber","Google","https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/","official-provider-evaluation","official-provider-evaluation","source-checked","benchmark scores|pricing|release status|token efficiency","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::google-gemini-36-product","google-gemini-36-product","benchmark table|model specifications|pricing","Gemini 3.6 Flash product page with evaluation table","Google DeepMind","https://deepmind.google/models/gemini/flash/","official-provider-evaluation","official-provider-evaluation","source-checked","benchmark table|model specifications|pricing","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::anthropic-claude-opus-5-launch","anthropic-claude-opus-5-launch","benchmark table|pricing|release status|model positioning vs Fable 5 and Opus 4.8|effort ladder notes","Introducing Claude Opus 5","Anthropic","https://www.anthropic.com/news/claude-opus-5","official-provider-evaluation","official-provider-evaluation","source-checked","benchmark table|pricing|release status|model positioning vs Fable 5 and Opus 4.8|effort ladder notes","2026-07-24",null,"2026-07-24",null,null,null,null,null,"source-checked",null,null,"Primary launch post with the public Opus 5 evaluation table and product positioning. Exact scores taken from the official table image and launch copy."],["production::terminal-bench-4-repository-release-2026-08-26","terminal-bench-4-repository-release-2026-08-26","benchmark-version|dataset identity|task changes|harness","Terminal-Bench v4.0.0 repository release","Harbor / Terminal-Bench","https://github.com/harbor-framework/terminal-bench/releases/tag/v4.0.0","official-repository","official-repository","source-checked","benchmark-version|dataset identity|task changes|harness","2026-08-26",null,"2026-08-30",null,"42a72e82cd3cf420c4ab2e89cd73fdac4c18a5d9822b3bda1ab051d84559a577",null,null,"metadata-only","source-checked",null,null,"Signed v4.0.0 repository release and exact Harbor dataset command."],["production::swe-bench-official-leaderboard-2026-08-29","swe-bench-official-leaderboard-2026-08-29","benchmark|benchmark-version|configuration|result|verification","SWE-bench official leaderboard data","SWE-bench","https://github.com/SWE-bench/swe-bench.github.io/blob/master/data/leaderboards.json","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|configuration|result|verification",null,null,"2026-08-29",null,"fa4b61d3167dfe99e1a834e007a38372c5bac07b7627f8e2c3904fb48cd4a006",null,null,"metadata-only","source-checked",null,null,"Official leaderboard checked for exact current-model corroboration. Kimi K2.5 is present under a high configuration that is not treated as interchangeable with Lumina's ranked default-thinking configuration."],["production::terminal-bench-4-leaderboard-2026-08-29","terminal-bench-4-leaderboard-2026-08-29","benchmark|benchmark-version|model-agent system|reasoning effort|evaluation date|result|trial count","Terminal-Bench 4.0 official leaderboard","Terminal-Bench","https://www.tbench.ai/leaderboard/terminal-bench/4.0","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|model-agent system|reasoning effort|evaluation date|result|trial count","2026-08-29",null,"2026-08-30",null,"4c6c3f3182ffc8a4598655797b28a2fddc33999b1781a0203080212ea220206a",null,null,"metadata-only","source-checked",null,null,"Official benchmark-owner leaderboard. Every row is retained as an exact model-plus-agent system and is reference-only for ranking."],["production::refresh-aider-leaderboard","refresh-aider-leaderboard","benchmark|benchmark-version|result","Aider permanent refresh source","Aider","https://aider.chat/docs/leaderboards/","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Aider source terms","Aider (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aider-leaderboard-reviewed-html@2.0.0; role manual-review."],["production::refresh-arc-prize","refresh-arc-prize","benchmark|benchmark-version|result","ARC Prize permanent refresh source","ARC Prize","https://arcprize.org/leaderboard","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"ARC Prize source terms","ARC Prize (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter arc-prize-reviewed-html@2.0.0; role manual-review."],["production::refresh-bfcl","refresh-bfcl","benchmark|benchmark-version|result","Berkeley Function Calling Leaderboard permanent refresh source","Berkeley Function Calling Leaderboard","https://gorilla.cs.berkeley.edu/leaderboard.html","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Berkeley Function Calling Leaderboard source terms","Berkeley Function Calling Leaderboard (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter bfcl-reviewed-html@2.0.0; role manual-review."],["production::refresh-humanitys-last-exam","refresh-humanitys-last-exam","benchmark|benchmark-version|result","Center for AI Safety permanent refresh source","Center for AI Safety","https://agi.safe.ai/","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Center for AI Safety source terms","Center for AI Safety (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter humanitys-last-exam-reviewed-html@2.0.0; role manual-review."],["production::refresh-frontiermath-v1","refresh-frontiermath-v1","benchmark|benchmark-version|result","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/frontiermath","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter frontiermath-v1-reviewed-html@2.0.0; role historical."],["production::refresh-frontiermath-v2-tier-4","refresh-frontiermath-v2-tier-4","benchmark|benchmark-version|result","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/benchmarks/frontiermath-tier-4-v2","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter frontiermath-v2-tier-4-reviewed-html@2.0.0; role manual-review."],["production::refresh-frontiermath-v2-tiers-1-3","refresh-frontiermath-v2-tiers-1-3","benchmark|benchmark-version|result","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter frontiermath-v2-tiers-1-3-reviewed-html@2.0.0; role manual-review."],["production::refresh-livecodebench","refresh-livecodebench","benchmark|benchmark-version|result","LiveCodeBench permanent refresh source","LiveCodeBench","https://livecodebench.github.io/leaderboard.html","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"LiveCodeBench source terms","LiveCodeBench (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter livecodebench-reviewed-html@2.0.0; role manual-review."],["production::refresh-livecodebench-repo","refresh-livecodebench-repo","benchmark|benchmark-version|result","LiveCodeBench permanent refresh source","LiveCodeBench","https://github.com/LiveCodeBench/LiveCodeBench","official-repository","official-repository","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-08",null,null,"LiveCodeBench source terms","LiveCodeBench (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter livecodebench-repo-github-api@2.0.0; role release-triggered."],["production::refresh-mathvista","refresh-mathvista","benchmark|benchmark-version|result","MathVista permanent refresh source","MathVista","https://mathvista.github.io/","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"MathVista source terms","MathVista (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter mathvista-reviewed-html@2.0.0; role manual-review."],["production::refresh-mmmu","refresh-mmmu","benchmark|benchmark-version|result","MMMU permanent refresh source","MMMU","https://mmmu-benchmark.github.io/","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"MMMU source terms","MMMU (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter mmmu-reviewed-html@2.0.0; role manual-review."],["production::refresh-osworld-20","refresh-osworld-20","benchmark|benchmark-version|result","OSWorld permanent refresh source","OSWorld","https://osworld-v2.xlang.ai/","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"OSWorld source terms","OSWorld (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter osworld-20-reviewed-html@2.0.0; role manual-review."],["production::refresh-osworld-20-repo","refresh-osworld-20-repo","benchmark|benchmark-version|result","OSWorld permanent refresh source","OSWorld","https://github.com/xlang-ai/OSWorld-V2","official-repository","official-repository","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-08",null,null,"OSWorld source terms","OSWorld (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter osworld-20-repo-github-api@2.0.0; role release-triggered."],["production::refresh-osworld-v1","refresh-osworld-v1","benchmark|benchmark-version|result","OSWorld permanent refresh source","OSWorld","https://os-world.github.io/","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"OSWorld source terms","OSWorld (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter osworld-v1-reviewed-html@2.0.0; role historical."],["production::refresh-scale-seal","refresh-scale-seal","benchmark|benchmark-version|result","Scale AI permanent refresh source","Scale AI","https://labs.scale.com/leaderboard","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Scale AI source terms","Scale AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter scale-seal-reviewed-html@2.0.0; role manual-review."],["production::refresh-tau-bench-current","refresh-tau-bench-current","benchmark|benchmark-version|result","Sierra Research permanent refresh source","Sierra Research","https://tau-bench.com/","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Sierra Research source terms","Sierra Research (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter tau-bench-current-reviewed-html@2.0.0; role manual-review."],["production::refresh-tau-bench-legacy","refresh-tau-bench-legacy","benchmark|benchmark-version|result","Sierra Research permanent refresh source","Sierra Research","https://github.com/sierra-research/tau-bench","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Sierra Research source terms","Sierra Research (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter tau-bench-legacy-reviewed-html@2.0.0; role historical."],["production::refresh-tau2-bench-repo","refresh-tau2-bench-repo","benchmark|benchmark-version|result","Sierra Research permanent refresh source","Sierra Research","https://github.com/sierra-research/tau2-bench","official-repository","official-repository","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-08",null,null,"Sierra Research source terms","Sierra Research (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter tau2-bench-repo-github-api@2.0.0; role release-triggered."],["production::refresh-swe-bench-results","refresh-swe-bench-results","benchmark|benchmark-version|result","SWE-bench permanent refresh source","SWE-bench","https://github.com/SWE-bench/experiments","official-repository","official-repository","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-23",null,null,"SWE-bench source terms","SWE-bench (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter swe-bench-results-v3@3.0.0; role release-triggered."],["production::refresh-swe-bench-site","refresh-swe-bench-site","benchmark|benchmark-version|result","SWE-bench permanent refresh source","SWE-bench","https://www.swebench.com/","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"SWE-bench source terms","SWE-bench (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter swe-bench-site-reviewed-html@2.0.0; role manual-review."],["production::refresh-terminal-bench-21","refresh-terminal-bench-21","benchmark|benchmark-version|result","Terminal-Bench permanent refresh source","Terminal-Bench","https://www.tbench.ai/leaderboard/terminal-bench/2.1","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Terminal-Bench source terms","Terminal-Bench (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter terminal-bench-21-reviewed-html@2.0.0; role manual-review."],["production::refresh-terminal-bench-21-repo","refresh-terminal-bench-21-repo","benchmark|benchmark-version|result","Terminal-Bench permanent refresh source","Terminal-Bench","https://github.com/harbor-framework/terminal-bench-2-1","official-repository","official-repository","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-08",null,null,"Terminal-Bench source terms","Terminal-Bench (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter terminal-bench-21-repo-github-api@2.0.0; role release-triggered."],["production::refresh-vals-ai","refresh-vals-ai","benchmark|benchmark-version|result","Vals AI permanent refresh source","Vals AI","https://www.vals.ai/benchmarks","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Vals AI source terms","Vals AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter vals-ai-reviewed-html@2.0.0; role manual-review."],["production::refresh-video-mme-v1","refresh-video-mme-v1","benchmark|benchmark-version|result","Video-MME permanent refresh source","Video-MME","https://video-mme.github.io/home_page.html","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-07",null,null,"Video-MME source terms","Video-MME (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter video-mme-v1-reviewed-html@2.0.0; role historical."],["production::refresh-video-mme-v2","refresh-video-mme-v2","benchmark|benchmark-version|result","Video-MME permanent refresh source","Video-MME","https://github.com/MME-Benchmarks/Video-MME-v2","official-repository","official-repository","source-checked","benchmark|benchmark-version|result",null,null,"2026-08-08",null,null,"Video-MME source terms","Video-MME (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter video-mme-v2-github-api@2.0.0; role release-triggered."],["production::refresh-epoch-benchmark-archive","refresh-epoch-benchmark-archive","benchmark|benchmark-version|result|discovery","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/data/benchmark_data.zip","independent-registry","independent-registry","source-checked","benchmark|benchmark-version|result|discovery",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter epoch-benchmark-zip-v2@2.0.0; role historical."],["production::refresh-open-asr","refresh-open-asr","benchmark|benchmark-version|result|media","Hugging Face permanent refresh source","Hugging Face","https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","official-leaderboard","official-leaderboard","source-checked","benchmark|benchmark-version|result|media",null,null,"2026-08-07",null,null,"Hugging Face source terms","Hugging Face (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter open-asr-reviewed-html@2.0.0; role manual-review."],["production::refresh-open-asr-repo","refresh-open-asr-repo","benchmark|benchmark-version|result|media","Hugging Face permanent refresh source","Hugging Face","https://github.com/huggingface/open_asr_leaderboard","official-repository","official-repository","source-checked","benchmark|benchmark-version|result|media",null,null,"2026-08-08",null,null,"Hugging Face source terms","Hugging Face (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter open-asr-repo-github-api@2.0.0; role release-triggered."],["production::refresh-i2i-bench","refresh-i2i-bench","benchmark|benchmark-version|result|media","I2I-Bench permanent refresh source","I2I-Bench","https://github.com/IntMeGroup/I2I-Bench","official-repository","official-repository","source-checked","benchmark|benchmark-version|result|media",null,null,"2026-08-08",null,null,"I2I-Bench source terms","I2I-Bench (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter i2i-bench-github-api@2.0.0; role release-triggered."],["production::aa-evaluation-artificial-analysis-long-context-reasoning-2026-08-27","aa-evaluation-artificial-analysis-long-context-reasoning-2026-08-27","benchmark|benchmark-version|result|verification","Artificial Analysis aa-lcr evaluation","Artificial Analysis","https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","independent-lab","independent-lab","source-checked","benchmark|benchmark-version|result|verification",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Individual evaluation page states that Artificial Analysis conducts the evaluation independently and documents the benchmark-specific metric or harness."],["production::aa-evaluation-critpt-2026-08-27","aa-evaluation-critpt-2026-08-27","benchmark|benchmark-version|result|verification","Artificial Analysis critpt evaluation","Artificial Analysis","https://artificialanalysis.ai/evaluations/critpt","independent-lab","independent-lab","source-checked","benchmark|benchmark-version|result|verification",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Individual evaluation page states that Artificial Analysis conducts the evaluation independently and documents the benchmark-specific metric or harness."],["production::aa-evaluation-gdpval-aa-2026-08-27","aa-evaluation-gdpval-aa-2026-08-27","benchmark|benchmark-version|result|verification","Artificial Analysis gdpval-aa evaluation","Artificial Analysis","https://artificialanalysis.ai/evaluations/gdpval-aa","independent-lab","independent-lab","source-checked","benchmark|benchmark-version|result|verification",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Individual evaluation page states that Artificial Analysis conducts the evaluation independently and documents the benchmark-specific metric or harness."],["production::aa-evaluation-gpqa-diamond-2026-08-27","aa-evaluation-gpqa-diamond-2026-08-27","benchmark|benchmark-version|result|verification","Artificial Analysis gpqa-diamond evaluation","Artificial Analysis","https://artificialanalysis.ai/evaluations/gpqa-diamond","independent-lab","independent-lab","source-checked","benchmark|benchmark-version|result|verification",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Individual evaluation page states that Artificial Analysis conducts the evaluation independently and documents the benchmark-specific metric or harness."],["production::aa-evaluation-humanitys-last-exam-2026-08-27","aa-evaluation-humanitys-last-exam-2026-08-27","benchmark|benchmark-version|result|verification","Artificial Analysis humanitys-last-exam evaluation","Artificial Analysis","https://artificialanalysis.ai/evaluations/humanitys-last-exam","independent-lab","independent-lab","source-checked","benchmark|benchmark-version|result|verification",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Individual evaluation page states that Artificial Analysis conducts the evaluation independently and documents the benchmark-specific metric or harness."],["production::aa-evaluation-scicode-2026-08-27","aa-evaluation-scicode-2026-08-27","benchmark|benchmark-version|result|verification","Artificial Analysis scicode evaluation","Artificial Analysis","https://artificialanalysis.ai/evaluations/scicode","independent-lab","independent-lab","source-checked","benchmark|benchmark-version|result|verification",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Individual evaluation page states that Artificial Analysis conducts the evaluation independently and documents the benchmark-specific metric or harness."],["production::aa-evaluation-tau3-banking-2026-08-27","aa-evaluation-tau3-banking-2026-08-27","benchmark|benchmark-version|result|verification","Artificial Analysis tau3-banking evaluation","Artificial Analysis","https://artificialanalysis.ai/evaluations/tau3-banking","independent-lab","independent-lab","source-checked","benchmark|benchmark-version|result|verification",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Individual evaluation page states that Artificial Analysis conducts the evaluation independently and documents the benchmark-specific metric or harness."],["production::aa-evaluation-terminalbench-v2-1-2026-08-27","aa-evaluation-terminalbench-v2-1-2026-08-27","benchmark|benchmark-version|result|verification","Artificial Analysis terminal-bench evaluation","Artificial Analysis","https://artificialanalysis.ai/evaluations/terminalbench-v2-1","independent-lab","independent-lab","source-checked","benchmark|benchmark-version|result|verification",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Individual evaluation page states that Artificial Analysis conducts the evaluation independently and documents the benchmark-specific metric or harness."],["production::terminal-bench-4-release-2026-08-28","terminal-bench-4-release-2026-08-28","benchmark|benchmark-version|task set|resource policy|lifecycle|verification","Terminal-Bench 4.0 release","Terminal-Bench","https://www.tbench.ai/news/terminal-bench-4-0","official-docs","official-docs","source-checked","benchmark|benchmark-version|task set|resource policy|lifecycle|verification","2026-08-28",null,"2026-08-30",null,"0a4a25b8c2e0c015016cb0111d00c1ed3622535e7092b8b689191792213b9a84",null,null,"metadata-only","source-checked",null,null,"Official release article: 4.0 is a breaking semantic-version update with 66 tasks, eight removals, 19 fixes, and a flat eight-hour agent timeout."],["production::refresh-benchlm-benchmarks","refresh-benchlm-benchmarks","benchmark|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/data/benchmarks.json","independent-registry","independent-registry","source-checked","benchmark|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-corroboration-v2@2.0.0; role corroboration."],["production::refresh-gaia-space-legacy","refresh-gaia-space-legacy","benchmark|result|discovery","GAIA permanent refresh source","GAIA","https://huggingface.co/spaces/gaia-benchmark/leaderboard","official-leaderboard","official-leaderboard","source-checked","benchmark|result|discovery",null,null,"2026-08-07",null,null,"GAIA source terms","GAIA (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter gaia-space-legacy-reviewed-html@2.0.0; role historical."],["production::benchlm-browsecomp-2026-07-20","benchlm-browsecomp-2026-07-20","BrowseComp accuracy","BrowseComp Leaderboard & Scores — July 2026","BenchLM","https://benchlm.ai/benchmarks/browsecomp","independent-lab","independent-lab","source-checked","BrowseComp accuracy","2026-07-20",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::nvidia-nemotron-3-5-lightning-model-card-ce38b6ab","nvidia-nemotron-3-5-lightning-model-card-ce38b6ab","canonical identity|BF16 and NVFP4 offerings|30B total and 3B active parameters|1M context|OpenMDW-1.1 licence|14 exact release-evaluation rows|reproducibility harness","NVIDIA Nemotron 3.5 Lightning 30B-A3B BF16 model card","NVIDIA","https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16/blob/ce38b6ab8b252b4b8ee7165b4605e93191cafd73/README.md","official-model-card","official-model-card","source-checked","canonical identity|BF16 and NVFP4 offerings|30B total and 3B active parameters|1M context|OpenMDW-1.1 licence|14 exact release-evaluation rows|reproducibility harness","2026-08-11",null,"2026-08-12","ce38b6ab8b252b4b8ee7165b4605e93191cafd73","c8d4288b5f9fb3a09f5148e155063cdab58dd3dce53b588ffe3a3a849a929801","OpenMDW-1.1","NVIDIA model card","metadata-only","source-checked",null,null,"README resolved at immutable Hugging Face commit ce38b6ab8b252b4b8ee7165b4605e93191cafd73 and SHA-256 checked. NVIDIA states that results use a consistent NeMo Gym / NeMo Evaluator SDK harness and may differ from vendor self-reports."],["production::xai-grok-4-6-release-2026-08-12","xai-grok-4-6-release-2026-08-12","canonical identity|release date|availability|nine non-index evaluation rows|four exact comparison configurations|starting API price","Grok 4.6","xAI","https://x.ai/news/grok-4-6","official-provider-evaluation","official-provider-evaluation","source-checked","canonical identity|release date|availability|nine non-index evaluation rows|four exact comparison configurations|starting API price","2026-08-12",null,"2026-08-12","sha256:9e3e881d6f52bab62a9a4678e9704d523cabc44989e81afda992fd7651e1c94e","9e3e881d6f52bab62a9a4678e9704d523cabc44989e81afda992fd7651e1c94e","xAI website terms","xAI Grok 4.6 release table","metadata-only","source-checked",null,null,"Official release HTML fetched directly on 2026-08-12. The Artificial Analysis Intelligence Index row is intentionally excluded; the remaining nine source-published evaluation rows are retained as provider-reported evidence."],["production::qwen-qwen38-release-2026-08-03","qwen-qwen38-release-2026-08-03","canonical model identity|release lifecycle|architecture|context and reasoning configurations|benchmark result table|evaluation harness notes|announced weight release","Qwen3.8 Max official release","Qwen","https://qwen.ai/blog?id=qwen3.8","official-model-card","official-model-card","source-checked","canonical model identity|release lifecycle|architecture|context and reasoning configurations|benchmark result table|evaluation harness notes|announced weight release","2026-08-03",null,"2026-08-05",null,null,null,null,null,"source-checked",null,null,"Official Qwen3.8 Max release, benchmark table, and evaluation footnotes. Pricing is verified separately against the official QwenCloud model catalogue."],["production::benchlm-leaderboard-2026-07-16","benchlm-leaderboard-2026-07-16","category scores|list prices|overall consensus","BenchLM leaderboard snapshot 2026-07-16","BenchLM","https://benchlm.ai/api/data/leaderboard?mode=bench-align-v5&limit=300","independent-lab","independent-lab","source-checked","category scores|list prices|overall consensus","2026-07-14",null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::cursor-bench-public","cursor-bench-public","coding agent scores","CursorBench public evaluation via BenchLM","Cursor / BenchLM","https://benchlm.ai/benchmarks/cursorBench","independent-lab","independent-lab","source-checked","coding agent scores","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::refresh-livebench","refresh-livebench","complete comparison table|benchmark version|source-native model configuration|Reasoning category and subtask scores","LiveBench 2026-06-25 complete owner table","LiveBench","https://livebench.ai/","official-leaderboard","official-leaderboard","source-checked","complete comparison table|benchmark version|source-native model configuration|Reasoning category and subtask scores","2026-06-25",null,"2026-08-15","page:f7cf0c526daff3881f40f61d7fd6584909a5413b116ae1a1f3f347742efa0502;table:ef6e0cb799d4ebaa955cbb235dd7203f53909d8020226ce6d559c0dc03e07913;categories:dad300ad18655b69db720e1b88fc5a5eac06c5b2f0e52c2bf50f10ff057674f3","9fbefcd337e14f3374a90bd2bd810dfebfe2d53b8802770a9650bb2ec0025a65","LiveBench source terms","LiveBench (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"The complete 43-row owner table was parsed with all seven categories. Only the owner-defined Reasoning partition is admitted under the existing livebench methodology mapping; other partitions remain in the immutable extraction artifact and do not create new pillar mappings."],["production::refresh-google-gemini-3-7-flash-evaluation","refresh-google-gemini-3-7-flash-evaluation","configuration|benchmark|benchmark-version|result|verification","Google DeepMind permanent refresh source","Google DeepMind","https://storage.googleapis.com/deepmind-media/gemini/gemini_3-7_flash_model_evaluation.pdf","official-docs","official-docs","source-checked","configuration|benchmark|benchmark-version|result|verification",null,null,"2026-08-15",null,null,"Google DeepMind source terms","Google DeepMind (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter google-gemini-3-7-flash-evaluation-reviewed-html@2.0.0; role release-triggered."],["production::xiaomi-mimo-v2-5-pro-agent-docs-2026-08-30","xiaomi-mimo-v2-5-pro-agent-docs-2026-08-30","configuration|specification|availability","MiMo-V2.5-Pro agent integration details","Xiaomi MiMo","https://raw.githubusercontent.com/XiaomiMiMo/awesome-mimo-agent/main/docs/oh-my-pi.md","official-repository","official-repository","source-checked","configuration|specification|availability",null,null,"2026-08-30",null,"2050f7b232222133a89c9eed13185f79b004d8ff83225f62a6aca36f9ac6e3f9",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 2050f7b232222133a89c9eed13185f79b004d8ff83225f62a6aca36f9ac6e3f9."],["production::alibaba-glm-5-2-detail-2026-08-30","alibaba-glm-5-2-detail-2026-08-30","configuration|specification|availability|pricing","glm-5.2 hosted model details","Alibaba Cloud Model Studio","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/glm-5-2","official-docs","official-docs","source-checked","configuration|specification|availability|pricing",null,null,"2026-08-30",null,"1bb4d45965d48bd2ea7a2c7faa26946a5b3aee622b86b92e223e9dd7cd2a1269",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 1bb4d45965d48bd2ea7a2c7faa26946a5b3aee622b86b92e223e9dd7cd2a1269."],["production::meta-muse-spark-1-2-multimodal-methodology-2026-08-20","meta-muse-spark-1-2-multimodal-methodology-2026-08-20","configuration|specification|result|verification","Muse Spark 1.2 multimodal evaluation methodology","Meta Superintelligence Labs","https://research.meta.ai/static/muse-spark-1-2-multimodal-evaluation-methodology","official-paper","official-paper","source-checked","configuration|specification|result|verification","2026-08-20",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Official four-page methodology covering effort settings, tool containers, image handling, benchmark sampling and judging."],["production::refresh-deepseek-thinking-mode","refresh-deepseek-thinking-mode","configuration|specification|verification","DeepSeek permanent refresh source","DeepSeek","https://api-docs.deepseek.com/guides/thinking_mode","official-docs","official-docs","source-checked","configuration|specification|verification",null,null,"2026-08-15",null,null,"DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter deepseek-thinking-mode-reviewed-html@2.0.0; role release-triggered."],["production::longcat-default-thinking-docs-2026-08-29","longcat-default-thinking-docs-2026-08-29","configuration|verification","LongCat 2.0 thinking-mode documentation","LongCat","https://longcat.chat/platform/docs/OpenCode.html","official-docs","official-docs","source-checked","configuration|verification",null,null,"2026-08-29",null,"9860c822121fbb159c381ac4a8f4a2b75f4a53bd6c553d64c30cde4093d21ff3",null,null,"metadata-only","source-checked",null,null,"Current first-party LongCat API documentation checked during the saturation pass."],["production::livebench-2026-06-25","livebench-2026-06-25","contamination-free multi-category scores","LiveBench 2026-06-25 release","LiveBench","https://livebench.ai/","official-leaderboard","official-leaderboard","source-checked","contamination-free multi-category scores","2026-06-25",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::meta-muse-spark-1-2-developer-2026-08-05","meta-muse-spark-1-2-developer-2026-08-05","context window|input token price|cached input token price|output token price|data-use condition|tool calling|API availability","Muse Spark 1.2 model and pricing","Meta","https://developer.meta.com/ai/models/muse-spark/","official-docs","official-docs","source-checked","context window|input token price|cached input token price|output token price|data-use condition|tool calling|API availability",null,null,"2026-08-05",null,null,null,null,null,"source-checked",null,null,"Official Meta developer page lists two 1M-context endpoints: standard muse-spark-1.2 at $1.25 input, $0.15 cached input, and $4.25 output, and muse-spark-1.2-contributor at $0.10 input, $0.002 cached input, and $0.20 output per million tokens. Meta labels the contributor endpoint as used to improve its products."],["production::aa-critpt-leaderboard","aa-critpt-leaderboard","CritPt accuracy","CritPt Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/critpt","independent-lab","independent-lab","source-checked","CritPt accuracy","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::google-gemini-models-2026-08-03","google-gemini-models-2026-08-03","current model identity|preview lifecycle|deprecated model catalogue","Gemini API model catalogue","Google","https://ai.google.dev/gemini-api/docs/models","official-docs","official-docs","source-checked","current model identity|preview lifecycle|deprecated model catalogue",null,null,"2026-08-03",null,null,null,null,null,"source-checked",null,null,"The current catalogue lists Gemini 3.1 Pro as Preview and does not publish a separate stable gemini-3.1-pro endpoint."],["production::cursorbench-fable-5-1-2026-09-01","cursorbench-fable-5-1-2026-09-01","CursorBench 3.2.0 score|effort configuration|cost|tokens|steps","CursorBench 3.2.0 cost savings benchmark table","Cursor","https://cursor.com/en-US/cost-savings","official-leaderboard","official-leaderboard","source-checked","CursorBench 3.2.0 score|effort configuration|cost|tokens|steps","2026-09-01",null,"2026-09-01",null,null,null,null,"metadata-only","source-checked",null,null,"Cursor's first-party table independently reports Fable 5.1 Max at 73.4%, with $9.64 cost, 72,060 tokens and 70 steps."],["production::cybergym-official","cybergym-official","cybersecurity vulnerability agent benchmark","CyberGym repository","UC Berkeley SunBlaze","https://github.com/sunblaze-ucb/cybergym","official-repository","official-repository","source-checked","cybersecurity vulnerability agent benchmark",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::deepswe-leaderboard","deepswe-leaderboard","DeepSWE accuracy|mini-SWE-agent harness","DeepSWE leaderboard","DataCurve","https://deepswe.datacurve.ai/","official-leaderboard","official-leaderboard","source-checked","DeepSWE accuracy|mini-SWE-agent harness",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::deepswe-datacurve","deepswe-datacurve","DeepSWE v1.1 scores|thinking level","DeepSWE public leaderboard","DataCurve","https://deepswe.datacurve.ai/","official-leaderboard","official-leaderboard","source-checked","DeepSWE v1.1 scores|thinking level",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::xiaomi-mimo-v2-flash-deprecation-2026-07-27","xiaomi-mimo-v2-flash-deprecation-2026-07-27","deprecation status|routing to MiMo V2.5","MiMo-V2-Flash routing and deprecation notice","Xiaomi MiMo","https://platform.xiaomimimo.com/token-plan?planCode=pro%3Ayear","official-docs","official-docs","source-checked","deprecation status|routing to MiMo V2.5",null,null,"2026-07-27",null,null,null,null,null,"source-checked",null,null,"Provider notice says MiMo-V2-Flash auto-routed to V2.5 in June 2026 and was fully deprecated by 30 June 2026."],["production::refresh-huggingface-recent-models","refresh-huggingface-recent-models","discovery","Hugging Face permanent refresh source","Hugging Face","https://huggingface.co/api/models?sort=lastModified&direction=-1&limit=100","independent-registry","independent-registry","source-checked","discovery",null,null,"2026-08-07",null,null,"Hugging Face source terms","Hugging Face (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter huggingface-discovery-v2@2.0.0; role discovery-only."],["production::anthropic-fable-5-1-prompting-2026-09-01","anthropic-fable-5-1-prompting-2026-09-01","effort levels|default effort|model behavior","Prompting Claude Fable 5.1","Anthropic","https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1","official-docs","official-docs","source-checked","effort levels|default effort|model behavior","2026-09-01",null,"2026-09-01",null,null,null,null,"metadata-only","source-checked",null,null,"Official prompting guidance documents low, medium, high, xhigh and max effort controls, with high as the starting default."],["production::google-gemini-deprecations-2026-08-03","google-gemini-deprecations-2026-08-03","endpoint shutdown date|replacement endpoint|lifecycle status","Gemini API deprecations","Google","https://ai.google.dev/gemini-api/docs/deprecations","official-docs","official-docs","source-checked","endpoint shutdown date|replacement endpoint|lifecycle status",null,null,"2026-08-03",null,null,null,null,null,"source-checked",null,null,"Google records gemini-3-pro-preview as shut down on 9 March 2026 and recommends gemini-3.1-pro-preview."],["production::aa-enterpriseops-gym","aa-enterpriseops-gym","EnterpriseOps-Gym success","EnterpriseOps-Gym-AA Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","independent-lab","independent-lab","source-checked","EnterpriseOps-Gym success","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::meta-muse-glimmer-30b-methodology-2026-08-10","meta-muse-glimmer-30b-methodology-2026-08-10","exact High reasoning configuration|temperature|top_p|top_k|evaluation harnesses|benchmark versions|benchmark scores","Muse Glimmer Evaluation Methodology","Meta Superintelligence Lab","https://research.meta.ai/static/muse-glimmer-methodology","official-provider-evaluation","official-provider-evaluation","source-checked","exact High reasoning configuration|temperature|top_p|top_k|evaluation harnesses|benchmark versions|benchmark scores","2026-08-10",null,"2026-08-10",null,"fb08920ab31c5df3e07e2c3b32856d80d65a48dd14864f42bce8a1ac38026c91",null,null,null,"source-checked",null,null,"Official seven-page methodology PDF captured and SHA-256 checked on 2026-08-10. It states that every Muse Glimmer benchmark used High reasoning with temperature=1.0, top_p=0.95, and top_k=64."],["production::artificial-analysis-data-api-2026-07-27","artificial-analysis-data-api-2026-07-27","exact model configuration|independent benchmark rows|pricing|runtime observations|display-only composite indices","Artificial Analysis LLM data API — 2026-07-27","Artificial Analysis","https://artificialanalysis.ai/api/v2/data/llms/models","independent-lab","independent-lab","source-checked","exact model configuration|independent benchmark rows|pricing|runtime observations|display-only composite indices","2026-07-27",null,"2026-07-27",null,null,null,null,null,"source-checked",null,null,"Authenticated API data requires attribution. Raw API payloads are not committed; current direct benchmark rows supersede older observations from the same exact configuration."],["production::artificial-analysis-data-api-2026-08-01","artificial-analysis-data-api-2026-08-01","exact model configuration|independent benchmark rows|pricing|runtime observations|display-only composite indices","Artificial Analysis LLM data API — 2026-08-01","Artificial Analysis","https://artificialanalysis.ai/api/v2/data/llms/models","independent-lab","independent-lab","source-checked","exact model configuration|independent benchmark rows|pricing|runtime observations|display-only composite indices","2026-08-01",null,"2026-08-01",null,null,null,null,null,"source-checked",null,null,"Authenticated exact-variant API data is retained with source dates. Composite indices remain display-only; benchmark fields are admitted only with the exact API variant attached."],["production::swe-bench-experiments-2026-08-01","swe-bench-experiments-2026-08-01","experiment files|evaluation configurations|repository-derived benchmark reference","SWE-bench experiments repository — 2026-08-01","SWE-bench","https://github.com/SWE-bench/experiments","official-repository","official-repository","source-checked","experiment files|evaluation configurations|repository-derived benchmark reference",null,null,"2026-08-01",null,null,null,null,null,"source-checked",null,null,"Repository state is checked for experiment and result discovery. Rows without a complete, exact harness configuration remain reference-only."],["production::benchlm-exploitbench","benchlm-exploitbench","ExploitBench score","ExploitBench via BenchLM","BenchLM / ExploitBench","https://benchlm.ai/benchmarks/exploitBench","independent-lab","independent-lab","source-checked","ExploitBench score","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::refresh-benchlm-api-leaderboard","refresh-benchlm-api-leaderboard","external-identity|external-index|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/api/data/leaderboard","independent-registry","independent-registry","source-checked","external-identity|external-index|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-leaderboard-v2@2.0.0; role automatic."],["production::refresh-arena-owner-dataset","refresh-arena-owner-dataset","external-identity|external-index|result|media|verification","Arena permanent refresh source","Arena","https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","official-leaderboard","official-leaderboard","source-checked","external-identity|external-index|result|media|verification",null,null,"2026-08-08",null,null,"Arena source terms","Arena (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter arena-huggingface-dataset-v2@2.1.0; role automatic."],["production::refresh-benchlm-models","refresh-benchlm-models","external-identity|specification|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/data/models.json","independent-registry","independent-registry","source-checked","external-identity|specification|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-corroboration-v2@2.0.0; role corroboration."],["production::refresh-benchlm-comparisons","refresh-benchlm-comparisons","external-index|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/data/comparisons.json","independent-registry","independent-registry","source-checked","external-index|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-corroboration-v2@2.0.0; role corroboration."],["production::refresh-benchlm-leaderboard","refresh-benchlm-leaderboard","external-index|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/data/leaderboard.json","independent-registry","independent-registry","source-checked","external-index|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-corroboration-v2@2.0.0; role corroboration."],["production::frontierswe-site","frontierswe-site","FrontierSWE dominance","FrontierSWE official leaderboard","FrontierSWE","https://www.frontierswe.com/","official-leaderboard","official-leaderboard","source-checked","FrontierSWE dominance",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::benchlm-gaia","benchlm-gaia","GAIA accuracy","GAIA leaderboard via BenchLM","BenchLM / GAIA","https://benchlm.ai/benchmarks/gaia","independent-lab","independent-lab","source-checked","GAIA accuracy","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,"Scores mirrored from BenchLM GAIA page for exact named model variants only."],["production::aa-gdpval-aa","aa-gdpval-aa","GDPval-AA Elo / normalized","GDPval-AA v2 Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/gdpval-aa","independent-lab","independent-lab","source-checked","GDPval-AA Elo / normalized","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::benchlm-gdpval-aa-normalized-2026-07-20","benchlm-gdpval-aa-normalized-2026-07-20","GDPval-AA normalized percent","GDPval-AA Normalized Leaderboard & Scores — July 2026","BenchLM","https://benchlm.ai/benchmarks/gdpvalAaNormalized","independent-lab","independent-lab","source-checked","GDPval-AA normalized percent","2026-07-20",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-global-mmlu-lite","aa-global-mmlu-lite","Global-MMLU-Lite accuracy","Global-MMLU-Lite Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/global-mmlu-lite","independent-lab","independent-lab","source-checked","Global-MMLU-Lite accuracy","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::google-gemini-36-evals-methodology","google-gemini-36-evals-methodology","harness notes|benchmark protocols|result methodology","Gemini 3.6 Flash evaluation methodology","Google DeepMind","https://deepmind.google/models/evals-methodology/gemini-3-6-flash","official-provider-evaluation","official-provider-evaluation","source-checked","harness notes|benchmark protocols|result methodology","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-harvey-lab","aa-harvey-lab","Harvey LAB all-pass rate","Harvey LAB-AA Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/harvey-lab-aa","independent-lab","independent-lab","source-checked","Harvey LAB all-pass rate","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::openai-healthbench","openai-healthbench","HealthBench Hard","HealthBench (OpenAI)","OpenAI","https://openai.com/index/healthbench/","official-docs","official-docs","source-checked","HealthBench Hard",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::epoch-ai-datasets-2026-08-01","epoch-ai-datasets-2026-08-01","historical model reference|benchmark dataset reference","Epoch AI model and benchmark datasets — 2026-08-01","Epoch AI","https://epoch.ai/data/ai_models.zip","independent-lab","independent-lab","source-checked","historical model reference|benchmark dataset reference","2026-08-01",null,"2026-08-01",null,null,null,null,null,"source-checked",null,null,"ZIP datasets are retained as hashed reference inputs. Their heterogeneous historical records are not treated as interchangeable frontier benchmark rows."],["production::aa-hle-leaderboard","aa-hle-leaderboard","HLE accuracy","Humanity's Last Exam leaderboard (AA)","Artificial Analysis","https://artificialanalysis.ai/evaluations/humanitys-last-exam","independent-lab","independent-lab","source-checked","HLE accuracy",null,null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::qwen3-8-flash-next-modelscope-2026-08-26","qwen3-8-flash-next-modelscope-2026-08-26","identity|availability|verification","Qwen3.8-Flash-Next official ModelScope weights","Qwen","https://modelscope.cn/models/Qwen/Qwen3.8-Flash-Next","official-model-card","official-model-card","source-checked","identity|availability|verification","2026-08-26",null,"2026-08-26",null,null,null,null,"metadata-only","source-checked",null,null,"Official exact-name ModelScope repository, checked as a second provider-owned weight distribution surface."],["production::refresh-deepseek-v4-pro-0813-release","refresh-deepseek-v4-pro-0813-release","identity|configuration|alias|lifecycle|availability|benchmark|benchmark-version|result|verification","DeepSeek permanent refresh source","DeepSeek","https://api-docs.deepseek.com/news/news260813","official-docs","official-docs","source-checked","identity|configuration|alias|lifecycle|availability|benchmark|benchmark-version|result|verification",null,null,"2026-08-15",null,null,"DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter deepseek-v4-pro-0813-release-reviewed-html@2.0.0; role release-triggered."],["production::refresh-google-gemini-3-7-flash-launch","refresh-google-gemini-3-7-flash-launch","identity|configuration|alias|lifecycle|availability|pricing|benchmark|benchmark-version|result|verification","Google permanent refresh source","Google","https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/","official-docs","official-docs","source-checked","identity|configuration|alias|lifecycle|availability|pricing|benchmark|benchmark-version|result|verification",null,null,"2026-08-15",null,null,"Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter google-gemini-3-7-flash-launch-reviewed-html@2.0.0; role release-triggered."],["production::tencent-hy4-preview-model-card-2026-08-27","tencent-hy4-preview-model-card-2026-08-27","identity|configuration|architecture|context|availability|weights|licence|tool use","Hy4 Preview official model card","Tencent Hy Team","https://huggingface.co/tencent/Hy4-preview","official-model-card","official-model-card","source-checked","identity|configuration|architecture|context|availability|weights|licence|tool use","2026-08-27",null,"2026-08-30",null,"a596a79b27cccc18754eae0a4c10e7b40e2128aa97d67e80ce1eae645ebc1955","Apache-2.0",null,"metadata-only","source-checked",null,null,"Official model card for the exact Hy4 Preview release; no provider-hosted API price or maximum output length is stated."],["production::aa-parity-model-claude-fable-5-2026-08-27","aa-parity-model-claude-fable-5-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Claude Fable 5 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/claude-fable-5","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-06-09",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration claude-fable-5-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-claude-opus-4-8-2026-08-27","aa-parity-model-claude-opus-4-8-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Claude Opus 4.8 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-4-8","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-05-28",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration claude-opus-4-8-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-claude-opus-5-2026-08-27","aa-parity-model-claude-opus-5-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Claude Opus 5 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-5","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-24",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration claude-opus-5-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-claude-sonnet-5-2026-08-27","aa-parity-model-claude-sonnet-5-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Claude Sonnet 5 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/claude-sonnet-5","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-06-30",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration claude-sonnet-5-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-deepseek-v4-flash-vision-exp-2026-08-27","aa-parity-model-deepseek-v4-flash-vision-exp-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","DeepSeek V4 Flash Vision Exp individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v4-flash-vision","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-21",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA evaluated max, while the canonical default configuration is default. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-deepseek-v4-pro-0813-2026-08-27","aa-parity-model-deepseek-v4-pro-0813-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","DeepSeek V4 Pro 0813 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v4-pro","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-13",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA evaluated max, while the canonical default configuration is high. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-gemini-3-6-flash-2026-08-27","aa-parity-model-gemini-3-6-flash-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Gemini 3.6 Flash individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-6-flash","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-21",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort high matches the canonical default configuration gemini-3-6-flash-high. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-gemini-3-7-flash-2026-08-27","aa-parity-model-gemini-3-7-flash-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Gemini 3.7 Flash individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-7-flash-medium","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-13",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort medium matches the canonical default configuration gemini-3-7-flash-medium. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-glm-5-3-2026-08-27","aa-parity-model-glm-5-3-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","GLM-5.3 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/glm-5-3","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-18",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration glm-5-3-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-glm-5-3-flash-2026-08-27","aa-parity-model-glm-5-3-flash-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","GLM-5.3-Flash individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/glm-5-3-flash","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-26",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration glm-5-3-flash-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-gpt-5-4-2026-08-27","aa-parity-model-gpt-5-4-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","GPT-5.4 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-4","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-03-05",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort xhigh matches the canonical default configuration gpt-5-4-xhigh. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-gpt-5-5-2026-08-27","aa-parity-model-gpt-5-5-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","GPT-5.5 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-5","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-04-23",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort xhigh matches the canonical default configuration gpt-5-5-xhigh. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-gpt-5-6-luna-2026-08-27","aa-parity-model-gpt-5-6-luna-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","GPT-5.6 Luna individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-luna","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-09",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration gpt-5-6-luna-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-gpt-5-6-sol-2026-08-27","aa-parity-model-gpt-5-6-sol-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","GPT-5.6 Sol individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-sol","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-09",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration gpt-5-6-sol-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-gpt-5-6-terra-2026-08-27","aa-parity-model-gpt-5-6-terra-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","GPT-5.6 Terra individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-terra","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-09",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration gpt-5-6-terra-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-grok-4-5-2026-08-27","aa-parity-model-grok-4-5-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Grok 4.5 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-5","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-08",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort high matches the canonical default configuration grok-4-5-aa-2-high. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-grok-4-6-2026-08-27","aa-parity-model-grok-4-6-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Grok 4.6 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-6","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-12",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort high matches the canonical default configuration grok-4-6-high. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-kimi-k3-2026-08-27","aa-parity-model-kimi-k3-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Kimi K3 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/kimi-k3","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-16",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort max matches the canonical default configuration kimi-k3-max. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-muse-spark-1-1-2026-08-27","aa-parity-model-muse-spark-1-1-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Muse Spark 1.1 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/muse-spark-1-1","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-09",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort xhigh matches the canonical default configuration muse-spark-1-1-xhigh. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-muse-spark-1-2-2026-08-27","aa-parity-model-muse-spark-1-2-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Muse Spark 1.2 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/muse-spark-1-2","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-05",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA effort xhigh matches the canonical default configuration muse-spark-1-2-xhigh. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-qwen-3-7-max-2026-08-27","aa-parity-model-qwen-3-7-max-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Qwen3.7-Max individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-7-max","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-05-19",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. The canonical model has no reviewed default configuration, so the AA run cannot be selected for direct scoring. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-qwen-3-8-max-2026-08-27","aa-parity-model-qwen-3-8-max-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Qwen3.8 Max individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-8-max","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-03",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA publishes no effort label while the canonical default is xhigh; equivalence is not inferred. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-parity-model-qwen-3-8-flash-next-2026-08-27","aa-parity-model-qwen-3-8-flash-next-2026-08-27","identity|configuration|benchmark|benchmark-version|result|verification","Qwen3.8-Flash-Next individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-8-flash-next","independent-lab","independent-lab","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-08-26",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current model page exposes the individual v4.1.1 evaluation values and the exact AA model variant. AA publishes no effort label while the canonical default is xhigh; equivalence is not inferred. Composite Intelligence, Coding and Agentic indices are excluded."],["production::moonshot-kimi-k3-model-card-2026-08-29","moonshot-kimi-k3-model-card-2026-08-29","identity|configuration|benchmark|benchmark-version|result|verification","Kimi K3 official model card and benchmark protocols","Moonshot AI","https://huggingface.co/moonshotai/Kimi-K3/blob/main/README.md","official-model-card","official-model-card","source-checked","identity|configuration|benchmark|benchmark-version|result|verification","2026-07-16",null,"2026-08-29",null,null,null,null,"metadata-only","source-checked",null,null,"Current first-party model card. It states that every Kimi K3 table result uses reasoning_effort=max and temperature=1.0, then gives row-specific tool, harness and provenance footnotes. Values that differ from newer evaluator records are not overwritten."],["production::refresh-anthropic-models","refresh-anthropic-models","identity|configuration|lifecycle|specification","Anthropic permanent refresh source","Anthropic","https://platform.claude.com/docs/en/about-claude/models/overview","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification",null,null,"2026-08-07",null,null,"Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter anthropic-models-reviewed-html@2.0.0; role release-triggered."],["production::refresh-google-gemini-models","refresh-google-gemini-models","identity|configuration|lifecycle|specification","Google permanent refresh source","Google","https://ai.google.dev/gemini-api/docs/models","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification",null,null,"2026-08-07",null,null,"Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter google-gemini-models-reviewed-html@2.0.0; role release-triggered."],["production::refresh-openai-model-catalogue","refresh-openai-model-catalogue","identity|configuration|lifecycle|specification|availability","OpenAI permanent refresh source","OpenAI","https://developers.openai.com/api/docs/models/all","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability",null,null,"2026-08-07",null,null,"OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter openai-model-catalogue-reviewed-html@2.0.0; role release-triggered."],["production::refresh-xai-models","refresh-xai-models","identity|configuration|lifecycle|specification|availability","xAI permanent refresh source","xAI","https://docs.x.ai/developers/models","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability",null,null,"2026-08-07",null,null,"xAI source terms","xAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter xai-models-reviewed-html@2.0.0; role release-triggered."],["production::anthropic-pricing","anthropic-pricing","identity|configuration|lifecycle|specification|availability|licence|pricing","Claude API pricing","Anthropic","https://platform.claude.com/docs/en/about-claude/pricing","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"d4078f9e228448e5d58425b5ea496df1134b56d6dc6f2f966e02514ec384e2d2",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash d4078f9e228448e5d58425b5ea496df1134b56d6dc6f2f966e02514ec384e2d2."],["production::anthropic-opus-4-5-overview-2026-08-31","anthropic-opus-4-5-overview-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Claude Opus 4.5 model overview","Anthropic","https://platform.claude.com/docs/en/models/opus-4-5/overview","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing","2025-11-24",null,"2026-08-31",null,"9e6916c7b8df81b59233f4a40b79179a8d04ef59dbd1ed6ebcd3154ba7b555d6",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 9e6916c7b8df81b59233f4a40b79179a8d04ef59dbd1ed6ebcd3154ba7b555d6."],["production::anthropic-opus-4-6-overview-2026-08-31","anthropic-opus-4-6-overview-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Claude Opus 4.6 model overview","Anthropic","https://platform.claude.com/docs/en/models/opus-4-6/overview","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing","2026-02-05",null,"2026-08-31",null,"12c7f19f348c94cb2edbc0bf64a06bcb25e0661a7179c23006e2847691cee5a1",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 12c7f19f348c94cb2edbc0bf64a06bcb25e0661a7179c23006e2847691cee5a1."],["production::anthropic-sonnet-4-5-overview-2026-08-31","anthropic-sonnet-4-5-overview-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Claude Sonnet 4.5 model overview","Anthropic","https://platform.claude.com/docs/en/models/sonnet-4-5/overview","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing","2025-09-29",null,"2026-08-31",null,"49d67ce8c77bad782c8817a4081453b7a5f141cc0b832eac229efc56b0bbd283",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 49d67ce8c77bad782c8817a4081453b7a5f141cc0b832eac229efc56b0bbd283."],["production::anthropic-sonnet-4-6-overview-2026-08-31","anthropic-sonnet-4-6-overview-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Claude Sonnet 4.6 model overview","Anthropic","https://platform.claude.com/docs/en/models/sonnet-4-6/overview","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing","2026-02-17",null,"2026-08-31",null,"b10a79b003dcebe8a787c9ac50fbdba4c7c46dbb24a7d4c9d42ee457aa366b30",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash b10a79b003dcebe8a787c9ac50fbdba4c7c46dbb24a7d4c9d42ee457aa366b30."],["production::google-gemini-25-flash-2026-08-31","google-gemini-25-flash-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Gemini 2.5 Flash model documentation","Google","https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"a1332c54ae31196476c0871596911da2e557e417c4118a02890ab675de961d8f",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash a1332c54ae31196476c0871596911da2e557e417c4118a02890ab675de961d8f."],["production::google-gemini-25-pro-2026-08-31","google-gemini-25-pro-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Gemini 2.5 Pro model documentation","Google","https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"59d1a70a7fcca77232cb8fcdfe2e8efd1209ae399bff552a00539468ac8c77e9",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 59d1a70a7fcca77232cb8fcdfe2e8efd1209ae399bff552a00539468ac8c77e9."],["production::google-gemini-3-flash-preview-2026-08-31","google-gemini-3-flash-preview-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Gemini 3 Flash Preview model documentation","Google","https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"58b7ad13ee6e078ff8223aeeeaa158c2c04a8b88edeffc7b98147b9ea862d563",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 58b7ad13ee6e078ff8223aeeeaa158c2c04a8b88edeffc7b98147b9ea862d563."],["production::google-gemini-31-flash-lite","google-gemini-31-flash-lite","identity|configuration|lifecycle|specification|availability|licence|pricing","Gemini 3.1 Flash-Lite model documentation","Google","https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"f68437cb4ef6230ab001299b0a02f247a7137ed2fa7c3f5af6669f4db97d8638",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash f68437cb4ef6230ab001299b0a02f247a7137ed2fa7c3f5af6669f4db97d8638."],["production::google-gemini-31-pro","google-gemini-31-pro","identity|configuration|lifecycle|specification|availability|licence|pricing","Gemini 3.1 Pro Preview model documentation","Google","https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"297cbf2210b6f7a3037da8892950a90b8031a1d696893ce39d19155e88069a53",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 297cbf2210b6f7a3037da8892950a90b8031a1d696893ce39d19155e88069a53."],["production::google-gemini-35-flash-lite-docs","google-gemini-35-flash-lite-docs","identity|configuration|lifecycle|specification|availability|licence|pricing","Gemini 3.5 Flash-Lite model documentation","Google","https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"f657056767ff6c0948f8e4ff438253da5bc442610020767ad229a1f41115f088",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash f657056767ff6c0948f8e4ff438253da5bc442610020767ad229a1f41115f088."],["production::google-pricing","google-pricing","identity|configuration|lifecycle|specification|availability|licence|pricing","Gemini Developer API pricing","Google","https://ai.google.dev/gemini-api/docs/pricing","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"553f02029e227f1781066af088a72413cbfe215aad43e3994ea249c04475137e",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 553f02029e227f1781066af088a72413cbfe215aad43e3994ea249c04475137e."],["production::meta-muse-spark-1-1-blog","meta-muse-spark-1-1-blog","identity|configuration|lifecycle|specification|availability|licence|pricing","Introducing Muse Spark 1.1","Meta","https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing","2026-07-09",null,"2026-08-31",null,"8da9754e6d974c341af7215bbf65c04fc494bb911b59c5dde1cb867a92d006ea",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 8da9754e6d974c341af7215bbf65c04fc494bb911b59c5dde1cb867a92d006ea."],["production::minimax-m3-paygo-pricing-2026-08-31","minimax-m3-paygo-pricing-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","MiniMax pay-as-you-go pricing","MiniMax","https://platform.minimax.io/docs/guides/pricing-paygo","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"3402a5c3e4d6cbd9ad2af111e735cd00e035a260631d200803e8208170092a24",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 3402a5c3e4d6cbd9ad2af111e735cd00e035a260631d200803e8208170092a24."],["production::openai-gpt-5-model-2026-08-31","openai-gpt-5-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GPT-5 API model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"16e3856b57f8ab929befd598209b8a612282df3d47821b1f71ba7b253f85dc97",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 16e3856b57f8ab929befd598209b8a612282df3d47821b1f71ba7b253f85dc97."],["production::refresh-openai-gpt-5-codex-model","refresh-openai-gpt-5-codex-model","identity|configuration|lifecycle|specification|availability|licence|pricing","GPT-5 Codex API model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5-codex","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"26e7b773cedecdbe1811ad6d86cc54b3738c31bcf393b8736f63f269eca6b42c","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 26e7b773cedecdbe1811ad6d86cc54b3738c31bcf393b8736f63f269eca6b42c."],["production::openai-gpt-5-mini-model-2026-08-31","openai-gpt-5-mini-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GPT-5 mini API model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5-mini","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"e028e0c446e5e7401aa2a24aa99a7a13a85114191b859d9825d62e30b451af1e",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash e028e0c446e5e7401aa2a24aa99a7a13a85114191b859d9825d62e30b451af1e."],["production::refresh-openai-gpt-5-1-model","refresh-openai-gpt-5-1-model","identity|configuration|lifecycle|specification|availability|licence|pricing","GPT-5.1 API model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.1","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"953b076f16181e14a1407e91e671cae30e52b205eab97b2c7c1f97ec468fbdf9","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 953b076f16181e14a1407e91e671cae30e52b205eab97b2c7c1f97ec468fbdf9."],["production::openai-gpt-5-2-model-2026-08-31","openai-gpt-5-2-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GPT-5.2 API model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.2","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"d1f84f48c2247d4b4c6823b97ecf01fb5b0e5bc2ee2c65d8c2f1482ac796eb14",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash d1f84f48c2247d4b4c6823b97ecf01fb5b0e5bc2ee2c65d8c2f1482ac796eb14."],["production::refresh-openai-gpt-5-2-codex-model","refresh-openai-gpt-5-2-codex-model","identity|configuration|lifecycle|specification|availability|licence|pricing","GPT-5.2 Codex API model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.2-codex","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"fbdf62b6a668508caa259ebfec2cdb6c9c3cb9b2e29cb1f451ca5cef5b8f455c","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash fbdf62b6a668508caa259ebfec2cdb6c9c3cb9b2e29cb1f451ca5cef5b8f455c."],["production::openai-gpt-5-4-mini-model-2026-08-31","openai-gpt-5-4-mini-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GPT-5.4 mini API model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.4-mini","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"e4860f4250af2aaa8c20f578510460dcfd9db058be8611f2acf9a99a00fbce62",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash e4860f4250af2aaa8c20f578510460dcfd9db058be8611f2acf9a99a00fbce62."],["production::refresh-openai-gpt-5-4-nano-model","refresh-openai-gpt-5-4-nano-model","identity|configuration|lifecycle|specification|availability|licence|pricing","GPT-5.4 nano API model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.4-nano","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"ff525f1a15b4e4c18719165025c24f825125b48403fc0316850424b846616000","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash ff525f1a15b4e4c18719165025c24f825125b48403fc0316850424b846616000."],["production::openai-o1-model-2026-08-31","openai-o1-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","o1 API model documentation","OpenAI","https://developers.openai.com/api/docs/models/o1","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"eee10d27546db7aaeaf51c27d08e819fc37b04413d1ea2159f18e2b6a4d73119",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash eee10d27546db7aaeaf51c27d08e819fc37b04413d1ea2159f18e2b6a4d73119."],["production::openai-o3-model-2026-08-31","openai-o3-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","o3 API model documentation","OpenAI","https://developers.openai.com/api/docs/models/o3","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"3b170f1a59fdef057866529862314002f87d78c3e55a2a91844f46db2a15b974",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 3b170f1a59fdef057866529862314002f87d78c3e55a2a91844f46db2a15b974."],["production::openai-o4-mini-model-2026-08-31","openai-o4-mini-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","o4-mini API model documentation","OpenAI","https://developers.openai.com/api/docs/models/o4-mini","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"ecd0a5d96aba78df2a8d2441d7ff938b1c6d6ada9e8314472a4704d25f59a7fc",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash ecd0a5d96aba78df2a8d2441d7ff938b1c6d6ada9e8314472a4704d25f59a7fc."],["production::qwen-3-8-27b-huggingface-2026-08-15","qwen-3-8-27b-huggingface-2026-08-15","identity|configuration|lifecycle|specification|availability|licence|pricing","Qwen3.8-27B official model card","Qwen","https://huggingface.co/Qwen/Qwen3.8-27B","official-model-card","official-model-card","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing","2026-08-14",null,"2026-08-31",null,"b3506b1c64f9d8e839a8529ab94642ccee3e0c5d64610758a67826f9fcecbe92",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash b3506b1c64f9d8e839a8529ab94642ccee3e0c5d64610758a67826f9fcecbe92."],["production::xai-grok-4-3-model-2026-08-31","xai-grok-4-3-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Grok 4.3 API model documentation","xAI","https://docs.x.ai/developers/models/grok-4.3","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"a203c01cdae3cbd954d2023f361ffb917ede6d7170edc98e72f4243b77dea63c",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash a203c01cdae3cbd954d2023f361ffb917ede6d7170edc98e72f4243b77dea63c."],["production::xai-grok-4-5-model-2026-08-31","xai-grok-4-5-model-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","Grok 4.5 API model documentation","xAI","https://docs.x.ai/developers/models/grok-4.5","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"70c855da86a431354e65de1f346ab5b58a6002259142fb9ebf292528dedb0c06",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 70c855da86a431354e65de1f346ab5b58a6002259142fb9ebf292528dedb0c06."],["production::zai-glm-4-6-docs-2026-08-31","zai-glm-4-6-docs-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-4.6 developer overview","Z.AI","https://docs.z.ai/guides/llm/glm-4.6","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"3d90fb2c922e650f7fb2370cf0c2730e8a3ad804e952f35a3c7397284c05a4aa",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 3d90fb2c922e650f7fb2370cf0c2730e8a3ad804e952f35a3c7397284c05a4aa."],["production::zai-glm-4-6-hf-api-2026-08-31","zai-glm-4-6-hf-api-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-4.6 official repository metadata","Z.AI","https://huggingface.co/api/models/zai-org/GLM-4.6","official-model-card","official-model-card","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"ca6a83bbbcc6aaf3e4cd5dc91906e93591ee99099cefb69c568fc3f72a2d97a8",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash ca6a83bbbcc6aaf3e4cd5dc91906e93591ee99099cefb69c568fc3f72a2d97a8."],["production::zai-glm-4-7-docs-2026-08-31","zai-glm-4-7-docs-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-4.7 developer overview","Z.AI","https://docs.z.ai/guides/llm/glm-4.7","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"ea7f13919818baa8a87013354114727ad1be16057729985bdc8a51e8f1a2966f",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash ea7f13919818baa8a87013354114727ad1be16057729985bdc8a51e8f1a2966f."],["production::zai-glm-4-7-hf-api-2026-08-31","zai-glm-4-7-hf-api-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-4.7 official repository metadata","Z.AI","https://huggingface.co/api/models/zai-org/GLM-4.7","official-model-card","official-model-card","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"9222c4289698e3e18e0c6751033c58b057ea4c38d3084d40a9a23c14c4410ea9",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 9222c4289698e3e18e0c6751033c58b057ea4c38d3084d40a9a23c14c4410ea9."],["production::zai-glm-5-docs-2026-08-31","zai-glm-5-docs-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-5 developer overview","Z.AI","https://docs.z.ai/guides/llm/glm-5","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"e2e35e82caf4e10795224bed7d54a61e129e4c29dee23f6e59b0882b092ced99",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash e2e35e82caf4e10795224bed7d54a61e129e4c29dee23f6e59b0882b092ced99."],["production::zai-glm-5-hf-api-2026-08-31","zai-glm-5-hf-api-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-5 official repository metadata","Z.AI","https://huggingface.co/api/models/zai-org/GLM-5","official-model-card","official-model-card","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"4e1dd3ca992b6e06247f711f8254b155da039ad18646780607626c511b59454b",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 4e1dd3ca992b6e06247f711f8254b155da039ad18646780607626c511b59454b."],["production::zai-glm-5-1-docs-2026-08-31","zai-glm-5-1-docs-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-5.1 developer overview","Z.AI","https://docs.z.ai/guides/llm/glm-5.1","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"ae6cb509d7d20359726cd1b016ba3727f10f19b76a92cfe2421484bc3cb8eda3",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash ae6cb509d7d20359726cd1b016ba3727f10f19b76a92cfe2421484bc3cb8eda3."],["production::zai-glm-5-1-hf-api-2026-08-31","zai-glm-5-1-hf-api-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-5.1 official repository metadata","Z.AI","https://huggingface.co/api/models/zai-org/GLM-5.1","official-model-card","official-model-card","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"6c968354676ec8a6c090ada501f0931a2bd9b546fcbe5dd204fe5eff714205cc",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 6c968354676ec8a6c090ada501f0931a2bd9b546fcbe5dd204fe5eff714205cc."],["production::zai-glm-5-2-docs-2026-08-31","zai-glm-5-2-docs-2026-08-31","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-5.2 developer overview","Z.AI","https://docs.z.ai/guides/llm/glm-5.2","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"4da4b3fda376a290e7cc64ff6479788d42f7f370b3de2e99443aaba810bd476c",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 4da4b3fda376a290e7cc64ff6479788d42f7f370b3de2e99443aaba810bd476c."],["production::zai-glm-5-3-docs-2026-08-15","zai-glm-5-3-docs-2026-08-15","identity|configuration|lifecycle|specification|availability|licence|pricing","GLM-5.3 developer overview","Z.AI","https://docs.z.ai/guides/llm/glm-5.3","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"111734231ab2a04bebc2a8b6dfd27d1b80f0e0151e95747f0e234e792ee17fda",null,null,"metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash 111734231ab2a04bebc2a8b6dfd27d1b80f0e0151e95747f0e234e792ee17fda."],["production::refresh-zai-pricing","refresh-zai-pricing","identity|configuration|lifecycle|specification|availability|licence|pricing","Z.AI model pricing","Z.AI","https://docs.z.ai/guides/overview/pricing","official-docs","official-docs","source-checked","identity|configuration|lifecycle|specification|availability|licence|pricing",null,null,"2026-08-31",null,"cf649a80d9ae80cab0e2af08d54ab6eaa9506f98c4b4f09fe1d8429b4673105a","Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Current official public surface acquired for the Top-100 saturation pass; response hash cf649a80d9ae80cab0e2af08d54ab6eaa9506f98c4b4f09fe1d8429b4673105a."],["production::meta-llama-4-official-2026-08-29","meta-llama-4-official-2026-08-29","identity|configuration|lifecycle|specification|availability|licence|verification","The Llama 4 herd: natively multimodal Scout and Maverick","Meta","https://ai.meta.com/blog/llama-4-multimodal-intelligence/","official-model-card","official-model-card","source-checked","identity|configuration|lifecycle|specification|availability|licence|verification","2025-04-05",null,"2026-08-29",null,"5665ce4b85184efcea20e26497eda6a6c58091aaab8f36600480dc512cf19cc3",null,null,"metadata-only","source-checked",null,null,"First-party release identifies Llama 4 Scout and Maverick as open-weight, natively multimodal non-reasoning models released on 2025-04-05, with 10M and 1M context respectively."],["production::kimi-k2-5-official-repository-2026-08-29","kimi-k2-5-official-repository-2026-08-29","identity|configuration|lifecycle|specification|availability|licence|verification","Kimi K2.5 official repository and model documentation","Moonshot AI","https://github.com/MoonshotAI/Kimi-K2.5","official-repository","official-repository","source-checked","identity|configuration|lifecycle|specification|availability|licence|verification","2026-01-27",null,"2026-08-29",null,"d163cd83b26e209b94927ccba56c32f4c99641df42bb93a61bbead955e3c9bc0",null,null,"metadata-only","source-checked",null,null,"First-party repository identifies Kimi K2.5 as an open-weight native multimodal model with instant and thinking modes, plus official API and self-hosted access."],["production::openai-gpt-5-2-pro-2026-08-29","openai-gpt-5-2-pro-2026-08-29","identity|configuration|model-offering|pricing|verification","GPT-5.2 Pro model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.2-pro","official-docs","official-docs","source-checked","identity|configuration|model-offering|pricing|verification","2025-12-11",null,"2026-08-29",null,null,null,null,"metadata-only","source-checked",null,null,"OpenAI documents GPT-5.2 Pro as the Pro compute variant in the GPT-5.2 generation, with a distinct API alias, snapshots, effort settings and pricing."],["production::openai-gpt-5-4-pro-2026-08-29","openai-gpt-5-4-pro-2026-08-29","identity|configuration|model-offering|pricing|verification","GPT-5.4 Pro model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.4-pro","official-docs","official-docs","source-checked","identity|configuration|model-offering|pricing|verification","2026-03-05",null,"2026-08-29",null,null,null,null,"metadata-only","source-checked",null,null,"OpenAI describes GPT-5.4 Pro as a more-compute version of GPT-5.4, while retaining a distinct API alias, snapshots, effort settings and pricing."],["production::openai-gpt-5-5-pro-2026-08-29","openai-gpt-5-5-pro-2026-08-29","identity|configuration|model-offering|pricing|verification","GPT-5.5 Pro model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.5-pro","official-docs","official-docs","source-checked","identity|configuration|model-offering|pricing|verification","2026-04-23",null,"2026-08-29",null,null,null,null,"metadata-only","source-checked",null,null,"OpenAI describes GPT-5.5 Pro as a more-compute version of GPT-5.5, while retaining a distinct API alias, snapshots, effort settings and pricing."],["production::anthropic-opus-4-6-configuration-2026-08-29","anthropic-opus-4-6-configuration-2026-08-29","identity|configuration|result|verification","Claude Opus 4.6 official launch and evaluation configuration","Anthropic","https://www.anthropic.com/news/claude-opus-4-6","official-provider-evaluation","official-provider-evaluation","source-checked","identity|configuration|result|verification","2026-02-05",null,"2026-08-29",null,"af7736bfc83b9131f71207e50ebede8581d285a710f11a5332e2d7a0494ac87b",null,null,"metadata-only","source-checked",null,null,"First-party release material explicitly identifies adaptive thinking and the evaluated max-effort configuration."],["production::anthropic-opus-4-7-configuration-2026-08-29","anthropic-opus-4-7-configuration-2026-08-29","identity|configuration|result|verification","Claude Opus 4.7 official launch and evaluation configuration","Anthropic","https://www.anthropic.com/news/claude-opus-4-7","official-provider-evaluation","official-provider-evaluation","source-checked","identity|configuration|result|verification","2026-04-16",null,"2026-08-29",null,"0e396f09526fc4e81b0f9d493a61a40461ea97aea067715d0d769d6ab9ad3455",null,null,"metadata-only","source-checked",null,null,"First-party release material explicitly identifies adaptive thinking and the evaluated max-effort configuration."],["production::aa-current-claude-opus-4-5-thinking-2026-08-29","aa-current-claude-opus-4-5-thinking-2026-08-29","identity|configuration|result|verification","Claude Opus 4.5 (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-4-5-thinking","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-11-24",null,"2026-08-29",null,"5ac9dc138994493e1cf06a3b96bb7dbd6ca0af0b08e35a0ce124fc88f5681010",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-claude-opus-4-6-thinking-2026-08-29","aa-current-claude-opus-4-6-thinking-2026-08-29","identity|configuration|result|verification","Claude Opus 4.6 (Adaptive Reasoning, Max Effort) individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-02-05",null,"2026-08-29",null,"0153eb5f2de7866e5f141086dce1c2657fc00593eb35423146f06f040305f45e",null,null,"metadata-only","source-checked",null,null,"Current public model page exposes independently run individual evaluations. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-current-claude-opus-4-7-adaptive-2026-08-29","aa-current-claude-opus-4-7-adaptive-2026-08-29","identity|configuration|result|verification","Claude Opus 4.7 (Adaptive Reasoning, Max Effort) individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-4-7","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-16",null,"2026-08-29",null,"37b4a62277ec04c1d608b25575eaac5e6fd904ed69637997e14783dab3fd3682",null,null,"metadata-only","source-checked",null,null,"Current public model page exposes independently run individual evaluations. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-current-claude-opus-5-2026-08-29","aa-current-claude-opus-5-2026-08-29","identity|configuration|result|verification","Claude Opus 5 (Adaptive Reasoning, Max Effort) individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-5","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-07-24",null,"2026-08-29",null,"9832bdc8ff79c69932687ff82ed5ec16ffa4404e331f677b29d9f371e9a7c3f7",null,null,"metadata-only","source-checked",null,null,"Current public model page exposes independently run individual evaluations. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-current-deepseek-r1-aa-2-2026-08-29","aa-current-deepseek-r1-aa-2-2026-08-29","identity|configuration|result|verification","DeepSeek R1 0528 (May '25) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-r1","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-05-28",null,"2026-08-29",null,"0bba7a067efbdc5287c56fd1c6304a8e129e2b2065f709af0319ba44cf6660b1",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-deepseek-v3-1-2026-08-29","aa-current-deepseek-v3-1-2026-08-29","identity|configuration|result|verification","DeepSeek V3.1 (Non-reasoning) individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v3-1","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-08-21",null,"2026-08-29",null,"fe9210df6ee8658301668c546c3369610ffffae9c3834755f8ce5392bd5dc3e3",null,null,"metadata-only","source-checked",null,null,"Current public model page exposes independently run individual evaluations. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-current-deepseek-v3-1-reasoning-2026-08-29","aa-current-deepseek-v3-1-reasoning-2026-08-29","identity|configuration|result|verification","DeepSeek V3.1 (Reasoning) individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v3-1-reasoning","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-08-21",null,"2026-08-29",null,"2025fc919340a1ede0ecbaa4ba0f12da96d507957282db659b83e05554d4827d",null,null,"metadata-only","source-checked",null,null,"Current public model page exposes independently run individual evaluations. Composite Intelligence, Coding and Agentic indices are excluded."],["production::aa-deepseek-v4-flash-vision-2026-08-27","aa-deepseek-v4-flash-vision-2026-08-27","identity|configuration|result|verification","DeepSeek V4 Flash Vision Exp individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v4-flash-vision","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-08-21",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Public model page exposes individual evaluation fields and states that Artificial Analysis measured the evaluations independently. The composite Intelligence Index is not ingested."],["production::aa-current-exaone-4-0-1-2b-2026-08-29","aa-current-exaone-4-0-1-2b-2026-08-29","identity|configuration|result|verification","Exaone 4.0 1.2B (Non-reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/exaone-4-0-1-2b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-07-15",null,"2026-08-29",null,"bb2cd006cf6d36d442f4d661aa9e6d2680452e509abdabed803a19f1fa6c5304",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-exaone-4-0-32b-2026-08-29","aa-current-exaone-4-0-32b-2026-08-29","identity|configuration|result|verification","EXAONE 4.0 32B (Non-reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/exaone-4-0-32b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-07-15",null,"2026-08-29",null,"84572494c80d1808916b4552e0887341c3e5c4102eb0f2ea1cd1df318175e4b6",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gemini-1-0-pro-2026-08-29","aa-current-gemini-1-0-pro-2026-08-29","identity|configuration|result|verification","Gemini 1.0 Pro current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gemini-1-0-pro","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2023-12-06",null,"2026-08-29",null,"2146035aa8fb26da3fc51be1dbc66ed2d840370de2421e568f16f819ce65fc9a",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gemini-1-5-pro-may-2024-2026-08-29","aa-current-gemini-1-5-pro-may-2024-2026-08-29","identity|configuration|result|verification","Gemini 1.5 Pro (May '24) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gemini-1-5-pro-may-2024","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-05-15",null,"2026-08-29",null,"ea7c3600c9890b757c78119954eede4a4d8c86d200c6e80d5963ec53bb5e088c",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gemini-1-5-pro-2026-08-29","aa-current-gemini-1-5-pro-2026-08-29","identity|configuration|result|verification","Gemini 1.5 Pro (Sep '24) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gemini-1-5-pro","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-09-24",null,"2026-08-29",null,"c9f09a822f98e75cceae2038b48a6823bdade64aa4b2e97c0b640c4e3f3eeb0e",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gemma-3-27b-2026-08-29","aa-current-gemma-3-27b-2026-08-29","identity|configuration|result|verification","Gemma 3 27B Instruct current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gemma-3-27b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-03-12",null,"2026-08-29",null,"62189d826879b2669712ef5c1efd5b9e4fff7eaa9500a0171959e9e580503e15",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-gemma-4-26b-a4b-2026-08-29","aa-current-gemma-4-26b-a4b-2026-08-29","identity|configuration|result|verification","Gemma 4 26B A4B (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gemma-4-26b-a4b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-02",null,"2026-08-29",null,"31108e5a6e51ff8cadfad99c4ac94e8ccc70a735cbaf39c638693136eeb26538",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-gemma-4-e2b-2026-08-29","aa-current-gemma-4-e2b-2026-08-29","identity|configuration|result|verification","Gemma 4 E2B (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gemma-4-e2b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-02",null,"2026-08-29",null,"a8fca8bbd5fc05260335537a4cba2abf9edea877784ba388559b84f528596df5",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gemma-4-e4b-2026-08-29","aa-current-gemma-4-e4b-2026-08-29","identity|configuration|result|verification","Gemma 4 E4B (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gemma-4-e4b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-03",null,"2026-08-29",null,"7f6ea43c150dcd9306b69278ca08453af46369758005ee82a7d03e7afdccc33e",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-glm-4-5-air-2026-08-29","aa-current-glm-4-5-air-2026-08-29","identity|configuration|result|verification","GLM-4.5-Air current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/glm-4-5-air","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-07-28",null,"2026-08-29",null,"43ba18e65932f5629ebfa09d378b102619ff0d19a0afd014ff013f26f1865e50",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-glm-5-2-2026-08-29","aa-current-glm-5-2-2026-08-29","identity|configuration|result|verification","GLM-5.2 (max) individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/glm-5-2","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-06-16",null,"2026-08-29",null,"8e79935660a4f1fe6a32362574935506f9a9290de27c5f62c575036b2e515c3b",null,null,"metadata-only","source-checked",null,null,"Current public model page exposes Artificial Analysis individual evaluations. Composite Intelligence, Coding and Agentic indices are excluded. Exact evaluator configuration was checked against the canonical configuration before admission."],["production::aa-glm-5-3-flash-2026-08-27","aa-glm-5-3-flash-2026-08-27","identity|configuration|result|verification","GLM-5.3-Flash individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/glm-5-3-flash","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-08-26",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Public model page exposes individual evaluation fields and states that Artificial Analysis measured the evaluations independently. The composite Intelligence Index is not ingested."],["production::aa-current-gpt-4-turbo-2026-08-29","aa-current-gpt-4-turbo-2026-08-29","identity|configuration|result|verification","GPT-4 Turbo current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-4-turbo","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2023-11-06",null,"2026-08-29",null,"8ebb0a6d2466ef780f0ff3ed9853f131f5f704628c92f339b0d7aa6422e52114",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gpt-4-1-2026-08-29","aa-current-gpt-4-1-2026-08-29","identity|configuration|result|verification","GPT-4.1 current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-4-1","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-04-14",null,"2026-08-29",null,"d5343cac62805e084602c93f9cb5ce18812a630b0339396b57b6ca6fa04cb6f1",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gpt-4-1-mini-2026-08-29","aa-current-gpt-4-1-mini-2026-08-29","identity|configuration|result|verification","GPT-4.1 mini current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-4-1-mini","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-04-14",null,"2026-08-29",null,"7479b0c3ba5f67aed0d6ba36da3e8b0217f0d457fa27b08831468b3e345990f2",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-gpt-4-1-nano-2026-08-29","aa-current-gpt-4-1-nano-2026-08-29","identity|configuration|result|verification","GPT-4.1 nano current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-4-1-nano","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-04-14",null,"2026-08-29",null,"b530e64bd603398b5038ec4a18776814d4f4e0d4466831dffb5f120a23d6e3ea",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-gpt-4o-2024-08-06-2026-08-29","aa-current-gpt-4o-2024-08-06-2026-08-29","identity|configuration|result|verification","GPT-4o (Aug '24) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-4o-2024-08-06","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-08-06",null,"2026-08-29",null,"926fbb15c06215f85df2047b7255b689c3cea8b59777889b39b62175e816a45d",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gpt-4o-2024-05-13-2026-08-29","aa-current-gpt-4o-2024-05-13-2026-08-29","identity|configuration|result|verification","GPT-4o (May '24) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-4o-2024-05-13","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-05-13",null,"2026-08-29",null,"aed24511e6083a856236afbf4029b95f97fe3ba2669287b4a2a32c56190f13ed",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gpt-4o-2026-08-29","aa-current-gpt-4o-2026-08-29","identity|configuration|result|verification","GPT-4o (Nov '24) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-4o","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-11-20",null,"2026-08-29",null,"734751075bc60cab2a9d023ae57004e06a81506d664ff59d7e0de2a5b91ff74e",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gpt-5-nano-2026-08-29","aa-current-gpt-5-nano-2026-08-29","identity|configuration|result|verification","GPT-5 nano (high) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-nano","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-08-07",null,"2026-08-29",null,"22380824cadf295e482d8d142ebb798dd5847e420efa274553386045e9acb442",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-gpt-5-4-pro-2026-08-29","aa-current-gpt-5-4-pro-2026-08-29","identity|configuration|result|verification","GPT-5.4 Pro (xhigh) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-4-pro","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-03-05",null,"2026-08-29",null,"57b1f94276053aa16bb53e018051e1ea0e79ae5794b9e34abbd21d833d135341",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-granite-4-0-1b-2026-08-29","aa-current-granite-4-0-1b-2026-08-29","identity|configuration|result|verification","Granite 4.0 1B current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/granite-4-0-nano-1b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-10-28",null,"2026-08-29",null,"abe4690ad0d2b9bd3543b25f7212284cda10102d89026b4ed82cd0a8097aa0d8",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-granite-4-0-350m-2026-08-29","aa-current-granite-4-0-350m-2026-08-29","identity|configuration|result|verification","Granite 4.0 350M current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/granite-4-0-350m","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-10-28",null,"2026-08-29",null,"15d32b69428d5fece9191f414b46a3a66e1995c70af47b2468c83bc6076bff42",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-granite-4-0-h-1b-2026-08-29","aa-current-granite-4-0-h-1b-2026-08-29","identity|configuration|result|verification","Granite 4.0 H 1B current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/granite-4-0-h-nano-1b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-10-28",null,"2026-08-29",null,"63b2b159db3015ca703010c7cf765e71e4f4826556eb949d2e552768197e9724",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-granite-4-0-h-350m-2026-08-29","aa-current-granite-4-0-h-350m-2026-08-29","identity|configuration|result|verification","Granite 4.0 H 350M current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/granite-4-0-h-350m","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-10-28",null,"2026-08-29",null,"4fcac5d232d1391910181ad488fee72406597da6973e32136c14a8447ac4a3c7",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-grok-4-fast-reasoning-2026-08-29","aa-current-grok-4-fast-reasoning-2026-08-29","identity|configuration|result|verification","Grok 4 Fast (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-fast-reasoning","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-09-19",null,"2026-08-29",null,"0fb6e0a22f60c925b582f40af8668aba93e5abd2f5dfeaf8e9f8d1f4097edf14",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-grok-4-1-fast-2026-08-29","aa-current-grok-4-1-fast-2026-08-29","identity|configuration|result|verification","Grok 4.1 Fast (Non-reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-1-fast","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-11-19",null,"2026-08-29",null,"d103d55a388a2fd065f82a4d7295b70c0aefd67fa7b2b3913a92d3bcdd5503ab",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-grok-4-1-fast-reasoning-2026-08-29","aa-current-grok-4-1-fast-reasoning-2026-08-29","identity|configuration|result|verification","Grok 4.1 Fast (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-1-fast-reasoning","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-11-19",null,"2026-08-29",null,"1486e3c45641306c744880dccfbe3b91fb67792c362133860aef53e1358751b9",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-k-exaone-2026-08-29","aa-current-k-exaone-2026-08-29","identity|configuration|result|verification","K-EXAONE (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/k-exaone","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-12-31",null,"2026-08-29",null,"d1856d5cd2bc9b129b0f625719ff8a3385cf34dbb94e8f8eaa9b38c78cb12eec",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-kimi-k2-5-reasoning-2026-08-29","aa-current-kimi-k2-5-reasoning-2026-08-29","identity|configuration|result|verification","Kimi K2.5 (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/kimi-k2-5","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-01-27",null,"2026-08-29",null,"6105c4fcd5d7ac719e6b484243d7ab9a7eb40e536f5a846d2c1205647d9b71b8",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-llama-3-1-405b-2026-08-29","aa-current-llama-3-1-405b-2026-08-29","identity|configuration|result|verification","Llama 3.1 Instruct 405B current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/llama-3-1-instruct-405b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-07-23",null,"2026-08-29",null,"e3827c3c457ff71114151612e4d591ebd2928b21570a0c552ea540563c359581",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-llama-4-maverick-2026-08-29","aa-current-llama-4-maverick-2026-08-29","identity|configuration|result|verification","Llama 4 Maverick current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/llama-4-maverick","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-04-05",null,"2026-08-29",null,"d748d1487b61defcadf55f552508f46fa8ac70c4ef524a821b7e9817e2e10586",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-llama-4-scout-2026-08-29","aa-current-llama-4-scout-2026-08-29","identity|configuration|result|verification","Llama 4 Scout current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/llama-4-scout","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-04-05",null,"2026-08-29",null,"cffce7f3ff139b4a77a81a64fd3b647f0e985747f4c32cb9c77760d994447a05",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-longcat-2-0-2026-08-29","aa-current-longcat-2-0-2026-08-29","identity|configuration|result|verification","LongCat 2.0 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/longcat-2-0","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-06-29",null,"2026-08-29",null,"4efe85344a8ddc3a54e2941fbec1610fe99439c9ade8b87e4116095c32035ed1",null,null,"metadata-only","source-checked",null,null,"Current public model page exposes Artificial Analysis individual evaluations. Composite Intelligence, Coding and Agentic indices are excluded. Exact evaluator configuration was checked against the canonical configuration before admission."],["production::aa-current-mistral-large-2-2026-08-29","aa-current-mistral-large-2-2026-08-29","identity|configuration|result|verification","Mistral Large 2 (Nov '24) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/mistral-large-2","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-11-18",null,"2026-08-29",null,"c529432f4fd037f5e107a98d7669f368418b1b57c7abe3592eba28e4a050aea6",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-mistral-medium-3-2026-08-29","aa-current-mistral-medium-3-2026-08-29","identity|configuration|result|verification","Mistral Medium 3 current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/mistral-medium-3","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-05-07",null,"2026-08-29",null,"a735110310492d195fb6516b030c9c038a872689ecd8e6d5648514d88a31245c",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-mistral-medium-3-5-128b-2026-08-29","aa-current-mistral-medium-3-5-128b-2026-08-29","identity|configuration|result|verification","Mistral Medium 3.5 current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/mistral-medium-3-5","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-29",null,"2026-08-29",null,"0afc63ee7ac0aa76b8f55467d12760be8f57cde58224b2f91b2271462c78b323",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-mistral-small-4-reasoning-2026-08-29","aa-current-mistral-small-4-reasoning-2026-08-29","identity|configuration|result|verification","Mistral Small 4 (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/mistral-small-4","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-03-16",null,"2026-08-29",null,"d3748140e1e406c79c45dfad77a5d17118a7be7debd6b02af7f56bea3cc1da32",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-muse-spark-1-2-2026-08-27","aa-muse-spark-1-2-2026-08-27","identity|configuration|result|verification","Muse Spark 1.2 individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/muse-spark-1-2","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-08-05",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Public model page exposes individual evaluation fields and states that Artificial Analysis measured the evaluations independently. The composite Intelligence Index is not ingested."],["production::aa-current-nemotron-3-nano-omni-30b-a3b-2026-08-29","aa-current-nemotron-3-nano-omni-30b-a3b-2026-08-29","identity|configuration|result|verification","Nemotron 3 Nano Omni 30B A3B Reasoning current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-29",null,"2026-08-29",null,"c244fc25feed520eec319d5de265e3f10b571fc6883be8e903dd36f227dbd215",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-nemotron-3-nano-30b-2026-08-29","aa-current-nemotron-3-nano-30b-2026-08-29","identity|configuration|result|verification","NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2025-12-15",null,"2026-08-29",null,"931704cbdef2397c6facaaf979871f8865f6d9c8bbd0b189f462edb5d717c972",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-phi-4-2026-08-29","aa-current-phi-4-2026-08-29","identity|configuration|result|verification","Phi-4 current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/phi-4","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-12-12",null,"2026-08-29",null,"f8da76f654d964b7ef12d2cd34b9e8932e705fd7e2ea2a304ac329089cd4111c",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-qwen2-5-coder-32b-instruct-2026-08-29","aa-current-qwen2-5-coder-32b-instruct-2026-08-29","identity|configuration|result|verification","Qwen2.5 Coder Instruct 32B current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/qwen2-5-coder-32b-instruct","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2024-11-11",null,"2026-08-29",null,"2575d6e3a90092fa35db816faf3a82a368958cb7876763e51c9865ab9c78d78e",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-qwen3-5-122b-a10b-2026-08-29","aa-current-qwen3-5-122b-a10b-2026-08-29","identity|configuration|result|verification","Qwen3.5 122B A10B (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-5-122b-a10b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-02-24",null,"2026-08-29",null,"bc8e042ee7e98cd2d537a1bd23d251387bf332df1f7a4d63ab64bd74d5102346",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-qwen3-5-35b-a3b-2026-08-29","aa-current-qwen3-5-35b-a3b-2026-08-29","identity|configuration|result|verification","Qwen3.5 35B A3B (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-5-35b-a3b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-02-24",null,"2026-08-29",null,"6188856d44c4b1075729e77878c90c4f11cbd4666f2d9d904f24bf754f2b40db",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-qwen3-5-397b-reasoning-2026-08-29","aa-current-qwen3-5-397b-reasoning-2026-08-29","identity|configuration|result|verification","Qwen3.5 397B A17B (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-5-397b-a17b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-02-16",null,"2026-08-29",null,"db029e09f785e4a4b9d99226c3e8011d95b51012666b6dfecde8ed756ecd6a5f",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-qwen3-6-35b-a3b-2026-08-29","aa-current-qwen3-6-35b-a3b-2026-08-29","identity|configuration|result|verification","Qwen3.6 35B A3B (Reasoning) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-6-35b-a3b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-16",null,"2026-08-29",null,"d0ce0ba554b933e861200fbb882bf5b0abea6bbb3927ec3b61ab60e091788d92",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::aa-current-qwen3-6-max-preview-2026-08-29","aa-current-qwen3-6-max-preview-2026-08-29","identity|configuration|result|verification","Qwen3.6 Max Preview current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-6-max","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-20",null,"2026-08-29",null,"33c3f136f75ec9d9e19b0f0b688dbca5bbe78d3f30a1d52621112a88e8485f85",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-qwen-3-8-flash-next-2026-08-29","aa-current-qwen-3-8-flash-next-2026-08-29","identity|configuration|result|verification","Qwen3.8-Flash-Next individual evaluations","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-8-flash-next","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-08-26",null,"2026-08-29",null,"530044897119df9b6cb19f1d488d903b09a43470d21de8ee2beb1b1bbc077376",null,null,"metadata-only","source-checked",null,null,"Current public model page exposes Artificial Analysis individual evaluations. Composite indices are excluded. The page does not identify the reasoning-effort label required to match the ranked default, so every individual row remains reference-only."],["production::aa-current-sarvam-105b-2026-08-29","aa-current-sarvam-105b-2026-08-29","identity|configuration|result|verification","Sarvam 105B (high) current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/sarvam-105b","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-03-06",null,"2026-08-29",null,"a74f13f0f469c1391056a71b4589d50aad988edd47fa2b56cdcd9e4ab27f1a1a",null,null,"metadata-only","source-checked",null,null,"Current page exposes an exact model/configuration label, but marks the Intelligence evaluation estimated. Estimated individual fields are not admitted as observations."],["production::aa-current-trinity-large-thinking-2026-08-29","aa-current-trinity-large-thinking-2026-08-29","identity|configuration|result|verification","Trinity Large Thinking current model and individual-evaluation page","Artificial Analysis","https://artificialanalysis.ai/models/trinity-large-thinking","independent-lab","independent-lab","source-checked","identity|configuration|result|verification","2026-04-01",null,"2026-08-29",null,"ae0c3b1ec84a326555f74b98f70939ad2edc4efb79c839cc87d2f389e8b36f27",null,null,"metadata-only","source-checked",null,null,"Current page exposes completed individual evaluator results and an exact reasoning-mode configuration. Composite indices are excluded."],["production::deepseek-v3-1-modes-2026-08-29","deepseek-v3-1-modes-2026-08-29","identity|configuration|result|verification","DeepSeek V3.1 official thinking and non-thinking mode mapping","DeepSeek","https://api-docs.deepseek.com/news/news250821/","official-provider-evaluation","official-provider-evaluation","source-checked","identity|configuration|result|verification","2025-08-21",null,"2026-08-29",null,"77cfd4747bdf7e4734531e57fcedd4b5350803d08e52beee2413d643d2449762",null,null,"metadata-only","source-checked",null,null,"First-party release material explicitly maps DeepSeek V3.1 thinking mode to deepseek-reasoner and non-thinking mode to deepseek-chat."],["production::qwen-models","qwen-models","identity|configuration|specification|availability","Text generation models","Alibaba Cloud","https://www.alibabacloud.com/help/en/model-studio/text-generation-model","official-docs","official-docs","source-checked","identity|configuration|specification|availability",null,null,"2026-08-30",null,"0cfc65678b3277c842e9d8abdecfed9cac2d11ca8e3ed0a786033fec40bd16ae",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 0cfc65678b3277c842e9d8abdecfed9cac2d11ca8e3ed0a786033fec40bd16ae."],["production::deepseek-v4-flash-vision-exp-guide","deepseek-v4-flash-vision-exp-guide","identity|configuration|specification|availability","DeepSeek image understanding guide","DeepSeek","https://api-docs.deepseek.com/zh-cn/guides/vision/","official-docs","official-docs","source-checked","identity|configuration|specification|availability","2026-08-21",null,"2026-08-23",null,null,null,null,"metadata-only","source-checked",null,null,"Official endpoint and image-input documentation for the exact experimental model."],["production::refresh-zai-openapi","refresh-zai-openapi","identity|configuration|specification|availability","Z.AI permanent refresh source","Z.AI","https://docs.z.ai/openapi.json","official-docs","official-docs","source-checked","identity|configuration|specification|availability",null,null,"2026-08-07",null,null,"Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter zai-openapi-v2@2.0.0; role automatic."],["production::qwen3-8-flash-next-huggingface-2026-08-26","qwen3-8-flash-next-huggingface-2026-08-26","identity|configuration|specification|availability|licence","Qwen3.8-Flash-Next official model card and weights","Qwen","https://huggingface.co/Qwen/Qwen3.8-Flash-Next","official-model-card","official-model-card","source-checked","identity|configuration|specification|availability|licence","2026-08-24",null,"2026-08-26","f5d08274bafd880402bd16f5e3e6c514136ec06c","d75f249f4024af64518a5cb1fbb3d3f133eb09d3bce40be48df2e456e1c8cf46","Qwen Community License 1.0",null,"metadata-only","source-checked",null,null,"Official public, ungated model repository with the exact configuration and 131 safetensor shards present at the checked revision."],["production::qwen3-8-flash-next-repository-2026-08-26","qwen3-8-flash-next-repository-2026-08-26","identity|configuration|specification|availability|licence","Qwen3.8-Flash-Next official repository and technical report","Qwen","https://github.com/QwenLM/Qwen3.8-Flash-Next","official-repository","official-repository","source-checked","identity|configuration|specification|availability|licence","2026-08-24",null,"2026-08-26",null,null,null,null,"metadata-only","source-checked",null,null,"Official public source repository containing the technical report and links to the exact weight artifacts."],["production::zai-glm-5-3-flash-model-card-2026-08-27","zai-glm-5-3-flash-model-card-2026-08-27","identity|configuration|specification|availability|licence","GLM-5.3-Flash official model card and open weights","Z.AI","https://huggingface.co/zai-org/GLM-5.3-Flash","official-model-card","official-model-card","source-checked","identity|configuration|specification|availability|licence","2026-08-26",null,"2026-08-27",null,null,"MIT",null,"metadata-only","source-checked",null,null,"Official Z.AI Hugging Face repository for the distinct GLM-5.3-Flash weights under MIT."],["production::alibaba-qwen37-max-detail-2026-08-30","alibaba-qwen37-max-detail-2026-08-30","identity|configuration|specification|availability|pricing","qwen3.7-max model details","Alibaba Cloud","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-max","official-model-card","official-model-card","source-checked","identity|configuration|specification|availability|pricing",null,null,"2026-08-30",null,"33e8bbc93cc03691da703b3317c9dc7be86f1bbaaa653062b48cc61d38c7f6e7",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 33e8bbc93cc03691da703b3317c9dc7be86f1bbaaa653062b48cc61d38c7f6e7."],["production::meta-muse-spark-1-2-multimodal-2026-08-20","meta-muse-spark-1-2-multimodal-2026-08-20","identity|configuration|specification|availability|result|verification","Multimodal Intelligence of Muse Spark 1.2","Meta Superintelligence Labs","https://research.meta.ai/blog/multimodal-intelligence-of-muse-spark-1-2","official-provider-evaluation","official-provider-evaluation","source-checked","identity|configuration|specification|availability|result|verification","2026-08-20",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Official Meta multimodal follow-up with complete benchmark charts. Image generation and design-arena material is excluded from core-model intake. Fresh Luke-supplied official asset provenance was hash-verified on 2026-08-27; current official evidence takes precedence over archived extraction."],["production::openai-model-catalogue-2026-08-29","openai-model-catalogue-2026-08-29","identity|configuration|specification|verification","OpenAI API model catalogue","OpenAI","https://platform.openai.com/docs/models","official-docs","official-docs","source-checked","identity|configuration|specification|verification","2026-08-29",null,"2026-08-29",null,"72c9a7c7fe595f2e6dce27744d8c89471b6bdc806994d04fb79304c0f9018072",null,null,"metadata-only","source-checked",null,null,"Current first-party catalogue identifies GPT-4.1 as non-reasoning and lists the GPT-4.1 family variants."],["production::refresh-aa-language-models","refresh-aa-language-models","identity|external-identity|external-index|pricing|operational|result|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/language/models/free","independent-lab","independent-lab","source-checked","identity|external-identity|external-index|pricing|operational|result|verification",null,null,"2026-08-08",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-language-v2@2.0.0; role automatic."],["production::refresh-anthropic-news","refresh-anthropic-news","identity|lifecycle","Anthropic permanent refresh source","Anthropic","https://www.anthropic.com/news","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter anthropic-news-reviewed-html@2.0.0; role release-triggered."],["production::refresh-cohere-blog","refresh-cohere-blog","identity|lifecycle","Cohere permanent refresh source","Cohere","https://cohere.com/blog","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"Cohere source terms","Cohere (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter cohere-blog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-deepseek-news","refresh-deepseek-news","identity|lifecycle","DeepSeek permanent refresh source","DeepSeek","https://api-docs.deepseek.com/news","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter deepseek-news-reviewed-html@2.0.0; role release-triggered."],["production::google-gemini-deprecations-2026-08-30","google-gemini-deprecations-2026-08-30","identity|lifecycle","Gemini API model deprecations","Google","https://ai.google.dev/gemini-api/docs/deprecations","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-30",null,"8b6ff3e6f1708bb5e2b6fe62b2c019018d763b8379ffe7553957d29702c92b76",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 8b6ff3e6f1708bb5e2b6fe62b2c019018d763b8379ffe7553957d29702c92b76."],["production::refresh-google-deepmind-blog","refresh-google-deepmind-blog","identity|lifecycle","Google DeepMind permanent refresh source","Google DeepMind","https://deepmind.google/blog/","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"Google DeepMind source terms","Google DeepMind (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter google-deepmind-blog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-meta-ai-blog","refresh-meta-ai-blog","identity|lifecycle","Meta permanent refresh source","Meta","https://ai.meta.com/blog/","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"Meta source terms","Meta (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter meta-ai-blog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-microsoft-ai-blog","refresh-microsoft-ai-blog","identity|lifecycle","Microsoft permanent refresh source","Microsoft","https://microsoft.ai/blog/","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"Microsoft source terms","Microsoft (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter microsoft-ai-blog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-minimax-blog","refresh-minimax-blog","identity|lifecycle","MiniMax permanent refresh source","MiniMax","https://www.minimax.io/blog","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"MiniMax source terms","MiniMax (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter minimax-blog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-mistral-news","refresh-mistral-news","identity|lifecycle","Mistral AI permanent refresh source","Mistral AI","https://mistral.ai/news/","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"Mistral AI source terms","Mistral AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter mistral-news-reviewed-html@2.0.0; role release-triggered."],["production::refresh-moonshot-blog","refresh-moonshot-blog","identity|lifecycle","Moonshot AI permanent refresh source","Moonshot AI","https://www.kimi.ai/blog/","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-30",null,null,"Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter moonshot-blog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-openai-news","refresh-openai-news","identity|lifecycle","OpenAI permanent refresh source","OpenAI","https://openai.com/news/","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-08",null,null,"OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter openai-news-reviewed-html@2.0.0; role release-triggered."],["production::refresh-thinking-machines-news","refresh-thinking-machines-news","identity|lifecycle","Thinking Machines Lab permanent refresh source","Thinking Machines Lab","https://thinkingmachines.ai/news/","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"Thinking Machines Lab source terms","Thinking Machines Lab (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter thinking-machines-news-reviewed-html@2.0.0; role release-triggered."],["production::refresh-zai-release-notes","refresh-zai-release-notes","identity|lifecycle","Z.AI permanent refresh source","Z.AI","https://docs.z.ai/release-notes/new-released","official-docs","official-docs","source-checked","identity|lifecycle",null,null,"2026-08-07",null,null,"Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter zai-release-notes-reviewed-html@2.0.0; role release-triggered."],["production::refresh-azure-foundry-updates","refresh-azure-foundry-updates","identity|lifecycle|availability","Microsoft permanent refresh source","Microsoft","https://learn.microsoft.com/en-us/azure/foundry/whats-new-foundry","official-docs","official-docs","source-checked","identity|lifecycle|availability",null,null,"2026-08-07",null,null,"Microsoft source terms","Microsoft (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter azure-foundry-updates-reviewed-html@2.0.0; role release-triggered."],["production::deepseek-v4-flash-vision-exp-release","deepseek-v4-flash-vision-exp-release","identity|lifecycle|availability|configuration|result|verification","DeepSeek-V4-Flash-Vision-Exp release and provider evaluation","DeepSeek","https://api-docs.deepseek.com/zh-cn/updates/","official-provider-evaluation","official-provider-evaluation","source-checked","identity|lifecycle|availability|configuration|result|verification","2026-08-21",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Official DeepSeek changelog release. Provider-reported comparison cells remain one evidence event and do not constitute independent confirmation. Fresh Luke-supplied official asset provenance was hash-verified on 2026-08-27; current official evidence takes precedence over archived extraction."],["production::qwen3-8-flash-next-release-current-2026-08-27","qwen3-8-flash-next-release-current-2026-08-27","identity|lifecycle|availability|configuration|specification|result|verification","Qwen3.8-Flash-Next current official launch page","Qwen","https://qwen.ai/blog?id=qwen3.8-flash-next","official-provider-evaluation","official-provider-evaluation","source-checked","identity|lifecycle|availability|configuration|specification|result|verification","2026-08-26",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Current official page fetched on 2026-08-27. Archived screenshots remain a subordinate extraction cache for the same provider publication."],["production::qwen3-8-flash-next-release-2026-08-26","qwen3-8-flash-next-release-2026-08-26","identity|lifecycle|availability|configuration|specification|result|verification","Qwen3.8-Flash-Next launch and official provider evaluations","Qwen","https://qwen.ai/blog?id=qwen3.8-flash-next","official-provider-evaluation","official-provider-evaluation","source-checked","identity|lifecycle|availability|configuration|specification|result|verification","2026-08-26",null,"2026-08-26",null,null,null,null,"allowed","source-checked",null,null,"Official launch source for identity, architecture, model availability, configuration guidance and the two supplied comparison tables. Provider comparisons form one evidence event and are not independent corroboration."],["production::deepseek-v4-flash-0731-model-card","deepseek-v4-flash-0731-model-card","identity|lifecycle|configuration|result|verification","DeepSeek-V4-Flash-0731 official model card and provider evaluation","DeepSeek","https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731","official-model-card","official-model-card","source-checked","identity|lifecycle|configuration|result|verification","2026-07-31",null,"2026-08-24",null,null,null,null,"metadata-only","source-checked",null,null,"Official source-native subject table. Code-agent rows use DeepSeek Harness Minimal Mode, max reasoning effort, temperature 1.0 and top_p 0.95. Internal DSBench rows remain reference-only."],["production::zai-glm-5-3-flash-blog-2026-08-26","zai-glm-5-3-flash-blog-2026-08-26","identity|lifecycle|configuration|specification|availability|result|verification","GLM-5.3-Flash official launch and evaluation","Z.AI","https://z.ai/blog/glm-5.3-flash","official-provider-evaluation","official-provider-evaluation","source-checked","identity|lifecycle|configuration|specification|availability|result|verification","2026-08-26",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Official launch article and complete provider comparison evidence. Competitor cells are one non-independent provider event. Fresh Luke-supplied official asset provenance was hash-verified on 2026-08-27; current official evidence takes precedence over archived extraction."],["production::refresh-benchlm-updates","refresh-benchlm-updates","identity|lifecycle|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/updates.json","independent-registry","independent-registry","source-checked","identity|lifecycle|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-corroboration-v2@2.0.0; role corroboration."],["production::refresh-sakana-feed","refresh-sakana-feed","identity|lifecycle|discovery","Sakana AI permanent refresh source","Sakana AI","https://sakana.ai/feed.xml","official-docs","official-docs","source-checked","identity|lifecycle|discovery",null,null,"2026-08-07",null,null,"Sakana AI source terms","Sakana AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter sakana-atom-v2@2.0.0; role release-triggered."],["production::tencent-hy4-preview-research-2026-08-27","tencent-hy4-preview-research-2026-08-27","identity|lifecycle|result|verification","Hy4 Preview official research page","Tencent Hy Team","https://hy.tencent.ai/research/hy4-preview","official-provider-evaluation","official-provider-evaluation","source-checked","identity|lifecycle|result|verification","2026-08-27",null,"2026-08-30",null,"1e8a6d8ab449fdb0879ca776a8884d1960bb6478c1eb6d4c60cf9db5e39d59f9",null,null,"metadata-only","source-checked",null,null,"User-supplied capture of the official Tencent research table. Exact Hy4 subject values are preserved, but benchmark-specific configurations are not inferred."],["production::refresh-anthropic-release-notes","refresh-anthropic-release-notes","identity|lifecycle|specification","Anthropic permanent refresh source","Anthropic","https://platform.claude.com/docs/en/release-notes/overview","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter anthropic-release-notes-reviewed-html@2.0.0; role release-triggered."],["production::refresh-bytedance-seed-github","refresh-bytedance-seed-github","identity|lifecycle|specification","ByteDance Seed permanent refresh source","ByteDance Seed","https://github.com/ByteDance-Seed","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"ByteDance Seed source terms","ByteDance Seed (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter bytedance-seed-github-github-api@2.0.0; role discovery-only."],["production::refresh-bytedance-seed-huggingface","refresh-bytedance-seed-huggingface","identity|lifecycle|specification","ByteDance Seed permanent refresh source","ByteDance Seed","https://huggingface.co/ByteDance-Seed","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"ByteDance Seed source terms","ByteDance Seed (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter bytedance-seed-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-bytedance-seed-site","refresh-bytedance-seed-site","identity|lifecycle|specification","ByteDance Seed permanent refresh source","ByteDance Seed","https://seed.bytedance.com/en/","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"ByteDance Seed source terms","ByteDance Seed (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter bytedance-seed-site-reviewed-html@2.0.0; role release-triggered."],["production::refresh-cohere-changelog","refresh-cohere-changelog","identity|lifecycle|specification","Cohere permanent refresh source","Cohere","https://docs.cohere.com/v2/changelog","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"Cohere source terms","Cohere (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter cohere-lifecycle-v2@2.1.0; role release-triggered."],["production::refresh-cohere-models","refresh-cohere-models","identity|lifecycle|specification","Cohere permanent refresh source","Cohere","https://docs.cohere.com/docs/models","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Cohere source terms","Cohere (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter cohere-models-reviewed-html@2.0.0; role release-triggered."],["production::refresh-cursor-changelog","refresh-cursor-changelog","identity|lifecycle|specification","Cursor permanent refresh source","Cursor","https://cursor.com/changelog","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Cursor source terms","Cursor (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter cursor-changelog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-deepseek-github","refresh-deepseek-github","identity|lifecycle|specification","DeepSeek permanent refresh source","DeepSeek","https://github.com/deepseek-ai","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter deepseek-github-github-api@2.0.0; role discovery-only."],["production::refresh-deepseek-huggingface","refresh-deepseek-huggingface","identity|lifecycle|specification","DeepSeek permanent refresh source","DeepSeek","https://huggingface.co/deepseek-ai","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter deepseek-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-google-gemini-changelog","refresh-google-gemini-changelog","identity|lifecycle|specification","Google permanent refresh source","Google","https://ai.google.dev/gemini-api/docs/changelog","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter google-gemini-changelog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-meta-llama-github","refresh-meta-llama-github","identity|lifecycle|specification","Meta permanent refresh source","Meta","https://github.com/meta-llama","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"Meta source terms","Meta (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter meta-llama-github-github-api@2.0.0; role discovery-only."],["production::refresh-meta-llama-huggingface","refresh-meta-llama-huggingface","identity|lifecycle|specification","Meta permanent refresh source","Meta","https://huggingface.co/meta-llama","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Meta source terms","Meta (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter meta-llama-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-microsoft-huggingface","refresh-microsoft-huggingface","identity|lifecycle|specification","Microsoft permanent refresh source","Microsoft","https://huggingface.co/microsoft","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Microsoft source terms","Microsoft (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter microsoft-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-minimax-github","refresh-minimax-github","identity|lifecycle|specification","MiniMax permanent refresh source","MiniMax","https://github.com/MiniMax-AI","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"MiniMax source terms","MiniMax (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter minimax-github-github-api@2.0.0; role discovery-only."],["production::refresh-minimax-huggingface","refresh-minimax-huggingface","identity|lifecycle|specification","MiniMax permanent refresh source","MiniMax","https://huggingface.co/MiniMaxAI","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"MiniMax source terms","MiniMax (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter minimax-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-minimax-release-notes","refresh-minimax-release-notes","identity|lifecycle|specification","MiniMax permanent refresh source","MiniMax","https://platform.minimax.io/docs/release-notes/models","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"MiniMax source terms","MiniMax (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter minimax-release-notes-reviewed-html@2.0.0; role release-triggered."],["production::refresh-mistral-changelog","refresh-mistral-changelog","identity|lifecycle|specification","Mistral AI permanent refresh source","Mistral AI","https://docs.mistral.ai/resources/changelogs","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Mistral AI source terms","Mistral AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter mistral-changelog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-mistral-models","refresh-mistral-models","identity|lifecycle|specification","Mistral AI permanent refresh source","Mistral AI","https://docs.mistral.ai/models/overview","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Mistral AI source terms","Mistral AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter mistral-models-reviewed-html@2.0.0; role release-triggered."],["production::refresh-moonshot-github","refresh-moonshot-github","identity|lifecycle|specification","Moonshot AI permanent refresh source","Moonshot AI","https://github.com/MoonshotAI","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter moonshot-github-github-api@2.0.0; role discovery-only."],["production::refresh-moonshot-huggingface","refresh-moonshot-huggingface","identity|lifecycle|specification","Moonshot AI permanent refresh source","Moonshot AI","https://huggingface.co/moonshotai","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter moonshot-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-nvidia-huggingface","refresh-nvidia-huggingface","identity|lifecycle|specification","NVIDIA permanent refresh source","NVIDIA","https://huggingface.co/nvidia","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"NVIDIA source terms","NVIDIA (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter nvidia-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-qwen-blog","refresh-qwen-blog","identity|lifecycle|specification","Qwen permanent refresh source","Qwen","https://qwen.ai/blog","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter qwen-blog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-qwen-github","refresh-qwen-github","identity|lifecycle|specification","Qwen permanent refresh source","Qwen","https://github.com/QwenLM","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter qwen-github-github-api@2.0.0; role discovery-only."],["production::refresh-qwen-huggingface","refresh-qwen-huggingface","identity|lifecycle|specification","Qwen permanent refresh source","Qwen","https://huggingface.co/Qwen","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter qwen-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-qwen-modelscope","refresh-qwen-modelscope","identity|lifecycle|specification","Qwen permanent refresh source","Qwen","https://modelscope.cn/organization/qwen","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter qwen-modelscope-reviewed-html@2.0.0; role manual-review."],["production::refresh-sakana-huggingface","refresh-sakana-huggingface","identity|lifecycle|specification","Sakana AI permanent refresh source","Sakana AI","https://huggingface.co/SakanaAI","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Sakana AI source terms","Sakana AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter sakana-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-stepfun-github","refresh-stepfun-github","identity|lifecycle|specification","StepFun permanent refresh source","StepFun","https://github.com/stepfun-ai","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"StepFun source terms","StepFun (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter stepfun-github-github-api@2.0.0; role discovery-only."],["production::refresh-stepfun-huggingface","refresh-stepfun-huggingface","identity|lifecycle|specification","StepFun permanent refresh source","StepFun","https://huggingface.co/stepfun-ai","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"StepFun source terms","StepFun (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter stepfun-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-tencent-hunyuan-github","refresh-tencent-hunyuan-github","identity|lifecycle|specification","Tencent Hunyuan permanent refresh source","Tencent Hunyuan","https://github.com/Tencent-Hunyuan","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"Tencent Hunyuan source terms","Tencent Hunyuan (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter tencent-hunyuan-github-github-api@2.0.0; role discovery-only."],["production::refresh-tencent-hunyuan-huggingface","refresh-tencent-hunyuan-huggingface","identity|lifecycle|specification","Tencent Hunyuan permanent refresh source","Tencent Hunyuan","https://huggingface.co/tencent","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Tencent Hunyuan source terms","Tencent Hunyuan (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter tencent-hunyuan-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-xai-release-notes","refresh-xai-release-notes","identity|lifecycle|specification","xAI permanent refresh source","xAI","https://docs.x.ai/developers/release-notes","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"xAI source terms","xAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter xai-release-notes-reviewed-html@2.0.0; role release-triggered."],["production::refresh-xiaomi-mimo-github","refresh-xiaomi-mimo-github","identity|lifecycle|specification","Xiaomi MiMo permanent refresh source","Xiaomi MiMo","https://github.com/XiaomiMiMo","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"Xiaomi MiMo source terms","Xiaomi MiMo (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter xiaomi-mimo-github-github-api@2.0.0; role discovery-only."],["production::refresh-xiaomi-mimo-huggingface","refresh-xiaomi-mimo-huggingface","identity|lifecycle|specification","Xiaomi MiMo permanent refresh source","Xiaomi MiMo","https://huggingface.co/XiaomiMiMo","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Xiaomi MiMo source terms","Xiaomi MiMo (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter xiaomi-mimo-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-zai-github","refresh-zai-github","identity|lifecycle|specification","Z.AI permanent refresh source","Z.AI","https://github.com/zai-org","official-repository","official-repository","source-checked","identity|lifecycle|specification",null,null,"2026-08-08",null,null,"Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter zai-github-github-api@2.0.0; role discovery-only."],["production::refresh-zai-huggingface","refresh-zai-huggingface","identity|lifecycle|specification","Z.AI permanent refresh source","Z.AI","https://huggingface.co/zai-org","official-docs","official-docs","source-checked","identity|lifecycle|specification",null,null,"2026-08-07",null,null,"Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter zai-huggingface-reviewed-html@2.0.0; role manual-review."],["production::minimax-m3-license-2026-08-30","minimax-m3-license-2026-08-30","identity|lifecycle|specification|availability|licence","MiniMax-M3 official model licence","MiniMax","https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE","official-model-card","official-model-card","source-checked","identity|lifecycle|specification|availability|licence","2026-06-01",null,"2026-08-30",null,"5f72583de592c62fe5b1eff68bcbc5fd67978af6191dc1dbe67c77ef5098a5e6",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 5f72583de592c62fe5b1eff68bcbc5fd67978af6191dc1dbe67c77ef5098a5e6."],["production::xiaomi-mimo-v2-5-pro-huggingface-2026-08-30","xiaomi-mimo-v2-5-pro-huggingface-2026-08-30","identity|lifecycle|specification|availability|licence","MiMo-V2.5-Pro official model card and weights","Xiaomi MiMo","https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","official-model-card","official-model-card","source-checked","identity|lifecycle|specification|availability|licence","2026-04-27",null,"2026-08-30",null,"097abdcafb44f6bb23b42246ef5b98a1937dab38a19bf4cdec94acfc2985169d",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 097abdcafb44f6bb23b42246ef5b98a1937dab38a19bf4cdec94acfc2985169d."],["production::xiaomi-mimo-v2-5-pro-release-2026-08-30","xiaomi-mimo-v2-5-pro-release-2026-08-30","identity|lifecycle|specification|availability|licence","Xiaomi MiMo-V2.5-Pro release","Xiaomi MiMo","https://mimo.xiaomi.com/mimo-v2-5-pro/","official-model-card","official-model-card","source-checked","identity|lifecycle|specification|availability|licence","2026-04-27",null,"2026-08-30",null,"169c17e63ed923dde2ec4bcf53abeaef2de46d38412488aeea8f9c697fdff03f",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 169c17e63ed923dde2ec4bcf53abeaef2de46d38412488aeea8f9c697fdff03f."],["production::zai-glm-5-2-huggingface-2026-08-30","zai-glm-5-2-huggingface-2026-08-30","identity|lifecycle|specification|availability|licence","GLM-5.2 official model card","Z.AI","https://huggingface.co/zai-org/GLM-5.2","official-model-card","official-model-card","source-checked","identity|lifecycle|specification|availability|licence","2026-06-16",null,"2026-08-30",null,"6d80b6e55acb578a5ef397409ce6ca049a713c65aee534eee7dcddee0e96f625",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 6d80b6e55acb578a5ef397409ce6ca049a713c65aee534eee7dcddee0e96f625."],["production::refresh-poolside-laguna-xs-2-1-release","refresh-poolside-laguna-xs-2-1-release","identity|lifecycle|specification|availability|verification","Poolside permanent refresh source","Poolside","https://poolside.ai/blog/introducing-laguna-xs-2-1","official-docs","official-docs","source-checked","identity|lifecycle|specification|availability|verification",null,null,"2026-08-22",null,null,"Poolside source terms","Poolside (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter poolside-laguna-xs-2-1-release-reviewed-html@2.0.0; role manual-review."],["production::refresh-openai-gpt-oss-120b-model","refresh-openai-gpt-oss-120b-model","identity|lifecycle|specification|licence|availability|verification","OpenAI checked metadata source","OpenAI","https://developers.openai.com/api/docs/models/gpt-oss-120b","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|availability|verification",null,null,"2026-08-20",null,"79f83cfea0ee8d0a0f9915e05ca25c3edae8c73ab5b5246e5104b04261966634","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Manual metadata review using openai-gpt-oss-120b-model-reviewed-html@2.0.0; no capability evidence was admitted."],["production::refresh-moonshot-kimi-k3-official","refresh-moonshot-kimi-k3-official","identity|lifecycle|specification|licence|pricing|verification","Moonshot AI checked metadata source","Moonshot AI","https://www.kimi.ai/blog/kimi-k3","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|pricing|verification",null,null,"2026-08-20",null,"cf89d33303866b0f33ab43d99dafbcbed7fbc68230d67acc7119acdb5d9f357c","Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Manual metadata review using moonshot-kimi-k3-official-reviewed-html@2.0.0; no capability evidence was admitted."],["production::refresh-deepseek-v4-pro-0813-huggingface","refresh-deepseek-v4-pro-0813-huggingface","identity|lifecycle|specification|licence|verification","DeepSeek checked metadata source","DeepSeek","https://huggingface.co/api/models/deepseek-ai/DeepSeek-V4-Pro-0813","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|verification",null,null,"2026-08-20",null,"f4990d033dd8fdb983b656e8b54776e4459348091e0a7c6b494f85fc883c4315","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Manual metadata review using deepseek-huggingface-model-v1@2.0.0; no capability evidence was admitted."],["production::refresh-inclusionai-huggingface","refresh-inclusionai-huggingface","identity|lifecycle|specification|licence|verification","InclusionAI permanent refresh source","InclusionAI","https://huggingface.co/inclusionAI","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|verification",null,null,"2026-08-22",null,null,"InclusionAI source terms","InclusionAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter inclusionai-huggingface-reviewed-html@2.0.0; role manual-review."],["production::refresh-longcat-2-0-model-card","refresh-longcat-2-0-model-card","identity|lifecycle|specification|licence|verification","Meituan LongCat permanent refresh source","Meituan LongCat","https://huggingface.co/meituan-longcat/LongCat-2.0","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|verification",null,null,"2026-08-22",null,null,"Meituan LongCat source terms","Meituan LongCat (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter longcat-2-0-model-card-reviewed-html@2.0.0; role manual-review."],["production::refresh-longcat-2-0-release","refresh-longcat-2-0-release","identity|lifecycle|specification|licence|verification","Meituan LongCat permanent refresh source","Meituan LongCat","https://longcat.ai/blog/longcat-2.0","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|verification",null,null,"2026-08-22",null,null,"Meituan LongCat source terms","Meituan LongCat (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter longcat-2-0-release-reviewed-html@2.0.0; role manual-review."],["production::refresh-moonshot-kimi-k3-repository","refresh-moonshot-kimi-k3-repository","identity|lifecycle|specification|licence|verification","Moonshot AI checked metadata source","Moonshot AI","https://github.com/MoonshotAI/Kimi-K3","official-repository","official-repository","source-checked","identity|lifecycle|specification|licence|verification",null,null,"2026-08-20",null,"5dee38c76cd469d5e616a6126d709b405f76fc180ceda0c8d35450ef84e71295","Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Manual metadata review using moonshot-kimi-k3-repository-github-api@2.0.0; no capability evidence was admitted."],["production::refresh-poolside-laguna-xs-2-1-model-card","refresh-poolside-laguna-xs-2-1-model-card","identity|lifecycle|specification|licence|verification","Poolside permanent refresh source","Poolside","https://huggingface.co/poolside/Laguna-XS-2.1","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|verification",null,null,"2026-08-22",null,null,"Poolside source terms","Poolside (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter poolside-laguna-xs-2-1-model-card-reviewed-html@2.0.0; role manual-review."],["production::refresh-qwen-3-8-max-huggingface","refresh-qwen-3-8-max-huggingface","identity|lifecycle|specification|licence|verification","Qwen checked metadata source","Qwen","https://huggingface.co/api/models/Qwen/Qwen3.8-2.4T-A95B","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|verification",null,null,"2026-08-20",null,"097b8ba1517cb6964bf99027b439269f0da9808034a8431e96e7183bd96609c0","Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Manual metadata review using qwen-huggingface-model-v1@2.0.0; no capability evidence was admitted."],["production::refresh-upstage-solar-open2-250b-model-card","refresh-upstage-solar-open2-250b-model-card","identity|lifecycle|specification|licence|verification","Upstage permanent refresh source","Upstage","https://huggingface.co/upstage/Solar-Open2-250B","official-docs","official-docs","source-checked","identity|lifecycle|specification|licence|verification",null,null,"2026-08-22",null,null,"Upstage source terms","Upstage (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter upstage-solar-open2-250b-model-card-reviewed-html@2.0.0; role manual-review."],["production::refresh-deepseek-docs","refresh-deepseek-docs","identity|lifecycle|specification|pricing","DeepSeek permanent refresh source","DeepSeek","https://api-docs.deepseek.com/","official-docs","official-docs","source-checked","identity|lifecycle|specification|pricing",null,null,"2026-08-07",null,null,"DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter deepseek-docs-reviewed-html@2.0.0; role release-triggered."],["production::refresh-openai-changelog","refresh-openai-changelog","identity|lifecycle|specification|pricing","OpenAI permanent refresh source","OpenAI","https://developers.openai.com/api/docs/changelog","official-docs","official-docs","source-checked","identity|lifecycle|specification|pricing",null,null,"2026-08-07",null,null,"OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter openai-changelog-reviewed-html@2.0.0; role release-triggered."],["production::refresh-aa-image-editing-api","refresh-aa-image-editing-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/image-editing/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::refresh-aa-image-to-video-api","refresh-aa-image-to-video-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/image-to-video/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::refresh-aa-image-to-video-audio-api","refresh-aa-image-to-video-audio-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/image-to-video-audio/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::refresh-aa-speech-to-speech-api","refresh-aa-speech-to-speech-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/speech-to-speech/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::refresh-aa-speech-to-text-api","refresh-aa-speech-to-text-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/speech-to-text/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::refresh-aa-text-to-image-api","refresh-aa-text-to-image-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/text-to-image/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::refresh-aa-text-to-speech-api","refresh-aa-text-to-speech-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/text-to-speech/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::refresh-aa-text-to-video-api","refresh-aa-text-to-video-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/text-to-video/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::refresh-aa-text-to-video-audio-api","refresh-aa-text-to-video-audio-api","identity|pricing|operational|media|verification","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/text-to-video-audio/models/free","independent-lab","independent-lab","source-checked","identity|pricing|operational|media|verification",null,null,"2026-08-07",null,null,"Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","source-checked",null,null,"Adapter artificial-analysis-media-v2@2.0.0; role automatic."],["production::zai-glm-5-3-flash-docs-2026-08-27","zai-glm-5-3-flash-docs-2026-08-27","identity|provider-surface|model-offering|configuration|specification|availability","GLM-5.3-Flash official API documentation","Z.AI","https://docs.z.ai/guides/llm/glm-5.3-flash","official-docs","official-docs","source-checked","identity|provider-surface|model-offering|configuration|specification|availability","2026-08-26",null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Official endpoint documentation for glm-5.3-flash, 1M context, supported multimodal inputs, tools, structured output and low/high/max effort controls."],["production::refresh-aa-model-leaderboard","refresh-aa-model-leaderboard","identity|result|operational","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/leaderboards/models","independent-lab","independent-lab","source-checked","identity|result|operational",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-model-leaderboard-reviewed-html@2.0.0; role manual-review."],["production::anthropic-fable-mythos-5-1-launch-2026-09-01","anthropic-fable-mythos-5-1-launch-2026-09-01","identity|safeguards|benchmark matrix|benchmark footnotes|release","Claude Fable 5.1 and Mythos 5.1","Anthropic","https://www.anthropic.com/claude-fable-and-mythos-5-1","official-provider-evaluation","official-provider-evaluation","source-checked","identity|safeguards|benchmark matrix|benchmark footnotes|release","2026-09-01",null,"2026-09-01",null,"b9bd5957969f6d319f7fe13bc5aac18ee7b9a4afe373122c8194eb81243d1eca",null,null,"metadata-only","source-checked",null,null,"Official launch page. Fable 5.1 and Mythos 5.1 are one underlying model with different safeguard/access conditions. The full comparison table is one correlated provider launch event."],["production::refresh-thudm-legacy","refresh-thudm-legacy","identity|specification","THUDM permanent refresh source","THUDM","https://github.com/THUDM","official-docs","official-docs","source-checked","identity|specification",null,null,"2026-08-07",null,null,"THUDM source terms","THUDM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter thudm-legacy-reviewed-html@2.0.0; role historical."],["production::anthropic-programmatic-tool-calling-2026-08-30","anthropic-programmatic-tool-calling-2026-08-30","identity|specification|availability","Programmatic tool calling","Anthropic","https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling","official-docs","official-docs","source-checked","identity|specification|availability",null,null,"2026-08-30",null,"1340ff8d75a8a101efc502085aa43cb5dfeccaf2a10da5c3ea1b3a9c41fe8121",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 1340ff8d75a8a101efc502085aa43cb5dfeccaf2a10da5c3ea1b3a9c41fe8121."],["production::google-gemini-function-calling-2026-08-30","google-gemini-function-calling-2026-08-30","identity|specification|availability","Function calling with the Gemini API","Google","https://ai.google.dev/gemini-api/docs/generate-content/function-calling","official-docs","official-docs","source-checked","identity|specification|availability",null,null,"2026-08-30",null,"7024596081f8808cffb1ce05fc355bd3aa1edf064f80f1431c69df8f5f008f3d",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 7024596081f8808cffb1ce05fc355bd3aa1edf064f80f1431c69df8f5f008f3d."],["production::openai-models","openai-models","identity|specification|availability|pricing","Models | OpenAI API","OpenAI","https://developers.openai.com/api/docs/models","official-docs","official-docs","source-checked","identity|specification|availability|pricing",null,null,"2026-08-30",null,"72c9a7c7fe595f2e6dce27744d8c89471b6bdc806994d04fb79304c0f9018072",null,null,"metadata-only","source-checked",null,null,"Current official surface acquired for the Top-100 trust audit; response hash 72c9a7c7fe595f2e6dce27744d8c89471b6bdc806994d04fb79304c0f9018072."],["production::refresh-qwen-3-8-max-api-readme","refresh-qwen-3-8-max-api-readme","identity|specification|availability|pricing|verification","Alibaba Cloud checked metadata source","Alibaba Cloud","https://raw.githubusercontent.com/AlibabaCloud-Official/Qwen3.8-max/main/README.md","official-docs","official-docs","source-checked","identity|specification|availability|pricing|verification",null,null,"2026-08-20",null,"9c47e9bd116375b22b109a4692c332778cf637fcb16bbdb984c5a5a0c6e748b0","Alibaba Cloud source terms","Alibaba Cloud (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Manual metadata review using qwen-3-8-max-api-readme-reviewed-html@2.0.0; no capability evidence was admitted."],["production::refresh-epoch-all-models","refresh-epoch-all-models","identity|specification|discovery","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/data/all_ai_models.csv","independent-registry","independent-registry","source-checked","identity|specification|discovery",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter epoch-model-csv-v2@2.0.0; role historical."],["production::refresh-epoch-frontier-models","refresh-epoch-frontier-models","identity|specification|discovery","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/data/frontier_ai_models.csv","independent-registry","independent-registry","source-checked","identity|specification|discovery",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter epoch-model-csv-v2@2.0.0; role corroboration."],["production::refresh-epoch-large-scale-models","refresh-epoch-large-scale-models","identity|specification|discovery","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/data/large_scale_ai_models.csv","independent-registry","independent-registry","source-checked","identity|specification|discovery",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter epoch-model-csv-v2@2.0.0; role historical."],["production::refresh-epoch-model-archive","refresh-epoch-model-archive","identity|specification|discovery","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/data/ai_models.zip","independent-registry","independent-registry","source-checked","identity|specification|discovery",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter epoch-model-zip-v2@2.0.0; role historical."],["production::refresh-epoch-notable-models","refresh-epoch-notable-models","identity|specification|discovery","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/data/notable_ai_models.csv","independent-registry","independent-registry","source-checked","identity|specification|discovery",null,null,"2026-08-07",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter epoch-model-csv-v2@2.0.0; role corroboration."],["production::refresh-moonshot-platform-docs","refresh-moonshot-platform-docs","identity|specification|pricing","Moonshot AI permanent refresh source","Moonshot AI","https://platform.kimi.ai/docs/overview","official-docs","official-docs","source-checked","identity|specification|pricing",null,null,"2026-08-07",null,null,"Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter moonshot-platform-docs-reviewed-html@2.0.0; role release-triggered."],["production::refresh-models-dev-api","refresh-models-dev-api","identity|specification|pricing|discovery","models.dev permanent refresh source","models.dev","https://models.dev/api.json","independent-registry","independent-registry","source-checked","identity|specification|pricing|discovery",null,null,"2026-08-07",null,null,"models.dev source terms","models.dev (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter models-dev-v2@2.0.0; role corroboration."],["production::refresh-models-dev-catalogue","refresh-models-dev-catalogue","identity|specification|pricing|discovery","models.dev permanent refresh source","models.dev","https://models.dev/catalog.json","independent-registry","independent-registry","source-checked","identity|specification|pricing|discovery",null,null,"2026-08-07",null,null,"models.dev source terms","models.dev (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter models-dev-v2@2.0.0; role corroboration."],["production::refresh-models-dev-models","refresh-models-dev-models","identity|specification|pricing|discovery","models.dev permanent refresh source","models.dev","https://models.dev/models.json","independent-registry","independent-registry","source-checked","identity|specification|pricing|discovery",null,null,"2026-08-07",null,null,"models.dev source terms","models.dev (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter models-dev-v2@2.0.0; role corroboration."],["production::tencent-hy4-preview-repository-2026-08-27","tencent-hy4-preview-repository-2026-08-27","identity|weights|licence|availability","Hy4 Preview official repository","Tencent Hy Team","https://github.com/Tencent-Hunyuan/Hy4-preview","official-repository","official-repository","source-checked","identity|weights|licence|availability","2026-08-27",null,"2026-08-30",null,"80d573485c60986d535240cc393f2be3ad06e14cf889dab374bf83c90d1e5a5d","Apache-2.0",null,"metadata-only","source-checked",null,null,"Tencent-owned public source repository for the Hy4 Preview release."],["arena::image_edit::multi_image_edit::7fa9789cb64d69697be3d2c6b51c9e913e0c31cf2866c7f0aad5a53c1877a39c","7fa9789cb64d69697be3d2c6b51c9e913e0c31cf2866c7f0aad5a53c1877a39c","image-editing","Arena image-editing multi_image_edit leaderboard snapshot","Arena Intelligence","https://arena.ai/leaderboard/image-edit/multi-image-edit/","live-owner-page","official-benchmark","verified-primary-owner-page","ranking","2026-08-25",null,"2026-08-30","7fa9789cb64d69697be3d2c6b51c9e913e0c31cf2866c7f0aad5a53c1877a39c","7fa9789cb64d69697be3d2c6b51c9e913e0c31cf2866c7f0aad5a53c1877a39c",null,"Arena Intelligence (source-native ranking evidence).","metadata-only","verified-primary-owner-page",null,null,null],["arena::image_edit::overall::0d2cd1b2002ab469590e5938cd363cbdbb78b84d56fb48d88b3f1b5d248d08a8","0d2cd1b2002ab469590e5938cd363cbdbb78b84d56fb48d88b3f1b5d248d08a8","image-editing","Arena image-editing overall leaderboard snapshot","Arena Intelligence","https://arena.ai/leaderboard/image-edit/","live-owner-page","official-benchmark","verified-primary-owner-page","ranking","2026-08-25",null,"2026-08-30","0d2cd1b2002ab469590e5938cd363cbdbb78b84d56fb48d88b3f1b5d248d08a8","0d2cd1b2002ab469590e5938cd363cbdbb78b84d56fb48d88b3f1b5d248d08a8",null,"Arena Intelligence (source-native ranking evidence).","metadata-only","verified-primary-owner-page",null,null,null],["arena::image_to_video::overall::51d09b2e834b9d94fe15308531b8b039446fb33a","51d09b2e834b9d94fe15308531b8b039446fb33a","image-to-video","Arena image-to-video overall leaderboard snapshot","lmarena-ai/leaderboard-dataset","https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/51d09b2e834b9d94fe15308531b8b039446fb33a/image_to_video/latest-00000-of-00001.parquet","immutable-parquet","official-benchmark","verified-primary","ranking","2026-08-27",null,"2026-08-30","51d09b2e834b9d94fe15308531b8b039446fb33a",null,null,"lmarena-ai/leaderboard-dataset (source-native ranking evidence).","metadata-only","verified-primary",null,null,null],["production::artificial-analysis-fable-5-1-2026-09-01","artificial-analysis-fable-5-1-2026-09-01","independent evaluation availability|effort variants|Intelligence Index","Artificial Analysis changelog — Claude Fable 5.1","Artificial Analysis","https://artificialanalysis.ai/changelog","independent-lab","independent-lab","source-checked","independent evaluation availability|effort variants|Intelligence Index","2026-09-01",null,"2026-09-01",null,null,null,null,"metadata-only","source-checked",null,null,"Same-day changelog reports independent evaluations for low, medium, high, xhigh and max effort. Only composite Intelligence Index values were visible in the bounded check, so no component benchmark rows are inferred or admitted."],["production::minimax-m3-pricing","minimax-m3-pricing","input price|output price|cache-read price|long-context tier","MiniMax pay-as-you-go pricing","MiniMax","https://platform.minimax.io/subscribe/token-plan?tab=api-enterprise","official-docs","official-docs","source-checked","input price|output price|cache-read price|long-context tier",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::google-pricing-2026-07-21","google-pricing-2026-07-21","input price|output price|cached input price|batch rates","Gemini Developer API pricing (July 2026)","Google","https://ai.google.dev/gemini-api/docs/pricing","official-docs","official-docs","source-checked","input price|output price|cached input price|batch rates","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::anthropic-pricing-2026-07-24","anthropic-pricing-2026-07-24","input price|output price|cached input|fast mode rates","Claude API pricing (Opus 5 admission check)","Anthropic","https://platform.claude.com/docs/en/about-claude/pricing","official-docs","official-docs","source-checked","input price|output price|cached input|fast mode rates",null,null,"2026-07-24",null,null,null,null,null,"source-checked",null,null,null],["production::alibaba-qwen37-plus-pricing-2026-07-27","alibaba-qwen37-plus-pricing-2026-07-27","input price|output price|tiered context pricing|batch discount","Alibaba Cloud Model Studio Qwen3.7 Plus pricing","Alibaba Cloud","https://help.aliyun.com/en/model-studio/model-pricing","official-docs","official-docs","source-checked","input price|output price|tiered context pricing|batch discount",null,null,"2026-07-27",null,null,null,null,null,"source-checked",null,null,"Provider list rates used for the <=256K China deployment tier. Longer-context and promotional rates remain in the pricing note."],["production::anthropic-fable-5-1-pricing-2026-09-01","anthropic-fable-5-1-pricing-2026-09-01","input pricing|output pricing|cache pricing|batch pricing","Claude pricing","Anthropic","https://platform.claude.com/docs/en/about-claude/pricing","official-docs","official-docs","source-checked","input pricing|output pricing|cache pricing|batch pricing","2026-09-01",null,"2026-09-01",null,null,null,null,"metadata-only","source-checked",null,null,"Official pricing table preserves Fable 5.1 and Fable 5 separately, including the cache-read decrease from $1 to $0.25/MTok."],["production::qwencloud-qwen-3-8-max-2026-08-05","qwencloud-qwen-3-8-max-2026-08-05","input token price|output token price|context window|maximum output|API availability","Qwen3.8-Max model details and API pricing","QwenCloud","https://www.qwencloud.com/models/qwen3.8-max","official-docs","official-docs","source-checked","input token price|output token price|context window|maximum output|API availability",null,null,"2026-08-05",null,null,null,null,null,"source-checked",null,null,"Official model catalogue lists $2 input and $6 output per million tokens, 1M context, and 131.1K maximum output. No cached-input price is displayed."],["production::aa-models-leaderboard","aa-models-leaderboard","intelligence index|benchmark metrics|pricing|speed","Artificial Analysis Models Leaderboard","Artificial Analysis","https://artificialanalysis.ai/leaderboards/models","independent-lab","independent-lab","source-checked","intelligence index|benchmark metrics|pricing|speed","2026-07-15",null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gemini-3-5-flash-lite","aa-gemini-3-5-flash-lite","intelligence index|evaluation suite|output speed","Gemini 3.5 Flash-Lite (Artificial Analysis)","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-5-flash-lite","independent-lab","independent-lab","source-checked","intelligence index|evaluation suite|output speed",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gemini-3-6-flash","aa-gemini-3-6-flash","intelligence index|output speed|latency|pricing|evaluation suite","Gemini 3.6 Flash (Artificial Analysis)","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-6-flash","independent-lab","independent-lab","source-checked","intelligence index|output speed|latency|pricing|evaluation suite",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-hy3","aa-model-hy3","intelligence index|output speed|time to first token|context window|pricing","Hy3 analysis on Artificial Analysis","Artificial Analysis","https://artificialanalysis.ai/models/hy3","independent-lab","independent-lab","source-checked","intelligence index|output speed|time to first token|context window|pricing",null,null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::aa-itbench","aa-itbench","ITBench SRE score","ITBench-AA Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/itbench-aa","independent-lab","independent-lab","source-checked","ITBench SRE score","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::refresh-anthropic-deprecations","refresh-anthropic-deprecations","lifecycle","Anthropic permanent refresh source","Anthropic","https://platform.claude.com/docs/en/about-claude/model-deprecations","official-docs","official-docs","source-checked","lifecycle",null,null,"2026-08-08",null,null,"Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter anthropic-lifecycle-v2@2.1.0; role release-triggered."],["production::refresh-google-gemini-deprecations","refresh-google-gemini-deprecations","lifecycle","Google permanent refresh source","Google","https://ai.google.dev/gemini-api/docs/deprecations","official-docs","official-docs","source-checked","lifecycle",null,null,"2026-08-08",null,null,"Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter google-lifecycle-v2@2.1.0; role release-triggered."],["production::llm-stats-livebench","llm-stats-livebench","LiveBench score","LiveBench scores via LLM Stats","LLM Stats","https://llm-stats.com/benchmarks/livebench","independent-lab","independent-lab","source-checked","LiveBench score","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::vending-bench-official","vending-bench-official","long-horizon agent economic simulation","Vending-Bench evaluation","Andon Labs","https://andonlabs.com/evals/vending-bench","official-leaderboard","official-leaderboard","source-checked","long-horizon agent economic simulation",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-math-500","aa-math-500","MATH-500 accuracy","MATH-500 Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/math-500","independent-lab","independent-lab","source-checked","MATH-500 accuracy","2026-07-15",null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::artificial-analysis-methodology","artificial-analysis-methodology","measurement methodology","Artificial Analysis methodology","Artificial Analysis","https://artificialanalysis.ai/methodology","independent-lab","independent-lab","source-checked","measurement methodology",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["media::refresh-aa-image-editing-api-2026-08-07","refresh-aa-image-editing-api-2026-08-07","media","Artificial Analysis aa-image-editing-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-editing/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"92dd575c762f8186b6e2a08214dad0070b5612da8992807f07a22869d4dfe529",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-image-editing-api-2026-08-08","refresh-aa-image-editing-api-2026-08-08","media","Artificial Analysis aa-image-editing-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-editing/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"92dd575c762f8186b6e2a08214dad0070b5612da8992807f07a22869d4dfe529",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-image-editing-api-2026-08-14","refresh-aa-image-editing-api-2026-08-14","media","Artificial Analysis aa-image-editing-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-editing/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-14","2026-08-14",null,"a5d4fec74ce98a6c4ae2d6fc2f73edb81639033882a2b10a8b99e564b8859db5",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-image-to-video-api-2026-08-07","refresh-aa-image-to-video-api-2026-08-07","media","Artificial Analysis aa-image-to-video-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-to-video/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"f49827216a56c48280c0d1c4628f1bfc677061cb89175f9d55d2d02b0573de44",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-image-to-video-api-2026-08-08","refresh-aa-image-to-video-api-2026-08-08","media","Artificial Analysis aa-image-to-video-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-to-video/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"f49827216a56c48280c0d1c4628f1bfc677061cb89175f9d55d2d02b0573de44",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-image-to-video-api-2026-08-14","refresh-aa-image-to-video-api-2026-08-14","media","Artificial Analysis aa-image-to-video-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-to-video/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-14","2026-08-14",null,"01c8238f19a26b798d2ff3f0e0c3c9fd153bd690109055013cce7245f49de532",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-image-to-video-audio-api-2026-08-07","refresh-aa-image-to-video-audio-api-2026-08-07","media","Artificial Analysis aa-image-to-video-audio-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-to-video-audio/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"515633113f55e29766209eed6799c3ea3195d9836b26789483f79ef57d0bb606",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-image-to-video-audio-api-2026-08-08","refresh-aa-image-to-video-audio-api-2026-08-08","media","Artificial Analysis aa-image-to-video-audio-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-to-video-audio/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"515633113f55e29766209eed6799c3ea3195d9836b26789483f79ef57d0bb606",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-image-to-video-audio-api-2026-08-14","refresh-aa-image-to-video-audio-api-2026-08-14","media","Artificial Analysis aa-image-to-video-audio-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/image-to-video-audio/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-14","2026-08-14",null,"ca9faf2806a343802dc031cf05320d286001fb8ebe5c929b8fce179b08f8a9b5",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-speech-to-speech-api-2026-08-07","refresh-aa-speech-to-speech-api-2026-08-07","media","Artificial Analysis aa-speech-to-speech-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/speech-to-speech/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"c9340f08013d7d18b37d79a2525b474c66d82f26c7273e69c37ed7e50b2e73a1",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-speech-to-speech-api-2026-08-08","refresh-aa-speech-to-speech-api-2026-08-08","media","Artificial Analysis aa-speech-to-speech-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/speech-to-speech/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"c9340f08013d7d18b37d79a2525b474c66d82f26c7273e69c37ed7e50b2e73a1",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-speech-to-text-api-2026-08-07","refresh-aa-speech-to-text-api-2026-08-07","media","Artificial Analysis aa-speech-to-text-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/speech-to-text/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"8d95326e039cedb1ddf3425601a793677102477c311f0dc98922d8efe13beec1",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-speech-to-text-api-2026-08-08","refresh-aa-speech-to-text-api-2026-08-08","media","Artificial Analysis aa-speech-to-text-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/speech-to-text/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"8d95326e039cedb1ddf3425601a793677102477c311f0dc98922d8efe13beec1",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-image-api-2026-08-07","refresh-aa-text-to-image-api-2026-08-07","media","Artificial Analysis aa-text-to-image-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-image/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"a10785da3954a486074c5fc49a71cc260597a0cd03ebf055368b3bbd2a891594",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-image-api-2026-08-08","refresh-aa-text-to-image-api-2026-08-08","media","Artificial Analysis aa-text-to-image-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-image/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"a10785da3954a486074c5fc49a71cc260597a0cd03ebf055368b3bbd2a891594",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-image-api-2026-08-13","refresh-aa-text-to-image-api-2026-08-13","media","Artificial Analysis aa-text-to-image-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-image/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-13","2026-08-13",null,"36c5909c2b81125c9da4501abce0ed8ab2eee9df20f792423462e8dda356c9e8",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-image-api-2026-08-14","refresh-aa-text-to-image-api-2026-08-14","media","Artificial Analysis aa-text-to-image-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-image/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-14","2026-08-14",null,"36c5909c2b81125c9da4501abce0ed8ab2eee9df20f792423462e8dda356c9e8",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-speech-api-2026-08-07","refresh-aa-text-to-speech-api-2026-08-07","media","Artificial Analysis aa-text-to-speech-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-speech/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"d63b83a98ea0ff0d4375c6ba57db022b30ba77c2afc114ba68d46527589a124f",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-speech-api-2026-08-08","refresh-aa-text-to-speech-api-2026-08-08","media","Artificial Analysis aa-text-to-speech-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-speech/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"d63b83a98ea0ff0d4375c6ba57db022b30ba77c2afc114ba68d46527589a124f",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-video-api-2026-08-07","refresh-aa-text-to-video-api-2026-08-07","media","Artificial Analysis aa-text-to-video-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-video/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"09613dd4ebe2c24727ec242b9baf33f7cea4e61d38b94ebf8365c146d3f84b60",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-video-api-2026-08-08","refresh-aa-text-to-video-api-2026-08-08","media","Artificial Analysis aa-text-to-video-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-video/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"42691816b9306a6e61c3bf171cddceef4db4d00b09d922362341d7a881042e66",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-video-api-2026-08-14","refresh-aa-text-to-video-api-2026-08-14","media","Artificial Analysis aa-text-to-video-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-video/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-14","2026-08-14",null,"b43ed947ce30f8e6c53f759e6d1a792355fc26bf1ce64968190c9e0f05b88494",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-video-audio-api-2026-08-07","refresh-aa-text-to-video-audio-api-2026-08-07","media","Artificial Analysis aa-text-to-video-audio-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-video-audio/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-07","2026-08-07",null,"8a41eb68b3ee363a6ad3c8adaf0d2e758f88814f4ce74baee41ce17369b1178a",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-video-audio-api-2026-08-08","refresh-aa-text-to-video-audio-api-2026-08-08","media","Artificial Analysis aa-text-to-video-audio-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-video-audio/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-08","2026-08-08",null,"8a41eb68b3ee363a6ad3c8adaf0d2e758f88814f4ce74baee41ce17369b1178a",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::refresh-aa-text-to-video-audio-api-2026-08-14","refresh-aa-text-to-video-audio-api-2026-08-14","media","Artificial Analysis aa-text-to-video-audio-api checked API snapshot",null,"https://artificialanalysis.ai/api/v2/media/text-to-video-audio/models/free","media-evidence",null,"verified-primary","ranking",null,"2026-08-14","2026-08-14",null,"59033cf633b375e47f27f661daeee689d13e16fbed10e80fb4ee970eead73420",null,"Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.",null,"verified-primary",null,null,null],["media::aa-api-docs-2026-07-30","aa-api-docs-2026-07-30","media","Artificial Analysis api docs",null,"https://artificialanalysis.ai/data-api/docs","media-evidence",null,"verified-primary","methodology",null,"2026-07-30","2026-07-30",null,"47e76549d0211db2dc15ff54ffd538a93fef4319f72f25730ce5eebf8fbe80ca",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-primary",null,null,null],["media::aa-user-capture-grok-voice-think-fast-2-2026-07-30","aa-user-capture-grok-voice-think-fast-2-2026-07-30","media","Artificial Analysis Grok Voice Think Fast comparison capture supplied by the user",null,"https://artificialanalysis.ai/speech-to-speech","media-evidence",null,"user-supplied-primary-capture","ranking",null,"2026-07-30","2026-07-30",null,"a4539897c98d5720fa0457f58f9152124aeb0147e46b98d6b46e64c6d91bfbe9",null,"Artificial Analysis comparison capture supplied by the user. The supplied Artificial Analysis comparison capture reports BBA at 97.2%. The public table retrieved on 2026-07-30 reports 97.0%; both sources remain recorded rather than silently overwriting the discrepancy.",null,"user-supplied-primary-capture",null,null,null],["media::aa-image-methodology-2026-07-30","aa-image-methodology-2026-07-30","media","Artificial Analysis image methodology",null,"https://artificialanalysis.ai/image/methodology","media-evidence",null,"verified-primary","methodology",null,"2026-07-30","2026-07-30",null,"28f525a0bbfb7cbf746202d433fddc63e612c50647decd2f866cd92c82345e35",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-primary",null,null,null],["media::aa-image-providers-2026-07-30","aa-image-providers-2026-07-30","media","Artificial Analysis image providers",null,"https://artificialanalysis.ai/image/providers","media-evidence",null,"verified-primary","endpoint",null,"2026-07-30","2026-07-30",null,"1a311e7c25be44a968c9d9ed301b9c2f7e6f8f59497d299bdbec9e4d37663aa4",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-primary",null,null,null],["media::aa-image-ranking-2026-07-30","aa-image-ranking-2026-07-30","media","Artificial Analysis image-editing public leaderboard",null,"https://artificialanalysis.ai/image/leaderboard/editing/","media-evidence",null,"verified-public-primary","ranking",null,"2026-07-30","2026-07-30",null,"8b9ed37b447d6db471b0e966b71b7edc162b092f4c62f74f095dfa3438694301",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-public-primary",null,null,null],["media::aa-video-image-to-video-2026-07-30","aa-video-image-to-video-2026-07-30","media","Artificial Analysis image-to-video public leaderboard",null,"https://artificialanalysis.ai/video/leaderboard/image-to-video","media-evidence",null,"verified-public-primary","ranking",null,"2026-07-30","2026-07-30",null,"d51a555e9dd181c38da9115d6017f709f9d8500f82ba6b5f0dc8705534bb849c",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-public-primary",null,null,null],["media::aa-speech-to-speech-2026-07-30","aa-speech-to-speech-2026-07-30","media","Artificial Analysis speech to speech",null,"https://artificialanalysis.ai/speech-to-speech","media-evidence",null,"verified-primary","ranking",null,"2026-07-30","2026-07-30",null,"d2eb340101de75bff1415a6f341fc10100bcffccb619eed05e43eb28f70132c7",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-primary",null,null,null],["media::aa-image-text-to-image-2026-07-30","aa-image-text-to-image-2026-07-30","media","Artificial Analysis text-to-image public leaderboard",null,"https://artificialanalysis.ai/image/leaderboard/text-to-image","media-evidence",null,"verified-public-primary","ranking",null,"2026-07-30","2026-07-30",null,"3d131641b1657e4bda3d7ce04bd10cb333583833c5304fd468c33f7d55120524",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-public-primary",null,null,null],["media::aa-voice-provider-voice-2026-07-30","aa-voice-provider-voice-2026-07-30","media","Artificial Analysis text-to-speech public leaderboard",null,"https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice","media-evidence",null,"verified-public-primary","ranking",null,"2026-07-30","2026-07-30",null,"71688fdb95aa8d5e6362d82eca079ba7d62336888937a48e1c7d31900624193c",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-public-primary",null,null,null],["media::aa-video-text-to-video-2026-07-30","aa-video-text-to-video-2026-07-30","media","Artificial Analysis text-to-video public leaderboard",null,"https://artificialanalysis.ai/video/leaderboard/text-to-video","media-evidence",null,"verified-public-primary","ranking",null,"2026-07-30","2026-07-30",null,"63bcd98e81e9a3d9c6592e4a343b1b73fe5074aad57c46d9591dad1b915b05a9",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-public-primary",null,null,null],["media::aa-video-methodology-2026-07-30","aa-video-methodology-2026-07-30","media","Artificial Analysis video methodology",null,"https://artificialanalysis.ai/video/methodology","media-evidence",null,"verified-primary","methodology",null,"2026-07-30","2026-07-30",null,"ffbe32b546c2d74166ba18324ffcdaa03729f57a7d674f8f9d59e257ef12d812",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-primary",null,null,null],["media::aa-video-providers-2026-07-30","aa-video-providers-2026-07-30","media","Artificial Analysis video providers",null,"https://artificialanalysis.ai/video/providers","media-evidence",null,"verified-primary","endpoint",null,"2026-07-30","2026-07-30",null,"f38611055a2f14cbb9fa981ae756a6f0913bd04555e35d2f51f550cdba152a0c",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-primary",null,null,null],["media::aa-voice-methodology-2026-07-30","aa-voice-methodology-2026-07-30","media","Artificial Analysis voice methodology",null,"https://artificialanalysis.ai/text-to-speech/methodology","media-evidence",null,"verified-primary","methodology",null,"2026-07-30","2026-07-30",null,"a60372a16f17cfe98abb1dfc6abd991c2e8d54d0cb77b42be783336208c74009",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-primary",null,null,null],["media::aa-voice-controlled-voice-2026-07-30","aa-voice-controlled-voice-2026-07-30","media","Artificial Analysis voice-cloning public leaderboard",null,"https://artificialanalysis.ai/text-to-speech/leaderboard/controlled-voice","media-evidence",null,"verified-public-primary","ranking",null,"2026-07-30","2026-07-30",null,"da79cc5a8a814e66dfa94f76457ef38129caaa28bbb0ee54a739a616337c7006",null,"Artificial Analysis (retrieved by LuminaBench; ratings and measurements remain source-native).",null,"verified-public-primary",null,null,null],["media::i2i-bench-cvpr-2026-2026-07-30","i2i-bench-cvpr-2026-2026-07-30","media","I2I-Bench official CVPR 2026 results",null,"https://openaccess.thecvf.com/content/CVPR2026/html/Wang_I2I-Bench_A_Comprehensive_Benchmark_Suite_for_Image-to-Image_Editing_Models_CVPR_2026_paper.html","media-evidence",null,"verified-primary","research-benchmark",null,"2026-07-30","2026-07-30",null,"23468b64796a987fd8c8b53ae43f2397a7aac1274cede83b37d3a08d5469b92e",null,"I2I-Bench, CVPR 2026 (official open-access paper results).",null,"verified-primary",null,null,null],["production::refresh-aa-controlled-voice-leaderboard","refresh-aa-controlled-voice-leaderboard","media|result","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/text-to-speech/leaderboard/controlled-voice","independent-lab","independent-lab","source-checked","media|result",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-controlled-voice-leaderboard-reviewed-html@2.0.0; role manual-review."],["production::refresh-aa-image-editing-leaderboard","refresh-aa-image-editing-leaderboard","media|result","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/image/leaderboard/editing","independent-lab","independent-lab","source-checked","media|result",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-image-editing-leaderboard-reviewed-html@2.0.0; role manual-review."],["production::refresh-aa-image-to-video-leaderboard","refresh-aa-image-to-video-leaderboard","media|result","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/video/leaderboard/image-to-video","independent-lab","independent-lab","source-checked","media|result",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-image-to-video-leaderboard-reviewed-html@2.0.0; role manual-review."],["production::refresh-aa-provider-voice-leaderboard","refresh-aa-provider-voice-leaderboard","media|result","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice","independent-lab","independent-lab","source-checked","media|result",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-provider-voice-leaderboard-reviewed-html@2.0.0; role manual-review."],["production::refresh-aa-text-to-image-leaderboard","refresh-aa-text-to-image-leaderboard","media|result","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/image/leaderboard/text-to-image","independent-lab","independent-lab","source-checked","media|result",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-text-to-image-leaderboard-reviewed-html@2.0.0; role manual-review."],["production::refresh-aa-text-to-video-leaderboard","refresh-aa-text-to-video-leaderboard","media|result","Artificial Analysis permanent refresh source","Artificial Analysis","https://artificialanalysis.ai/video/leaderboard/text-to-video","independent-lab","independent-lab","source-checked","media|result",null,null,"2026-08-07",null,null,"Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter aa-text-to-video-leaderboard-reviewed-html@2.0.0; role manual-review."],["production::benchlm-kimi-k3","benchlm-kimi-k3","mirrored public benchmark rows|pricing|overall score","Kimi K3 Benchmarks, Pricing & Speed (July 2026)","BenchLM","https://benchlm.ai/models/kimi-3","independent-lab","independent-lab","source-checked","mirrored public benchmark rows|pricing|overall score","2026-07-20",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::benchlm-mmlu-pro-2026-07-20","benchlm-mmlu-pro-2026-07-20","MMLU-Pro accuracy","MMLU-Pro Leaderboard & Scores — July 2026","BenchLM","https://benchlm.ai/benchmarks/mmluPro","independent-lab","independent-lab","source-checked","MMLU-Pro accuracy","2026-07-20",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::google-gemini-36-model-card","google-gemini-36-model-card","model description|knowledge cutoff|evaluation methodology link","Gemini 3.6 Flash model card","Google DeepMind","https://deepmind.google/models/model-cards/gemini-3-6-flash/","official-model-card","official-model-card","source-checked","model description|knowledge cutoff|evaluation methodology link","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::xai-grok-4-6-docs-2026-08-12","xai-grok-4-6-docs-2026-08-12","model ID|500,000-token context|modalities|no text output limit|reasoning efforts|tool support|pricing|long-context threshold","Grok 4.6 API documentation","xAI","https://docs.x.ai/developers/grok-4-6","official-docs","official-docs","source-checked","model ID|500,000-token context|modalities|no text output limit|reasoning efforts|tool support|pricing|long-context threshold","2026-08-12",null,"2026-08-12","sha256:c7f14d372589b708d3d96045e8325bdca7195dcb9a809aa61212f6911e7000cb","c7f14d372589b708d3d96045e8325bdca7195dcb9a809aa61212f6911e7000cb","xAI documentation terms","xAI API documentation","metadata-only","source-checked",null,null,"Official documentation and its embedded model catalogue were fetched directly. Standard token prices are $2 input, $0.50 cached input and $6 output per million tokens; prices double above 200,000 input tokens."],["production::anthropic-fable-5-1-model-docs-2026-09-01","anthropic-fable-5-1-model-docs-2026-09-01","model ID|specifications|capabilities|availability|release status","Claude Fable 5.1 model overview","Anthropic","https://platform.claude.com/docs/en/models/fable-5-1/overview","official-docs","official-docs","source-checked","model ID|specifications|capabilities|availability|release status","2026-09-01",null,"2026-09-01",null,null,null,null,"metadata-only","source-checked",null,null,"Official model page identifies the API/cloud model IDs, 1M context, 128K output, adaptive always-on thinking, default high effort, June 2026 cutoff, text and image input, and active latest status."],["production::longcat-2-0-blog-2026-06-30","longcat-2-0-blog-2026-06-30","model identity|1.6T MoE|1M context|open weights|API access","Introducing LongCat-2.0","Meituan LongCat","https://longcat.ai/blog/longcat-2.0","official-docs","official-docs","source-checked","model identity|1.6T MoE|1M context|open weights|API access","2026-06-30",null,"2026-08-15",null,"db4744d48bd7d183c1d0d7dc22983eefd3c9ada3f8db644bdbc5db5cee1c7523",null,null,null,"source-checked",null,null,"Official LongCat-2.0 launch blog. Starred competitor cells are cited from other official reports and are not stored as a 2.1 complete launch table."],["production::upstage-solar-open2-250b-huggingface-2026-08-15","upstage-solar-open2-250b-huggingface-2026-08-15","model identity|architecture|1M context|English and Korean benchmark tables","Solar Open 2 250B model card","Upstage","https://huggingface.co/upstage/Solar-Open2-250B","official-model-card","official-model-card","source-checked","model identity|architecture|1M context|English and Korean benchmark tables",null,null,"2026-08-15",null,"3e38c75c486610d88bac3fee8b1073dc807d9adc031521e04a73d4d0f99a8825",null,null,null,"source-checked",null,null,"Official Upstage card for Solar-Open2-250B. The English table is stored as per-benchmark complete official comparison tables. Korean owner scores are stored only where a registry benchmark already exists."],["production::poolside-laguna-xs-2-1-blog-2026-07-02","poolside-laguna-xs-2-1-blog-2026-07-02","model identity|architecture|pricing|OpenRouter id|SWE-bench Multilingual","Introducing Laguna XS 2.1","Poolside","https://poolside.ai/blog/introducing-laguna-xs-2-1","official-docs","official-docs","source-checked","model identity|architecture|pricing|OpenRouter id|SWE-bench Multilingual","2026-07-02",null,"2026-08-15",null,null,null,null,null,"source-checked",null,null,"Official Poolside launch post. Competitor bar-chart cells are highest-public figures and are not used as a 2.1 launch table. Direct API price is $0.10 / $0.20 / $0.05."],["production::anthropic-fable-mythos-5","anthropic-fable-mythos-5","model identity|availability|context window|maximum output|pricing|reasoning mode","Introducing Claude Fable 5 and Claude Mythos 5","Anthropic","https://platform.claude.com/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5","official-docs","official-docs","source-checked","model identity|availability|context window|maximum output|pricing|reasoning mode","2026-06-09",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::tencent-hy3-hf","tencent-hy3-hf","model identity|context window|architecture|licence|evaluation results","Tencent Hy3 model card on Hugging Face","Tencent Hy Team","https://huggingface.co/tencent/Hy3","official-model-card","official-model-card","source-checked","model identity|context window|architecture|licence|evaluation results","2026-07-06",null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,"Apache 2.0 open-weight MoE; evaluation results section used for provider-attached scores."],["production::poolside-laguna-xs-2-1-huggingface-2026-08-15","poolside-laguna-xs-2-1-huggingface-2026-08-15","model identity|context window|licence|owner benchmark table","Laguna XS 2.1 model card","Poolside","https://huggingface.co/poolside/Laguna-XS-2.1","official-model-card","official-model-card","source-checked","model identity|context window|licence|owner benchmark table","2026-07-02",null,"2026-08-15",null,"68ac16a52152a8bec6f02425d0d23a5c30b4a7521bcfe5bfc370dcc15f654415",null,null,null,"source-checked",null,null,"Official Hugging Face card. Only Laguna XS 2.1 owner scores are admitted; competitor cells are highest-public figures."],["production::openai-gpt-53-codex","openai-gpt-53-codex","model identity|context window|maximum output|pricing|modalities|reasoning mode","GPT-5.3-Codex model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.3-codex","official-docs","official-docs","source-checked","model identity|context window|maximum output|pricing|modalities|reasoning mode",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::openai-gpt-54","openai-gpt-54","model identity|context window|maximum output|pricing|modalities|reasoning mode","GPT-5.4 model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.4","official-docs","official-docs","source-checked","model identity|context window|maximum output|pricing|modalities|reasoning mode","2026-03-05",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::minimax-m3","minimax-m3","model identity|context window|modalities|availability|reasoning mode","MiniMax M3 model page","MiniMax","https://www.minimax.io/models/text/m3","official-model-card","official-model-card","source-checked","model identity|context window|modalities|availability|reasoning mode",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::google-gemini-36-flash-docs","google-gemini-36-flash-docs","model identity|context window|modalities|capabilities","Gemini 3.6 Flash model documentation","Google","https://ai.google.dev/gemini-api/docs/models/gemini-3.6-flash","official-docs","official-docs","source-checked","model identity|context window|modalities|capabilities","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::openai-gpt-55","openai-gpt-55","model identity|context window|pricing","GPT-5.5 model documentation","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.5","official-docs","official-docs","source-checked","model identity|context window|pricing","2026-04-23",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::anthropic-models-2026-07-24","anthropic-models-2026-07-24","model identity|context window|pricing cross-check","Claude models overview (Opus 5 admission check)","Anthropic","https://platform.claude.com/docs/en/about-claude/models/overview","official-docs","official-docs","source-checked","model identity|context window|pricing cross-check",null,null,"2026-07-24",null,null,null,null,null,"source-checked",null,null,null],["production::models-dev-api-2026-07-27","models-dev-api-2026-07-27","model identity|context|maximum output|modalities|tool use|structured output|open-weight status|pricing cross-check","models.dev API registry — 2026-07-27","models.dev","https://models.dev/api.json","independent-registry","independent-registry","source-checked","model identity|context|maximum output|modalities|tool use|structured output|open-weight status|pricing cross-check","2026-07-27",null,"2026-07-27",null,null,null,null,null,"source-checked",null,null,"Exact provider/model-ID matches fill missing metadata only. Existing provider-owned values are never overwritten by this registry."],["production::models-dev-api-2026-08-01","models-dev-api-2026-08-01","model identity|context|maximum output|modalities|tool use|structured output|open-weight status|pricing cross-check","models.dev registry feeds — 2026-08-01","models.dev","https://models.dev/api.json","independent-registry","independent-registry","source-checked","model identity|context|maximum output|modalities|tool use|structured output|open-weight status|pricing cross-check","2026-08-01",null,"2026-08-01",null,null,null,null,null,"source-checked",null,null,"Exact provider/model-ID matches fill missing metadata only. Existing provider-owned values are never overwritten by this registry."],["production::benchlm-public-dataset-2026-07-27","benchlm-public-dataset-2026-07-27","model identity|context|pricing|reference benchmark rows|display-only composite indices","BenchLM public datasets — 2026-07-27","BenchLM","https://benchlm.ai/data/leaderboard.json","independent-lab","independent-lab","source-checked","model identity|context|pricing|reference benchmark rows|display-only composite indices","2026-07-27",null,"2026-07-27",null,null,null,null,null,"source-checked",null,null,"Public JSON datasets used with visible attribution. Composite scores are priors/display references, never direct benchmark rows."],["production::benchlm-public-dataset-2026-08-01","benchlm-public-dataset-2026-08-01","model identity|context|pricing|reference benchmark rows|display-only composite indices","BenchLM public datasets — 2026-08-01","BenchLM","https://benchlm.ai/data/leaderboard.json","independent-lab","independent-lab","source-checked","model identity|context|pricing|reference benchmark rows|display-only composite indices","2026-08-01",null,"2026-08-01",null,null,null,null,null,"source-checked",null,null,"Public JSON datasets used with visible attribution. Composite scores are priors/display references, never direct benchmark rows."],["production::benchlm-public-dataset-2026-07-21","benchlm-public-dataset-2026-07-21","model identity|context|pricing|reference benchmark rows|display-only composite indices","BenchLM public datasets — 21 July 2026","BenchLM","https://benchlm.ai/embed","independent-lab","independent-lab","source-checked","model identity|context|pricing|reference benchmark rows|display-only composite indices","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,"Public JSON/CSV data used with visible attribution. Composite scores never enter the Lumina Power Index."],["production::longcat-2-0-huggingface-2026-08-15","longcat-2-0-huggingface-2026-08-15","model identity|MIT licence|owner benchmark table|thinking control","LongCat-2.0 model card","Meituan LongCat","https://huggingface.co/meituan-longcat/LongCat-2.0","official-model-card","official-model-card","source-checked","model identity|MIT licence|owner benchmark table|thinking control","2026-06-30",null,"2026-08-29",null,"465f906597726afdce4d58afb00e8bde1766e4886c26860becc2d3fd2edbedc9",null,null,"metadata-only","source-checked",null,null,"Official Hugging Face card. Owner scores are admitted. Starred competitor cells are cited from other reports and are not admitted as launch-table cells."],["production::alibaba-qwen38-preview","alibaba-qwen38-preview","model identity|preview availability","Qwen3.8 Max Preview availability (Alibaba Cloud / WAIC announcement coverage)","Alibaba Cloud","https://help.aliyun.com/en/model-studio/token-plan-personal-overview","official-docs","official-docs","source-checked","model identity|preview availability","2026-07-19",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,"No official public benchmark table published at check date; model admitted as identity-only preview."],["production::moonshot-kimi-k3-blog","moonshot-kimi-k3-blog","model identity|pricing|benchmark result table|architecture|context window|modalities","Kimi K3: Open Frontier Intelligence","Moonshot AI","https://www.kimi.com/blog/kimi-k3","official-model-card","official-model-card","source-checked","model identity|pricing|benchmark result table|architecture|context window|modalities","2026-07-16",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::tencent-hy3-research","tencent-hy3-research","model identity|release announcement","Introducing Hy3 research post","Tencent Hy","https://hy.tencent.com/research/hy3","official-docs","official-docs","source-checked","model identity|release announcement","2026-07-06",null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::benchlm-qwen38-max-preview","benchlm-qwen38-max-preview","model identity|release date","Qwen3.8 Max Preview profile (data coming soon)","BenchLM","https://benchlm.ai/models/qwen3-8-max-preview","independent-lab","independent-lab","source-checked","model identity|release date","2026-07-19",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,"BenchLM tracks the preview without sourced benchmark scores yet."],["production::meta-muse-spark-1-2-release-2026-08-05","meta-muse-spark-1-2-release-2026-08-05","model identity|release date|Muse Code availability|Meta Model API availability|official evaluation summary","Introducing Muse Code and Muse Spark 1.2","Meta Superintelligence Labs","https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2","official-model-card","official-model-card","source-checked","model identity|release date|Muse Code availability|Meta Model API availability|official evaluation summary","2026-08-05",null,"2026-08-05",null,null,null,null,null,"source-checked",null,null,"Official release. It does not publish a Muse Spark 1.2 token price, context limit, output limit, or measured output speed."],["production::meta-muse-glimmer-30b-release-2026-08-10","meta-muse-glimmer-30b-release-2026-08-10","model identity|release date|open-weight availability|local deployment|agentic positioning","Introducing Muse Glimmer, an open agentic model","Meta Superintelligence Lab","https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model","official-model-card","official-model-card","source-checked","model identity|release date|open-weight availability|local deployment|agentic positioning","2026-08-10",null,"2026-08-10",null,"30b8637267ab0aedb9b8a571e84a7192935efe0100829c82d8d04d667dbeced1",null,null,null,"source-checked",null,null,"Official release page captured and SHA-256 checked on 2026-08-10."],["production::zai-glm-5-3-blog-2026-08-14","zai-glm-5-3-blog-2026-08-14","model identity|thinking effort|complete comparison table|evaluation footnotes|open-weight timeline","GLM-5.3: Frontier Coding with Emergent Cyber Capabilities","Z.AI","https://z.ai/blog/glm-5.3","official-provider-evaluation","official-provider-evaluation","source-checked","model identity|thinking effort|complete comparison table|evaluation footnotes|open-weight timeline","2026-08-14",null,"2026-08-15",null,"3a61a4f33992406d0140ad7c2cb9983282bc0dbbf958f15e27a4ca62ed6c074c",null,null,null,"source-checked",null,null,"Official Z.AI launch blog captured 2026-08-15. The comparison table is stored as per-benchmark complete official tables. Z.AI Code Bench Max 34.5% is taken from the same post."],["production::refresh-qwen-3-8-27b-huggingface","refresh-qwen-3-8-27b-huggingface","model identity|weight availability|legal licence|repository revision","Qwen3.8-27B official repository metadata","Qwen","https://huggingface.co/api/models/Qwen/Qwen3.8-27B","official-model-card","official-model-card","source-checked","model identity|weight availability|legal licence|repository revision",null,null,"2026-08-22",null,"45cb4ba1e90aeb986fb25df8cbc84ae5741f48843a4d8a066bfdecca34a06f22",null,null,null,"source-checked",null,null,"Official repository API observed at immutable revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0; it exposes public safetensors weights and declares apache-2.0. No price, hosted speed, latency or maximum-output value was inferred."],["production::openai-mrcr","openai-mrcr","MRCRv2","MRCR long-context evaluation","OpenAI","https://huggingface.co/datasets/openai/mrcr","official-docs","official-docs","source-checked","MRCRv2",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gdpval-muse-spark-1-2-2026-08-05","aa-gdpval-muse-spark-1-2-2026-08-05","Muse Spark 1.2 xhigh Elo|80% confidence interval|GDPval-AA v2 normalization methodology","GDPval-AA v2 leaderboard — Muse Spark 1.2","Artificial Analysis","https://artificialanalysis.ai/evaluations/gdpval-aa","independent-lab","independent-lab","source-checked","Muse Spark 1.2 xhigh Elo|80% confidence interval|GDPval-AA v2 normalization methodology",null,null,"2026-08-05",null,null,null,null,null,"source-checked",null,null,"Artificial Analysis reports Muse Spark 1.2 (xhigh) at 1631 Elo with an 80% interval of -25/+18 in August 2026."],["production::musr-source","musr-source","MuSR accuracy","MuSR benchmark","MuSR authors","https://github.com/Zayne-sprague/MuSR","official-docs","official-docs","source-checked","MuSR accuracy",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::ocrbench-v2-source","ocrbench-v2-source","OCRBench v2","OCRBench v2","OCRBench authors","https://github.com/Yuliang-Liu/MultimodalOCR","official-docs","official-docs","source-checked","OCRBench v2",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::officeqa-pro-source","officeqa-pro-source","OfficeQA Pro","OfficeQA Pro","Databricks","https://github.com/databricks/officeqa","official-docs","official-docs","source-checked","OfficeQA Pro",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-omniscience-leaderboard","aa-omniscience-leaderboard","Omniscience index","AA-Omniscience Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/omniscience","independent-lab","independent-lab","source-checked","Omniscience index","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::refresh-benchlm-speed","refresh-benchlm-speed","operational|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/data/speed.json","independent-registry","independent-registry","source-checked","operational|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-corroboration-v2@2.0.0; role corroboration."],["production::aa-claude-4-5-haiku","aa-claude-4-5-haiku","output speed|time to first token","Claude 4.5 Haiku analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-4-5-haiku","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-claude-fable-5","aa-claude-fable-5","output speed|time to first token","Claude Fable 5 (with fallback) analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-fable-5","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-claude-opus-48-max","aa-claude-opus-48-max","output speed|time to first token","Claude Opus 4.8 (Max) analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-4-8","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-claude-sonnet-5","aa-claude-sonnet-5","output speed|time to first token","Claude Sonnet 5 (max) analysis","Artificial Analysis","https://artificialanalysis.ai/models/claude-sonnet-5","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-deepseek-v4-flash","aa-deepseek-v4-flash","output speed|time to first token","DeepSeek V4 Flash (max) analysis","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v4-flash","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-deepseek-v4-pro","aa-deepseek-v4-pro","output speed|time to first token","DeepSeek V4 Pro (max) analysis","Artificial Analysis","https://artificialanalysis.ai/models/deepseek-v4-pro","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gemini-3-1-pro-preview","aa-gemini-3-1-pro-preview","output speed|time to first token","Gemini 3.1 Pro Preview analysis","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-1-pro-preview","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gemini-35-flash-medium","aa-gemini-35-flash-medium","output speed|time to first token","Gemini 3.5 Flash (Medium) analysis","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-5-flash-medium","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-3-codex","aa-gpt-5-3-codex","output speed|time to first token","GPT-5.3 Codex (xhigh) analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-3-codex","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-4","aa-gpt-5-4","output speed|time to first token","GPT-5.4 (xhigh) analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-4","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-55-xhigh","aa-gpt-55-xhigh","output speed|time to first token","GPT-5.5 (xhigh) analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-5/","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-6-luna","aa-gpt-5-6-luna","output speed|time to first token","GPT-5.6 Luna (max) analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-luna","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-6-sol","aa-gpt-5-6-sol","output speed|time to first token","GPT-5.6 Sol (max) analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-sol","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-gpt-5-6-terra","aa-gpt-5-6-terra","output speed|time to first token","GPT-5.6 Terra (max) analysis","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-6-terra","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-grok-4-3","aa-grok-4-3","output speed|time to first token","Grok 4.3 (high) analysis","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-3","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-grok-45-high","aa-grok-45-high","output speed|time to first token","Grok 4.5 (High) analysis","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-5","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-minimax-m3","aa-minimax-m3","output speed|time to first token","MiniMax-M3 analysis","Artificial Analysis","https://artificialanalysis.ai/models/minimax-m3","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-mistral-large-3","aa-mistral-large-3","output speed|time to first token","Mistral Large 3 analysis","Artificial Analysis","https://artificialanalysis.ai/models/mistral-large-3","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::aa-mistral-medium-3-5","aa-mistral-medium-3-5","output speed|time to first token","Mistral Medium 3.5 analysis","Artificial Analysis","https://artificialanalysis.ai/models/mistral-medium-3-5","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-mistral-small-4","aa-mistral-small-4","output speed|time to first token","Mistral Small 4 analysis","Artificial Analysis","https://artificialanalysis.ai/models/mistral-small-4","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-qwen3-7-max","aa-qwen3-7-max","output speed|time to first token","Qwen3.7 Max analysis","Artificial Analysis","https://artificialanalysis.ai/models/qwen3-7-max","independent-lab","independent-lab","source-checked","output speed|time to first token",null,null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::benchlm-leaderboard-2026-07-28","benchlm-leaderboard-2026-07-28","overall composite|category composites|evidence status|methodology version","BenchLM BenchAlign leaderboard snapshot — 2026-07-28","BenchLM","https://benchlm.ai/api/data/leaderboard?mode=bench-align-v5&limit=300","independent-lab","independent-lab","source-checked","overall composite|category composites|evidence status|methodology version","2026-07-28",null,"2026-07-28",null,null,null,null,null,"source-checked",null,null,"Snapshot 2026-07-28-49fa9ece35a44829. Composite values remain display-only and capped priors; they never count as direct benchmark rows."],["production::benchlm-leaderboard","benchlm-leaderboard","overall score|category scores|pricing","BenchLM overall leaderboard snapshot","BenchLM","https://benchlm.ai/","independent-lab","independent-lab","source-checked","overall score|category scores|pricing","2026-07-15",null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,"Used for model registry expansion and category priors."],["production::llm-stats-paperbench","llm-stats-paperbench","PaperBench score","PaperBench scores via LLM Stats","LLM Stats","https://llm-stats.com/benchmarks/paperbench","independent-lab","independent-lab","source-checked","PaperBench score","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aider-polyglot-leaderboard","aider-polyglot-leaderboard","polyglot edit success rates","Aider polyglot coding leaderboard","Aider","https://aider.chat/docs/leaderboards/","official-leaderboard","official-leaderboard","source-checked","polyglot edit success rates",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::posttrain-bench-site","posttrain-bench-site","PostTrainBench scores","PostTrainBench","PostTrainBench","https://posttrainbench.com/","official-leaderboard","official-leaderboard","source-checked","PostTrainBench scores",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::refresh-amazon-bedrock-pricing","refresh-amazon-bedrock-pricing","pricing","Amazon permanent refresh source","Amazon","https://aws.amazon.com/bedrock/pricing/","official-docs","official-docs","source-checked","pricing",null,null,"2026-08-07",null,null,"Amazon source terms","Amazon (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter amazon-bedrock-pricing-reviewed-html@2.0.0; role release-triggered."],["production::refresh-anthropic-pricing","refresh-anthropic-pricing","pricing","Anthropic permanent refresh source","Anthropic","https://platform.claude.com/docs/en/about-claude/pricing","official-docs","official-docs","source-checked","pricing",null,null,"2026-08-07",null,null,"Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter anthropic-pricing-reviewed-html@2.0.0; role release-triggered."],["production::refresh-google-gemini-pricing","refresh-google-gemini-pricing","pricing","Google permanent refresh source","Google","https://ai.google.dev/gemini-api/docs/pricing?hl=en","official-docs","official-docs","source-checked","pricing",null,null,"2026-08-15",null,null,"Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter google-gemini-pricing-reviewed-html@2.0.0; role release-triggered."],["production::refresh-openai-pricing","refresh-openai-pricing","pricing","OpenAI permanent refresh source","OpenAI","https://developers.openai.com/api/docs/pricing","official-docs","official-docs","source-checked","pricing",null,null,"2026-08-07",null,null,"OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter openai-pricing-reviewed-html@2.0.0; role release-triggered."],["production::refresh-xai-pricing","refresh-xai-pricing","pricing","xAI permanent refresh source","xAI","https://docs.x.ai/developers/pricing","official-docs","official-docs","source-checked","pricing",null,null,"2026-08-07",null,null,"xAI source terms","xAI (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter xai-pricing-reviewed-html@2.0.0; role release-triggered."],["production::litellm-model-prices-2026-08-01","litellm-model-prices-2026-08-01","pricing conflict detection|context conflict detection","LiteLLM model pricing registry — 2026-08-01","LiteLLM","https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json","independent-registry","independent-registry","source-checked","pricing conflict detection|context conflict detection","2026-08-01",null,"2026-08-01",null,null,null,null,null,"source-checked",null,null,"Registry is used for conflict detection and discovery only; provider-owned pricing remains authoritative."],["production::refresh-benchlm-api-pricing","refresh-benchlm-api-pricing","pricing|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/api/data/pricing","independent-registry","independent-registry","source-checked","pricing|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-pricing-v2@2.0.0; role automatic."],["production::refresh-benchlm-pricing","refresh-benchlm-pricing","pricing|discovery","BenchLM permanent refresh source","BenchLM","https://benchlm.ai/data/pricing.json","independent-registry","independent-registry","source-checked","pricing|discovery",null,null,"2026-08-07",null,null,"BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter benchlm-corroboration-v2@2.0.0; role corroboration."],["production::aa-model-kimi-k3","aa-model-kimi-k3","pricing|output speed|time to first token|context window|benchmark scores|Intelligence Index","Kimi K3 Intelligence, Performance & Price Analysis","Artificial Analysis","https://artificialanalysis.ai/models/kimi-k3","independent-lab","independent-lab","source-checked","pricing|output speed|time to first token|context window|benchmark scores|Intelligence Index",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-kimi-k2-5","aa-kimi-k2-5","pricing|output speed|time to first token|context window|modalities","Kimi K2.5 analysis","Artificial Analysis","https://artificialanalysis.ai/models/kimi-k2-5","independent-lab","independent-lab","source-checked","pricing|output speed|time to first token|context window|modalities",null,null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::aa-model-muse-spark-1-1","aa-model-muse-spark-1-1","pricing|output speed|time to first token|context window|modalities","Muse Spark 1.1 (xhigh) analysis","Artificial Analysis","https://artificialanalysis.ai/models/muse-spark-1-1","independent-lab","independent-lab","source-checked","pricing|output speed|time to first token|context window|modalities",null,null,"2026-07-16",null,null,null,null,null,"source-checked",null,null,null],["production::refresh-ecb-cny-usd-fx-2026-08-20","refresh-ecb-cny-usd-fx-2026-08-20","pricing|verification","European Central Bank checked metadata source","European Central Bank","https://data-api.ecb.europa.eu/service/data/EXR/D.CNY+USD.EUR.SP00.A?startPeriod=2026-08-20&endPeriod=2026-08-20&format=csvdata","independent-registry","independent-registry","source-checked","pricing|verification",null,null,"2026-08-20",null,"21d508477ca7ab6fe8f3c1efd647cd2fbd825e0c6afc8df95a22f536e8b5949e","European Central Bank source terms","European Central Bank (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Manual metadata review using ecb-reference-fx-v1@2.0.0; no capability evidence was admitted."],["production::longcat-pricing-docs-2026-08-29","longcat-pricing-docs-2026-08-29","pricing|verification","LongCat 2.0 provider-native pricing","LongCat","https://longcat.chat/platform/docs/Pricing/LongCat-2.0.html","official-docs","official-docs","source-checked","pricing|verification",null,null,"2026-08-29",null,"c53c57e04c0e5823f485810068f3cb49f56c367a29e7fff8aa59124ffad4e011",null,null,"metadata-only","source-checked",null,null,"Provider-native permanent base prices are retained. Limited-time discounted prices are not substituted for the base tariff."],["production::qwen-pricing","qwen-pricing","production","Alibaba Cloud Model Studio model pricing","Alibaba Cloud","https://help.aliyun.com/en/model-studio/model-pricing","official-docs","official-docs","source-checked",null,null,null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::amazon-bedrock-models","amazon-bedrock-models","production","Amazon Bedrock models","Amazon","https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","official-docs","official-docs","source-checked",null,null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::anthropic-models","anthropic-models","production","Models overview","Anthropic","https://platform.claude.com/docs/en/about-claude/models/overview","official-docs","official-docs","source-checked",null,null,null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::cohere-models","cohere-models","production","Cohere models","Cohere","https://docs.cohere.com/docs/models","official-docs","official-docs","source-checked",null,null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::deepseek-v4","deepseek-v4","production","DeepSeek V4 Preview Release","DeepSeek","https://api-docs.deepseek.com/news/news260424","official-model-card","official-model-card","source-checked",null,"2026-04-24",null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::deepseek-pricing","deepseek-pricing","production","Models & Pricing","DeepSeek","https://api-docs.deepseek.com/quick_start/pricing","official-docs","official-docs","source-checked",null,null,null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::google-gemini-35-flash","google-gemini-35-flash","production","Gemini 3.5 Flash","Google","https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash","official-model-card","official-model-card","source-checked",null,"2026-06-24",null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::google-models","google-models","production","Models | Gemini API","Google","https://ai.google.dev/gemini-api/docs/models","official-docs","official-docs","source-checked",null,"2026-07-09",null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::inclusionai-models","inclusionai-models","production","InclusionAI models","InclusionAI","https://huggingface.co/inclusionAI","official-docs","official-docs","source-checked",null,null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::mistral-large-3","mistral-large-3","production","Mistral Large 3","Mistral AI","https://docs.mistral.ai/models/model-cards/mistral-large-3-25-12","official-model-card","official-model-card","source-checked",null,null,null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::mistral-medium-35","mistral-medium-35","production","Mistral Medium 3.5","Mistral AI","https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04","official-model-card","official-model-card","source-checked",null,"2026-04-28",null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::mistral-small-4","mistral-small-4","production","Mistral Small 4","Mistral AI","https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03","official-model-card","official-model-card","source-checked",null,"2026-03-16",null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::mistral-overview","mistral-overview","production","Models Overview","Mistral AI","https://docs.mistral.ai/models/overview","official-docs","official-docs","source-checked",null,null,null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::kimi-docs","kimi-docs","production","Best Practices for Prompts","Moonshot AI","https://platform.moonshot.ai/docs/guide/prompt-best-practice","official-docs","official-docs","source-checked",null,null,null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::nvidia-nim","nvidia-nim","production","NVIDIA NIM / Nemotron models","NVIDIA","https://build.nvidia.com/","official-docs","official-docs","source-checked",null,null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::xai-models","xai-models","production","Models","xAI","https://docs.x.ai/developers/models","official-docs","official-docs","source-checked",null,"2026-05-15",null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::xai-pricing","xai-pricing","production","Pricing","xAI","https://docs.x.ai/developers/pricing","official-docs","official-docs","source-checked",null,"2026-07-03",null,"2026-07-14",null,null,null,null,null,"source-checked",null,null,null],["production::program-bench-site","program-bench-site","ProgramBench raw pass rate","ProgramBench official site","ProgramBench","https://www.vals.ai/benchmarks/programbench","official-leaderboard","official-leaderboard","source-checked","ProgramBench raw pass rate",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::refresh-amazon-bedrock-models","refresh-amazon-bedrock-models","provider-surface|model-offering|availability","Amazon permanent refresh source","Amazon","https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html","official-docs","official-docs","source-checked","provider-surface|model-offering|availability",null,null,"2026-08-07",null,null,"Amazon source terms","Amazon (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter amazon-bedrock-models-reviewed-html@2.0.0; role release-triggered."],["production::refresh-nvidia-model-catalogue","refresh-nvidia-model-catalogue","provider-surface|model-offering|availability","NVIDIA permanent refresh source","NVIDIA","https://build.nvidia.com/models","official-docs","official-docs","source-checked","provider-surface|model-offering|availability",null,null,"2026-08-07",null,null,"NVIDIA source terms","NVIDIA (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter nvidia-model-catalogue-reviewed-html@2.0.0; role release-triggered."],["production::refresh-azure-foundry-models","refresh-azure-foundry-models","provider-surface|model-offering|availability|pricing","Microsoft permanent refresh source","Microsoft","https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure","official-docs","official-docs","source-checked","provider-surface|model-offering|availability|pricing",null,null,"2026-08-07",null,null,"Microsoft source terms","Microsoft (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter azure-foundry-models-reviewed-html@2.0.0; role release-triggered."],["production::refresh-google-gemini-3-7-flash-model","refresh-google-gemini-3-7-flash-model","provider-surface|model-offering|identity|configuration|lifecycle|specification|availability|pricing|verification","Google permanent refresh source","Google","https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash","official-docs","official-docs","source-checked","provider-surface|model-offering|identity|configuration|lifecycle|specification|availability|pricing|verification",null,null,"2026-08-15",null,null,"Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter google-gemini-3-7-flash-model-reviewed-html@2.0.0; role release-triggered."],["production::refresh-deepseek-pricing","refresh-deepseek-pricing","provider-surface|model-offering|identity|specification|availability|pricing|verification","DeepSeek permanent refresh source","DeepSeek","https://api-docs.deepseek.com/quick_start/pricing","official-docs","official-docs","source-checked","provider-surface|model-offering|identity|specification|availability|pricing|verification",null,null,"2026-08-30",null,null,"DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter deepseek-pricing-reviewed-html@2.0.0; role release-triggered."],["production::zai-glm-5-3-flash-pricing-2026-08-27","zai-glm-5-3-flash-pricing-2026-08-27","provider-surface|model-offering|pricing|availability","Z.AI official model pricing","Z.AI","https://docs.z.ai/guides/overview/pricing","official-docs","official-docs","source-checked","provider-surface|model-offering|pricing|availability",null,null,"2026-08-27",null,null,null,null,"metadata-only","source-checked",null,null,"Official list pricing for GLM-5.3-Flash is $0.15 input, $0.03 cached input and $0.50 output per million tokens. The page separately documents a time-bounded 50% launch promotion through 2026-09-09 24:00 UTC+8."],["production::refresh-openrouter-models","refresh-openrouter-models","provider|provider-surface|model-offering|pricing|availability|discovery","OpenRouter permanent refresh source","OpenRouter","https://openrouter.ai/api/v1/models?output_modalities=all","independent-registry","independent-registry","source-checked","provider|provider-surface|model-offering|pricing|availability|discovery",null,null,"2026-08-07",null,null,"OpenRouter source terms","OpenRouter (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter openrouter-models-v2@2.0.0; role automatic."],["production::huggingface-text-generation-2026-08-01","huggingface-text-generation-2026-08-01","recent text-generation model discovery|pipeline metadata","Hugging Face text-generation feed — 2026-08-01","Hugging Face","https://huggingface.co/api/models?pipeline_tag=text-generation&sort=lastModified&direction=-1&limit=100","independent-registry","independent-registry","source-checked","recent text-generation model discovery|pipeline metadata","2026-08-01",null,"2026-08-01",null,null,null,null,null,"source-checked",null,null,"The generic recent-model feed is discovery-only. It does not by itself verify a frontier model identity or benchmark result."],["refresh::aider-leaderboard","aider-leaderboard","refresh","Aider · aider-leaderboard","Aider","https://aider.chat/docs/leaderboards/","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"cea6cab3ac65e4d41cce072fcac5540497d757b3a6f72d997b7c3607b44c470e","Aider source terms","Aider (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::qwen-3-8-max-api-readme","qwen-3-8-max-api-readme","refresh","Alibaba Cloud · qwen-3-8-max-api-readme","Alibaba Cloud","https://raw.githubusercontent.com/AlibabaCloud-Official/Qwen3.8-max/main/README.md","reviewed-html","official-provider","complete","identity|specification|availability|pricing|verification",null,"2026-08-20","2026-08-20",null,"9c47e9bd116375b22b109a4692c332778cf637fcb16bbdb984c5a5a0c6e748b0","Alibaba Cloud source terms","Alibaba Cloud (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","reviewed-model-metadata-1.0.0 | Manual review admitted metadata only; ranking and capability evidence are out of scope."],["refresh::amazon-bedrock-models","amazon-bedrock-models","refresh","Amazon · amazon-bedrock-models","Amazon","https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html","reviewed-html","official-provider","complete","provider-surface|model-offering|availability",null,"2026-08-30","2026-08-30",null,"fff481e8213cd89dd12576a489c5b45f748e7e511165379e41581d4a71f31298","Amazon source terms","Amazon (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:1cae0414bec38d4f2a511c2127f81ced56a3ff08ea5614fa29cd33093acd3147; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:bee72767721f1d3d4ee76f91268570796e908cc826e6fa0dba94eaee2aab735f, parser output is 1, and classification is expected-content-change."],["refresh::amazon-bedrock-pricing","amazon-bedrock-pricing","refresh","Amazon · amazon-bedrock-pricing","Amazon","https://aws.amazon.com/bedrock/pricing/","reviewed-html","official-provider","complete","pricing",null,"2026-08-30","2026-08-30",null,"bc3b336f662842e08f521149ecdc1c0b618aff028c5735c664ccb319bfb8fc70","Amazon source terms","Amazon (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:d3478baf6c8214a5940af42a89a0664fa5f641572180c1afd3cb1d4a3301a3ac; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:bff7cfde35a9b2abf0d0717b17c9a87b83f90046ca7a45885959b16c24713f36, parser output is 1, and classification is expected-content-change."],["refresh::anthropic-deprecations","anthropic-deprecations","refresh","Anthropic · anthropic-deprecations","Anthropic","https://platform.claude.com/docs/en/about-claude/model-deprecations","reviewed-html","official-provider","complete","lifecycle",null,"2026-08-31","2026-08-31",null,"dd2a0980c9e530d59a9c521fda49e31a4f376c2aabf1661f9271397807b171ec","Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.1.0:e80b1c48f4f31ed7eb3ce91743dbb31c9e94d0621d6cf245354f8ac1df7f2ff5; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:9e4ccf0c3ecb4f870a3dde457ffc179e000ed68b94470fa800f5827101d7594c, parser output is 19, and classification is expected-content-change."],["refresh::anthropic-models","anthropic-models","refresh","Anthropic · anthropic-models","Anthropic","https://platform.claude.com/docs/en/about-claude/models/overview","reviewed-html","official-provider","complete","identity|configuration|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"84e5073f81d7c28a62a453bb1c53ec7b8931b8c6838e8c81711422ae9587b2a6","Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:30049db126be0e09e5e75b4306867f243a97b2568b370d54b92f60fd80606130; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:4e38ddd3a77b0e8d788001f7466389a6b74c6f90d2cc207eb4855271dd368a3d, parser output is 1, and classification is expected-content-change."],["refresh::anthropic-news","anthropic-news","refresh","Anthropic · anthropic-news","Anthropic","https://www.anthropic.com/news","reviewed-html","official-provider","not-modified","identity|lifecycle",null,"2026-08-31","2026-08-31",null,"7209ddf35d08b8b0ff5eb30c307358eafb620cd3961a5ea1cb13c2aa24b64cc4","Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::anthropic-pricing","anthropic-pricing","refresh","Anthropic · anthropic-pricing","Anthropic","https://platform.claude.com/docs/en/about-claude/pricing","reviewed-html","official-provider","complete","pricing",null,"2026-08-31","2026-08-31",null,"28569b2dbd963cceac8d70561006d0f637e06225706306da9051b08993915360","Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:d1e908ae5a06db83ff1d8d914870c0aa445a61e2e6668834c89c47358aa06b77; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:6185091359ff50cfd52ccf5172dc7cae6e0315798bd6b9c9db0c2ca0868a3c47, parser output is 1, and classification is expected-content-change."],["refresh::anthropic-release-notes","anthropic-release-notes","refresh","Anthropic · anthropic-release-notes","Anthropic","https://platform.claude.com/docs/en/release-notes/overview","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"eaae4af8602ba7d92c91ec0c056e4fbef4dcc52df41b265996fa24f7f42ecef7","Anthropic source terms","Anthropic (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:280da57d56f4608de5cdbc6362c4783967e111e0bc98ab60da9590f2801b279d; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:18ef8c51ad187a9454464c701fac22e132cc616e8b85360165e9c650c0afc416, parser output is 1, and classification is expected-content-change."],["refresh::arc-prize","arc-prize","refresh","ARC Prize · arc-prize","ARC Prize","https://arcprize.org/leaderboard","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"e16bed21ecb18e5c7d1db59729c9b1f14aa70f2211c7c8079aff06ae462a26ae","ARC Prize source terms","ARC Prize (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::arena-owner-dataset","arena-owner-dataset","refresh","Arena · arena-owner-dataset","Arena","https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","huggingface-dataset","official-benchmark","complete","external-identity|external-index|result|media|verification",null,"2026-08-23","2026-08-23",null,"cefbce0b27ec4950c565c2423fe5aa50081f4f0bd8279ee52a00b4d507e06919","Arena source terms","Arena (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0 | The core-models projection excluded generation-media Arena subsets: image_edit, image_to_video. | Fresh shadow parse replayed adapter:2.1.0:3179aa2017a655cf0c48432275ee17562b97be6068d8bc1e409d9ff3ece83160; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:9e424249a71012a29ed3a7d7085812360c754e65fb461c6e25495d576f1e7a03, parser output is 8767, and classification is expected-content-change."],["refresh::aa-controlled-voice-leaderboard","aa-controlled-voice-leaderboard","refresh","Artificial Analysis · aa-controlled-voice-leaderboard","Artificial Analysis","https://artificialanalysis.ai/text-to-speech/leaderboard/controlled-voice","reviewed-html","independent-lab","complete","media|result",null,"2026-08-15","2026-08-15",null,"986681f2e9d44ca2babc3345d342d024e733431227c8d6b2fc7b5f34b601e071","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::aa-image-editing-api","aa-image-editing-api","refresh","Artificial Analysis · aa-image-editing-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/image-editing/models/free","json","independent-lab","complete","identity|pricing|operational|media|verification",null,"2026-08-15","2026-08-15",null,"a5d4fec74ce98a6c4ae2d6fc2f73edb81639033882a2b10a8b99e564b8859db5","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::aa-image-editing-leaderboard","aa-image-editing-leaderboard","refresh","Artificial Analysis · aa-image-editing-leaderboard","Artificial Analysis","https://artificialanalysis.ai/image/leaderboard/editing","reviewed-html","independent-lab","complete","media|result",null,"2026-08-15","2026-08-15",null,"75f249365330d1f9ca2bd5b04a262783733a61c141f27a222dba0ebbcd38ab8a","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::aa-image-providers","aa-image-providers","refresh","Artificial Analysis · aa-image-providers","Artificial Analysis","https://artificialanalysis.ai/image/providers","reviewed-html","independent-lab","complete","availability|pricing|media",null,"2026-08-15","2026-08-15",null,"b3caf03a5b78595541c3583af85d6e1b65b43959b1503a9f868fd68132d3dfeb","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::aa-image-to-video-api","aa-image-to-video-api","refresh","Artificial Analysis · aa-image-to-video-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/image-to-video/models/free","json","independent-lab","complete","identity|pricing|operational|media|verification",null,"2026-08-15","2026-08-15",null,"9c0324f2a5c59ce2b91b3d2b53e66b4cef43cdaf11c5dbf9370b1efbc6aeaca8","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::aa-image-to-video-audio-api","aa-image-to-video-audio-api","refresh","Artificial Analysis · aa-image-to-video-audio-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/image-to-video-audio/models/free","json","independent-lab","complete","identity|pricing|operational|media|verification",null,"2026-08-15","2026-08-15",null,"ca9faf2806a343802dc031cf05320d286001fb8ebe5c929b8fce179b08f8a9b5","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::aa-image-to-video-leaderboard","aa-image-to-video-leaderboard","refresh","Artificial Analysis · aa-image-to-video-leaderboard","Artificial Analysis","https://artificialanalysis.ai/video/leaderboard/image-to-video","reviewed-html","independent-lab","complete","media|result",null,"2026-08-15","2026-08-15",null,"746aa0d8ec754f6f228b5e4e5a8e03f8d590a68154c637b9a3a4bfb25f5e586d","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::aa-language-models","aa-language-models","refresh","Artificial Analysis · aa-language-models","Artificial Analysis","https://artificialanalysis.ai/api/v2/language/models/free","json","independent-lab","complete","identity|external-identity|external-index|result|operational|verification",null,"2026-08-15","2026-08-15",null,"aff8527e2eb44fa660da129c6737f0635065e874e2731e7179641b7d667dc3db","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","blocking","every-refresh","permanent-refresh-2.1.0 | Artificial Analysis identity K-EXAONE 2.0 0803 (18721247-4e56-4cf7-9a9d-c71cc60c0961) has no deterministic same-provider canonical model match. | Artificial Analysis identity Solar Pro 4 (1b64aa81-c223-4b8f-909b-82185a234765) has no deterministic same-provider canonical model match. | Artificial Analysis identity Nemotron 3.5 Lightning (29976311-665a-4b2f-ac72-557c33e0758e) has no deterministic same-provider canonical model match. | Artificial Analysis identity Muse Glimmer (high) (583f98fb-c4b8-4df3-8d40-60ac0ed69882) has no deterministic same-provider canonical model match. | Artificial Analysis identity Solar Open2 250B (7eabd8ca-bf43-4d56-b3df-efd1c4eebfb0) has no deterministic same-provider canonical model match. | Artificial Analysis identity Ling 3.0 Tiny (7eaf926c-5f39-4e58-ae50-c38b5fc630fc) has no deterministic same-provider canonical model match. | Artificial Analysis identity A.X-K2 (8215372b-66ff-457b-855e-e8abeafc9571) has no deterministic same-provider canonical model match. | Artificial Analysis identity Qwen3.8 2.4T A95B (8df710d3-9dae-4498-9b4e-9818238e6f31) has no deterministic same-provider canonical model match. | Artificial Analysis identity Motif 3 (b01eefb1-c9f8-412d-8353-571031a52f23) has no deterministic same-provider canonical model match. | Artificial Analysis identity G9v3-39A5B (c5ccda86-5e84-4b69-9247-6d4287fc3336) has no deterministic same-provider canonical model match."],["refresh::aa-model-leaderboard","aa-model-leaderboard","refresh","Artificial Analysis · aa-model-leaderboard","Artificial Analysis","https://artificialanalysis.ai/leaderboards/models","reviewed-html","independent-lab","complete","identity|result|operational",null,"2026-08-15","2026-08-15",null,"d997596e2c6640d3538889c96a7ea7798d610d6ffb2c3aede5422e771158614f","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::aa-provider-voice-leaderboard","aa-provider-voice-leaderboard","refresh","Artificial Analysis · aa-provider-voice-leaderboard","Artificial Analysis","https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice","reviewed-html","independent-lab","complete","media|result",null,"2026-08-15","2026-08-15",null,"c92d9cd07740764ccee460d52a3a620ea3e2432a3d769725939f7ccc640473de","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::aa-speech-to-speech-api","aa-speech-to-speech-api","refresh","Artificial Analysis · aa-speech-to-speech-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/speech-to-speech/models/free","json","independent-lab","schema-drift","identity|pricing|operational|media|verification",null,"2026-08-08","2026-08-15",null,"e75df8985e283b86a3f8b512b27d733dd4752c506c2f87491f426948de2a5733","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:9233ce810bfef54d4166018d6938c937299a93a97effb2775c2b533456d31e63 to adapter:2.0.0:7b1b9382929a2f8403718735229ec8d61b10bdea990b551b065c500065b61e29."],["refresh::aa-speech-to-text-api","aa-speech-to-text-api","refresh","Artificial Analysis · aa-speech-to-text-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/speech-to-text/models/free","json","independent-lab","complete","identity|pricing|operational|media|verification",null,"2026-08-15","2026-08-15",null,"8d95326e039cedb1ddf3425601a793677102477c311f0dc98922d8efe13beec1","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::aa-text-to-image-api","aa-text-to-image-api","refresh","Artificial Analysis · aa-text-to-image-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/text-to-image/models/free","json","independent-lab","complete","identity|pricing|operational|media|verification",null,"2026-08-15","2026-08-15",null,"36c5909c2b81125c9da4501abce0ed8ab2eee9df20f792423462e8dda356c9e8","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::aa-text-to-image-leaderboard","aa-text-to-image-leaderboard","refresh","Artificial Analysis · aa-text-to-image-leaderboard","Artificial Analysis","https://artificialanalysis.ai/image/leaderboard/text-to-image","reviewed-html","independent-lab","complete","media|result",null,"2026-08-15","2026-08-15",null,"a9219a92ade372a0a3a32febb764bbee7508a4404455afe8c0a63fe0d056f203","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::aa-text-to-speech-api","aa-text-to-speech-api","refresh","Artificial Analysis · aa-text-to-speech-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/text-to-speech/models/free","json","independent-lab","complete","identity|pricing|operational|media|verification",null,"2026-08-15","2026-08-15",null,"67231ff9df4e62516e7516d8955de50f9ede525a2736dd4262bf979f4b1f16a1","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::aa-text-to-video-api","aa-text-to-video-api","refresh","Artificial Analysis · aa-text-to-video-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/text-to-video/models/free","json","independent-lab","complete","identity|pricing|operational|media|verification",null,"2026-08-15","2026-08-15",null,"b43ed947ce30f8e6c53f759e6d1a792355fc26bf1ce64968190c9e0f05b88494","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::aa-text-to-video-audio-api","aa-text-to-video-audio-api","refresh","Artificial Analysis · aa-text-to-video-audio-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/media/text-to-video-audio/models/free","json","independent-lab","complete","identity|pricing|operational|media|verification",null,"2026-08-15","2026-08-15",null,"a69c1cbc5c1ab15a5f5fbc382ec54c7bc01e679bf2bc34825a968380f643d320","Artificial Analysis API terms","Artificial Analysis is the evaluator for its measurements; LuminaBench retains attribution.","restricted","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::aa-text-to-video-leaderboard","aa-text-to-video-leaderboard","refresh","Artificial Analysis · aa-text-to-video-leaderboard","Artificial Analysis","https://artificialanalysis.ai/video/leaderboard/text-to-video","reviewed-html","independent-lab","complete","media|result",null,"2026-08-15","2026-08-15",null,"4c23de719dce973852d1f114814f94f3487bc401ffc131c53af965172d317818","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::aa-video-providers","aa-video-providers","refresh","Artificial Analysis · aa-video-providers","Artificial Analysis","https://artificialanalysis.ai/video/providers","reviewed-html","independent-lab","complete","availability|pricing|media",null,"2026-08-15","2026-08-15",null,"18f4cd5edf8b4ea66fc1d7648a891ea15ee13790cf7487c47b3465fdb28430d1","Artificial Analysis source terms","Artificial Analysis (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::benchlm-api-leaderboard","benchlm-api-leaderboard","refresh","BenchLM · benchlm-api-leaderboard","BenchLM","https://benchlm.ai/api/data/leaderboard","json","aggregator-discovery","complete","external-identity|external-index|discovery",null,"2026-08-15","2026-08-15",null,"849b12deae115bca6c64cab4335086660fdc83f817fa051fb7bc81daba663e4d","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::benchlm-api-pricing","benchlm-api-pricing","refresh","BenchLM · benchlm-api-pricing","BenchLM","https://benchlm.ai/api/data/pricing","json","aggregator-discovery","complete","pricing|discovery",null,"2026-08-15","2026-08-15",null,"f299a78d2e2b3e012c35437394cfed535c3c1055d4824c4300b40ec9f61e4c2a","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::benchlm-benchmarks","benchlm-benchmarks","refresh","BenchLM · benchlm-benchmarks","BenchLM","https://benchlm.ai/data/benchmarks.json","json","aggregator-discovery","schema-drift","benchmark|discovery",null,"2026-08-13","2026-08-15",null,"ecff96c005749bc3c5a63f0628af3ecfc75a3c671c04b82999ed8df103ef0c40","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:c5fa41b7b5aa6f5886702ac8a8eed0825d6c36c5ffe933e439a217e0ecdc9d0f to adapter:2.0.0:953c14b444d6ba695943e1b96601946270799c30dfedf7d87d8e8da3c1ea5a57."],["refresh::benchlm-comparisons","benchlm-comparisons","refresh","BenchLM · benchlm-comparisons","BenchLM","https://benchlm.ai/data/comparisons.json","json","aggregator-discovery","schema-drift","external-index|discovery",null,"2026-08-13","2026-08-15",null,"0b8c6f92ee2efa87949cdf6bd3059bc2f1c9431fa8f4b1a4142a20dcce8632e6","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:0f2850e1cd3bd93525005fd411fef15bec3746693d5b76768423932ca2a7fa41 to adapter:2.0.0:99924120eecf3308764a5847ec11c346b5381f075f169df2addb58541d940d5c."],["refresh::benchlm-leaderboard","benchlm-leaderboard","refresh","BenchLM · benchlm-leaderboard","BenchLM","https://benchlm.ai/data/leaderboard.json","json","aggregator-discovery","schema-drift","external-index|discovery",null,"2026-08-13","2026-08-15",null,"f5875e52aecb77cb8531ee2ae4d1ba7cf24955dc9823217a9542897f3af85333","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:d102e5605141419c7bce27dd13592cbc461ec12b7a01ca88ddf6838152161e10 to adapter:2.0.0:58cf3ef7337ab69b3099c25fe397a4d101e50669c98c42545cf8e35e585d9966."],["refresh::benchlm-models","benchlm-models","refresh","BenchLM · benchlm-models","BenchLM","https://benchlm.ai/data/models.json","json","aggregator-discovery","complete","external-identity|specification|discovery",null,"2026-08-15","2026-08-15",null,"284927cc37d107a460d98877f24b0fdb2ff0c1baf9fa92a4746c3cc7d5d9ff75","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::benchlm-pricing","benchlm-pricing","refresh","BenchLM · benchlm-pricing","BenchLM","https://benchlm.ai/data/pricing.json","json","aggregator-discovery","schema-drift","pricing|discovery",null,"2026-08-13","2026-08-15",null,"04a26d5e1e7351d64d2c38b70e12c628b3ada4df16189fee6af306196d7ec36a","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:5813d16c8348d49b8b0ad65e41cbcbdca842cfce3886e79395c067d3b62a41fc to adapter:2.0.0:b774d9e080c5170e29ff9f0fda5feb0aa82d590ce8b022decf4cf490ccfbb731."],["refresh::benchlm-speed","benchlm-speed","refresh","BenchLM · benchlm-speed","BenchLM","https://benchlm.ai/data/speed.json","json","aggregator-discovery","schema-drift","operational|discovery",null,"2026-08-13","2026-08-15",null,"195f8c3233239a77dd3c52f562b6f09fd392674d0f97dd9651cc22a6803123dd","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:bca5abda8546daf0192abc21bc47a659c2c8585e6dc928b73c950c57fb0294e7 to adapter:2.0.0:b4571a4f4147f8d81a9d2d27ac52955066bbbcb203d6c7cffdbb8ba88550020a."],["refresh::benchlm-updates","benchlm-updates","refresh","BenchLM · benchlm-updates","BenchLM","https://benchlm.ai/updates.json","json","aggregator-discovery","schema-drift","identity|lifecycle|discovery",null,"2026-08-13","2026-08-15",null,"8e728f93e503d1b37175b6e2ba31105170a1e08f607e800320bb04ca2f151c16","BenchLM source terms","BenchLM (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:07d872b3e8f8e7452d86a5cebb2b07cc3b5a6f28a84a19cc890cbd463f197629 to adapter:2.0.0:6a647aea17cb8b4ae5469fa0771fd66d58047649656c6da568ee88f99f0bf8af."],["refresh::bfcl","bfcl","refresh","Berkeley Function Calling Leaderboard · bfcl","Berkeley Function Calling Leaderboard","https://gorilla.cs.berkeley.edu/leaderboard.html","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"ef72a8621b6ea1b8aa1d1b7691f73cc3079fd38e86f599c9a38cb626c911fc29","Berkeley Function Calling Leaderboard source terms","Berkeley Function Calling Leaderboard (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::bytedance-seed-github","bytedance-seed-github","refresh","ByteDance Seed · bytedance-seed-github","ByteDance Seed","https://github.com/ByteDance-Seed","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"18dfe08de3d79aa2adc533957298c3684a9afe5691e34dc929953b18bc7add53","ByteDance Seed source terms","ByteDance Seed (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::bytedance-seed-huggingface","bytedance-seed-huggingface","refresh","ByteDance Seed · bytedance-seed-huggingface","ByteDance Seed","https://huggingface.co/ByteDance-Seed","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"d5efdb36a82b0d56b245f02a3d8536767f338c750362679fbae07551b5867016","ByteDance Seed source terms","ByteDance Seed (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::bytedance-seed-site","bytedance-seed-site","refresh","ByteDance Seed · bytedance-seed-site","ByteDance Seed","https://seed.bytedance.com/en/","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-30","2026-08-30",null,"9b1df05a0cf2a38b8040e5dad5e404732ce16e931ecef61713a5a2ce892bd519","ByteDance Seed source terms","ByteDance Seed (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:bc66226d04e027112da61b7f5aca9b237fe87a88c3e019bd61f1846236e80206; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:33face687f0bbb0bdc89c53cbc0a8ce6979a313a22f49635319116b7406bd22b, parser output is 1, and classification is expected-content-change."],["refresh::humanitys-last-exam","humanitys-last-exam","refresh","Center for AI Safety · humanitys-last-exam","Center for AI Safety","https://agi.safe.ai/","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"66ba18398df40126f802a10ef6f59da2ed282d38305d8c1880db8781952c0cc4","Center for AI Safety source terms","Center for AI Safety (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::cohere-blog","cohere-blog","refresh","Cohere · cohere-blog","Cohere","https://cohere.com/blog","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-30","2026-08-30",null,"36d9d79f8660453df54c4ddba6bc3f056c36d42beb3d3f19e08284faa535f18f","Cohere source terms","Cohere (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:956ee5216ec0b67883191a81a91a316447d07eb9bace142b6d189250a281fac5; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:9622b5d57c015f76b854f0e3a307e43b4877ad761eefb83920e5323ec079a481, parser output is 1, and classification is expected-content-change."],["refresh::cohere-changelog","cohere-changelog","refresh","Cohere · cohere-changelog","Cohere","https://docs.cohere.com/v2/changelog","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-23","2026-08-23",null,"ad9ed9783d67eed4ff4701461513f164c676ca0e9c3dbca77d5b45efa7e350f2","Cohere source terms","Cohere (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.1.0:80918a6ee9b3ea5f740e0366e9df037df5b22cbdf6fb1bfb8c0f309a3325e404; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:b87ef109ae750c67b7402fb494688b098a0077e64d305c8715f824f7aa445418, parser output is 6, and classification is expected-content-change."],["refresh::cohere-models","cohere-models","refresh","Cohere · cohere-models","Cohere","https://docs.cohere.com/docs/models","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-23","2026-08-23",null,"db23b3f76ad9da88f2cbfa2b307a07186f6e3ab017e659a3202fef2d06f47637","Cohere source terms","Cohere (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:33a4c51ad309d7bdc68789695f5279da5b9661a39553f9a85f2576a98455928f; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:ea93d62c7079e9bfe0e4ac59044aa3765a796f65ddbfdcc5f69dae249c89bed2, parser output is 1, and classification is expected-content-change."],["refresh::cursor-changelog","cursor-changelog","refresh","Cursor · cursor-changelog","Cursor","https://cursor.com/changelog","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-23","2026-08-23",null,"8d607ed30bf96d2c7064704a6f35df68ac47f384c50030146ab6c059ce4d461c","Cursor source terms","Cursor (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:71308173ee7832662001b11a223a339536d4be6e4fd130c05e5966a078640806; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:ff9e81690ca9d31bb9a59ba8113e567399ab92bbacb1aec4ac43154d5cda4407, parser output is 1, and classification is expected-content-change."],["refresh::deepseek-docs","deepseek-docs","refresh","DeepSeek · deepseek-docs","DeepSeek","https://api-docs.deepseek.com/","reviewed-html","official-provider","complete","identity|lifecycle|specification|pricing",null,"2026-08-30","2026-08-30",null,"fc590e5b2cc856c798d46314828dd790320e177317121a1864ef5428991d12d7","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:8b9ab360e9e486ea46dfbfdc92d064db90d52b4193250c2e014696af9d02512c; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:a4516195bc1a8ca06d7185e6ed6642453966864cd11b27f17fd0ab472ad26d63, parser output is 1, and classification is expected-content-change."],["refresh::deepseek-github","deepseek-github","refresh","DeepSeek · deepseek-github","DeepSeek","https://github.com/deepseek-ai","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"232a6fd8ab647e205c62b965e624bc481ed8e2bd45575435fe5e86b9c4626615","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::deepseek-huggingface","deepseek-huggingface","refresh","DeepSeek · deepseek-huggingface","DeepSeek","https://huggingface.co/deepseek-ai","reviewed-html","official-provider","schema-drift","identity|lifecycle|specification",null,"2026-08-08","2026-08-15",null,"deb3e776a1e62b60143d9360d742ca04f65a412a4b55579bb7068756e9e0f6f2","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:c78565b79b4819864b00316316ebb7a099b27e2e17e070f86a94b5397c309365 to adapter:2.0.0:0d84c57d2275220daa6044f49d715dd398037b706a1db9aa52bde5d9777d9749."],["refresh::deepseek-news","deepseek-news","refresh","DeepSeek · deepseek-news","DeepSeek","https://api-docs.deepseek.com/news","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-30","2026-08-30",null,"fc590e5b2cc856c798d46314828dd790320e177317121a1864ef5428991d12d7","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:8b9ab360e9e486ea46dfbfdc92d064db90d52b4193250c2e014696af9d02512c; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:a4516195bc1a8ca06d7185e6ed6642453966864cd11b27f17fd0ab472ad26d63, parser output is 1, and classification is expected-content-change."],["refresh::deepseek-pricing","deepseek-pricing","refresh","DeepSeek · deepseek-pricing","DeepSeek","https://api-docs.deepseek.com/quick_start/pricing","reviewed-html","official-provider","complete","provider-surface|model-offering|identity|specification|availability|pricing|verification",null,"2026-08-30","2026-08-30",null,"cf2c6fb2dd8a32a538f12a8176175b8809a3516326a5cb30dfe52d63c490a968","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0"],["refresh::deepseek-thinking-mode","deepseek-thinking-mode","refresh","DeepSeek · deepseek-thinking-mode","DeepSeek","https://api-docs.deepseek.com/guides/thinking_mode","reviewed-html","official-provider","complete","configuration|specification|verification",null,"2026-08-30","2026-08-30",null,"f28c43248d26db1f27af0cb082abb00326c957d560d33a21839736edd1d10724","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:a98ebf37e928f84a17fbc419819995737664690e2fc3a80e6ec726c91c687a48; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:e3c8cc6664851064805f1b0e802af24f32b0fa70545aeb4eec4fd514dc6f370a, parser output is 1, and classification is expected-content-change."],["refresh::deepseek-v4-pro-0813-huggingface","deepseek-v4-pro-0813-huggingface","refresh","DeepSeek · deepseek-v4-pro-0813-huggingface","DeepSeek","https://huggingface.co/api/models/deepseek-ai/DeepSeek-V4-Pro-0813","json","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-20","2026-08-20",null,"f4990d033dd8fdb983b656e8b54776e4459348091e0a7c6b494f85fc883c4315","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","reviewed-model-metadata-1.0.0 | Manual review admitted metadata only; ranking and capability evidence are out of scope."],["refresh::deepseek-v4-pro-0813-release","deepseek-v4-pro-0813-release","refresh","DeepSeek · deepseek-v4-pro-0813-release","DeepSeek","https://api-docs.deepseek.com/news/news260813","reviewed-html","official-provider","complete","identity|configuration|alias|lifecycle|availability|benchmark|benchmark-version|result|verification",null,"2026-08-30","2026-08-30",null,"214a2359a897756d9e453ced7b99443913651158b55846abce18e9b5743400dd","DeepSeek source terms","DeepSeek (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:8f6c2dab89feae22de888f422ccdc529bfcc7eef1c27927f858c2d9571c5287d; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:f4e30803de4d58c13e56ab32c6205f5e035737d940d7b99e816824d8558d1207, parser output is 1, and classification is expected-content-change."],["refresh::epoch-all-models","epoch-all-models","refresh","Epoch AI · epoch-all-models","Epoch AI","https://epoch.ai/data/all_ai_models.csv","csv","independent-registry","complete","identity|specification|discovery",null,"2026-08-15","2026-08-15",null,"e121a39f1f73b98270d678de5cabdcfbb561350fc81c97413722e9c6fa87c84a","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0 | Epoch AI is historical; 3574 records/files were retained for discovery or historical provenance and did not overwrite provider-owned facts."],["refresh::epoch-benchmark-archive","epoch-benchmark-archive","refresh","Epoch AI · epoch-benchmark-archive","Epoch AI","https://epoch.ai/data/benchmark_data.zip","zip","independent-registry","schema-drift","benchmark|benchmark-version|result|discovery",null,"2026-08-08","2026-08-15",null,"924d06ad52ae5941ffa3dd1475d8ccaf86cca50eccb360efab52d72899049de8","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:19df44493391bf6810bd1c2f5d7c0980a9566b126d08b859fecc42d50efe26c5 to adapter:2.0.0:f4bafb7fb4f69e6d7e3c19f461e47e682db354d9d5ecb2b25f2c7dac62aa1fd0."],["refresh::epoch-benchmarks","epoch-benchmarks","refresh","Epoch AI · epoch-benchmarks","Epoch AI","https://epoch.ai/data/benchmarks.csv","csv","independent-lab","complete","source|external-identity|configuration|benchmark-version|result|verification",null,"2026-08-18","2026-08-18",null,"e27bb38392eb083f3e932a169edfc171db3a7239344408d046ebe389612e014a","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","allowed","complete","blocking","every-refresh","permanent-refresh-2.1.0"],["refresh::epoch-frontier-models","epoch-frontier-models","refresh","Epoch AI · epoch-frontier-models","Epoch AI","https://epoch.ai/data/frontier_ai_models.csv","csv","independent-registry","complete","identity|specification|discovery",null,"2026-08-15","2026-08-15",null,"f13f20270227cb48b1d990486dbbb41ba1abbb09cd213f35fcedcac63ab9f2a8","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0 | Epoch AI is corroboration; 137 records/files were retained for discovery or historical provenance and did not overwrite provider-owned facts."],["refresh::epoch-large-scale-models","epoch-large-scale-models","refresh","Epoch AI · epoch-large-scale-models","Epoch AI","https://epoch.ai/data/large_scale_ai_models.csv","csv","independent-registry","complete","identity|specification|discovery",null,"2026-08-15","2026-08-15",null,"c4682d8b812d5779d11a0897f23d0d974a7026dc539f76409a440fe9f684b981","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0 | Epoch AI is historical; 523 records/files were retained for discovery or historical provenance and did not overwrite provider-owned facts."],["refresh::epoch-model-archive","epoch-model-archive","refresh","Epoch AI · epoch-model-archive","Epoch AI","https://epoch.ai/data/ai_models.zip","zip","independent-registry","complete","identity|specification|discovery",null,"2026-08-15","2026-08-15",null,"0353ecc828ae92c5caab2d4af641c4846e89abd60244cf27546726b3977ab80e","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0 | Epoch AI is historical; 5 records/files were retained for discovery or historical provenance and did not overwrite provider-owned facts."],["refresh::epoch-notable-models","epoch-notable-models","refresh","Epoch AI · epoch-notable-models","Epoch AI","https://epoch.ai/data/notable_ai_models.csv","csv","independent-registry","complete","identity|specification|discovery",null,"2026-08-15","2026-08-15",null,"024b62a20d1c12969f7d025f9d92c577ea476119ebb5e8d924fc432a4c576d57","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0 | Epoch AI is corroboration; 1046 records/files were retained for discovery or historical provenance and did not overwrite provider-owned facts."],["refresh::frontiermath-v1","frontiermath-v1","refresh","Epoch AI · frontiermath-v1","Epoch AI","https://epoch.ai/frontiermath","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"4a967d0a80e23496af0898979877b10ee40a79ff36432c59a8629acc47f835f6","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::frontiermath-v2-tier-4","frontiermath-v2-tier-4","refresh","Epoch AI · frontiermath-v2-tier-4","Epoch AI","https://epoch.ai/benchmarks/frontiermath-tier-4-v2","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"ef4f1c4cc35673fbead2d4a3bd3cbb6db793b5a73dceaab8e7f12fb801b181e1","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::frontiermath-v2-tiers-1-3","frontiermath-v2-tiers-1-3","refresh","Epoch AI · frontiermath-v2-tiers-1-3","Epoch AI","https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"1daa3df46664729115b0b422cd137ff9f0d194cf42b672e348a5bb3770e5c32c","Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::ecb-cny-usd-fx-2026-08-20","ecb-cny-usd-fx-2026-08-20","refresh","European Central Bank · ecb-cny-usd-fx-2026-08-20","European Central Bank","https://data-api.ecb.europa.eu/service/data/EXR/D.CNY+USD.EUR.SP00.A?startPeriod=2026-08-20&endPeriod=2026-08-20&format=csvdata","csv","independent-registry","complete","pricing|verification",null,"2026-08-20","2026-08-20",null,"21d508477ca7ab6fe8f3c1efd647cd2fbd825e0c6afc8df95a22f536e8b5949e","European Central Bank source terms","European Central Bank (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","reviewed-model-metadata-1.0.0 | Manual review admitted metadata only; ranking and capability evidence are out of scope."],["refresh::gaia-space-legacy","gaia-space-legacy","refresh","GAIA · gaia-space-legacy","GAIA","https://huggingface.co/spaces/gaia-benchmark/leaderboard","reviewed-html","official-benchmark","schema-drift","benchmark|result|discovery",null,"2026-08-08","2026-08-15",null,"07cbdab0bca38081e62ef363dc4f46956af911a108a9036b07ed10215f715805","GAIA source terms","GAIA (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:ac1a21162cb391babcc18b252cd416e2aac496598ff9a40460f8ee4e5578bd58 to adapter:2.0.0:8c48cf49b65b0ad6c52c64b2fe625173f5502748688e763e2bcac2564601c360."],["refresh::google-gemini-3-7-flash-launch","google-gemini-3-7-flash-launch","refresh","Google · google-gemini-3-7-flash-launch","Google","https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/","reviewed-html","official-provider","not-modified","identity|configuration|alias|lifecycle|availability|pricing|benchmark|benchmark-version|result|verification",null,"2026-08-31","2026-08-31",null,"380033d6a0212c619f3b0e509f64e2367f918a80df458beedad63abac3a1b1ac","Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::google-gemini-3-7-flash-model","google-gemini-3-7-flash-model","refresh","Google · google-gemini-3-7-flash-model","Google","https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash","reviewed-html","official-provider","complete","provider-surface|model-offering|identity|configuration|lifecycle|specification|availability|pricing|verification",null,"2026-08-31","2026-08-31",null,"d595197412a68cf4cc7cfaebb66b7f946e7e618bd5cecbe2b04626ff38ade9a1","Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:79bda869556f6fcfb38aa38f2b08e8a545eab0c8e7a5776b90e9821a5d933dbd; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:780e534445211d6a21f38312a1146fb4bb73c2344c1b0e54ea887aefe1dadfaa, parser output is 1, and classification is expected-content-change."],["refresh::google-gemini-changelog","google-gemini-changelog","refresh","Google · google-gemini-changelog","Google","https://ai.google.dev/gemini-api/docs/changelog","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"47ef7afe75e9e31c5142940e2aecff9f8995d13616909fab0646b3506a305ba5","Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:e4c19b15a09cee6161ec4a5a77587696a28b98e80c54543c18dbe77f99860852; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:0412eea9850195e4cde35ff1f1c2a8b3c645a1e8e1fea5d7adeb576662db826c, parser output is 1, and classification is expected-content-change."],["refresh::google-gemini-deprecations","google-gemini-deprecations","refresh","Google · google-gemini-deprecations","Google","https://ai.google.dev/gemini-api/docs/deprecations","reviewed-html","official-provider","complete","lifecycle",null,"2026-08-31","2026-08-31",null,"7580e725d0e5efc4f0dd625dedfd5dc1e936dbf464794c639968a5810a35163b","Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.1.0:1f85bfb5cbfb0db853c553f60e089ad69d67c8fa09fc97e9641abab693b3796e; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:e739e42e49097df0fd2727ef20c46f277b46f9cca4bbaa439812cb383a759e25, parser output is 38, and classification is expected-content-change."],["refresh::google-gemini-models","google-gemini-models","refresh","Google · google-gemini-models","Google","https://ai.google.dev/gemini-api/docs/models","reviewed-html","official-provider","complete","identity|configuration|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"f8d93b541faf3f7165c86ce9d7fdf5cb0f125c0c557a298b615536583ddccceb","Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:71dec030a46e498582d0242f8546b53b0a460f9d21f74e9528e37045dd09f591; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:c3effb10d2d2ce87025e296f90041b32de7b4d891c169953cf4355cf2326eab7, parser output is 1, and classification is expected-content-change."],["refresh::google-gemini-pricing","google-gemini-pricing","refresh","Google · google-gemini-pricing","Google","https://ai.google.dev/gemini-api/docs/pricing?hl=en","reviewed-html","official-provider","complete","pricing",null,"2026-08-31","2026-08-31",null,"e9e2a8f890bba075e77faccc315fae16880f71501170c1ee48821c8ba4ca03ee","Google source terms","Google (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:f8ba83e23b05ac5330bab65321459bcc77d17917a37846d962aabdfe1fc5a772; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:ffc67a41c686c8cdea2063ee81b1f8c655beb1b8738f04d8305e586accff8e12, parser output is 1, and classification is expected-content-change."],["refresh::google-deepmind-blog","google-deepmind-blog","refresh","Google DeepMind · google-deepmind-blog","Google DeepMind","https://deepmind.google/blog/","reviewed-html","official-provider","not-modified","identity|lifecycle",null,"2026-08-31","2026-08-31",null,"3dfbd11ae96d668b1009a727834873b70b873a4d3c974a7a9215e06ee63e4182","Google DeepMind source terms","Google DeepMind (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::google-gemini-3-7-flash-evaluation","google-gemini-3-7-flash-evaluation","refresh","Google DeepMind · google-gemini-3-7-flash-evaluation","Google DeepMind","https://storage.googleapis.com/deepmind-media/gemini/gemini_3-7_flash_model_evaluation.pdf","reviewed-html","official-provider","not-modified","configuration|benchmark|benchmark-version|result|verification",null,"2026-08-31","2026-08-31",null,"7971771c34a03898090f4525883e76c8b5bef0fb0eb5afdfd511df8a8faf9f19","Google DeepMind source terms","Google DeepMind (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | Conditional request returned 304; the prior immutable snapshot remains authoritative and extraction was skipped."],["refresh::huggingface-recent-models","huggingface-recent-models","refresh","Hugging Face · huggingface-recent-models","Hugging Face","https://huggingface.co/api/models?sort=lastModified&direction=-1&limit=100","json","independent-registry","schema-drift","discovery",null,"2026-08-15","2026-08-15",null,"5cdc8b15691a95c7e871e016e31da561262cfe7c04513851b47b41640f30b2fc","Hugging Face source terms","Hugging Face (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:4f86bdd610aec1ef34d66e54f8f9caaec068cc8bd42cf887bac48445675d7789 to adapter:2.0.0:fbcac62b477e93b3445e9671e9148de1097d74102c7135b5294f8d82c862a657."],["refresh::open-asr","open-asr","refresh","Hugging Face · open-asr","Hugging Face","https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","reviewed-html","official-benchmark","schema-drift","benchmark|benchmark-version|result|media",null,"2026-08-08","2026-08-15",null,"91f2b33d12343bc163a01ee226b2b2ac2bcb82552c9a1d5e4fe89515edbd2ca0","Hugging Face source terms","Hugging Face (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:5bf2415dcef1e6e68b90e4bba2164c8f7c1835c8535acc5d88d34ae043810277 to adapter:2.0.0:e4f7ace9d72780aeefe3727e24c255eb7edfa56b220b2ecb3e3e11edf699e700."],["refresh::open-asr-repo","open-asr-repo","refresh","Hugging Face · open-asr-repo","Hugging Face","https://github.com/huggingface/open_asr_leaderboard","github-api","official-benchmark","schema-drift","benchmark|benchmark-version|result|media",null,"2026-08-08","2026-08-15",null,"5f37ef9ca05f8a10ef017da922e7b2fea95e19b6d6009aa8068e6cb7dbdea905","Hugging Face source terms","Hugging Face (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","release-triggered","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:5a22a22addf4e5b63397e345a8243b9edf8f0d3985b5aedbf8224b513c5ab884 to adapter:2.0.0:a3c539f142dff8b0c35b98bbbda958c283d744c4a7bc7cda22778776fae6c986."],["refresh::i2i-bench","i2i-bench","refresh","I2I-Bench · i2i-bench","I2I-Bench","https://github.com/IntMeGroup/I2I-Bench","github-api","official-benchmark","schema-drift","benchmark|benchmark-version|result|media",null,"2026-08-08","2026-08-15",null,"13572c907c7e7354edcbcfd0e106a840ed68299f7b555268491ae8b3e36c1016","I2I-Bench source terms","I2I-Bench (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","release-triggered","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:89c85dd5343211af17a3df7000de78c4f6d6bf59f29e6d3432c544a4b768800f to adapter:2.0.0:699f1e5205d9f00029114bbb71855ccd9f0a25caf8aec25db8a8f017d9f4e14c."],["refresh::inclusionai-huggingface","inclusionai-huggingface","refresh","InclusionAI · inclusionai-huggingface","InclusionAI","https://huggingface.co/inclusionAI","reviewed-html","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-22","2026-08-22",null,"3cf2687ef968a057a78500b4d0c2030d95936634231f0ac56f9e2a77e5792ef7","InclusionAI source terms","InclusionAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::litellm-pricing-context","litellm-pricing-context","refresh","LiteLLM · litellm-pricing-context","LiteLLM","https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json","json","aggregator-discovery","complete","specification|pricing|discovery",null,"2026-08-15","2026-08-15",null,"a99d18043bed0afd66e5e4974efbb71e1324bd07f67ce2760e58493df521fd19","LiteLLM source terms","LiteLLM (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::livebench","livebench","refresh","LiveBench · livebench","LiveBench","https://livebench.ai/","reviewed-html","official-benchmark","complete","source|configuration|benchmark|benchmark-version|result|verification",null,"2026-08-15","2026-08-15",null,"f7cf0c526daff3881f40f61d7fd6584909a5413b116ae1a1f3f347742efa0502","LiveBench source terms","LiveBench (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::livecodebench","livecodebench","refresh","LiveCodeBench · livecodebench","LiveCodeBench","https://livecodebench.github.io/leaderboard.html","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"bc0135e58e08353fadee95924ed40aa61a2a5056a5002a1b51654d2bebf45182","LiveCodeBench source terms","LiveCodeBench (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::livecodebench-repo","livecodebench-repo","refresh","LiveCodeBench · livecodebench-repo","LiveCodeBench","https://github.com/LiveCodeBench/LiveCodeBench","github-api","official-benchmark","schema-drift","benchmark|benchmark-version|result",null,"2026-08-08","2026-08-15",null,"6c68d8d4d9689a95b373f2cefab89c603f54859005cbb91dbd9ced43b6bbaf5e","LiveCodeBench source terms","LiveCodeBench (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","release-triggered","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:8f67ce31b71dc7315d6a376efc25e6b789c79bd526bee64e72bc36169014aae8 to adapter:2.0.0:49338a8f78565309d580eb46665412277b0c36bea878a3844265abdb34b12a06."],["refresh::mathvista","mathvista","refresh","MathVista · mathvista","MathVista","https://mathvista.github.io/","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"ae92439181366330a5364821cfff665f8eac869cff527fc22c324842320650a0","MathVista source terms","MathVista (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::longcat-2-0-model-card","longcat-2-0-model-card","refresh","Meituan LongCat · longcat-2-0-model-card","Meituan LongCat","https://huggingface.co/meituan-longcat/LongCat-2.0","reviewed-html","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-22","2026-08-22",null,"403cdf553fca30739fe2d2a98032d3895a672cde356de73157d0063135d0865b","Meituan LongCat source terms","Meituan LongCat (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::longcat-2-0-release","longcat-2-0-release","refresh","Meituan LongCat · longcat-2-0-release","Meituan LongCat","https://longcat.ai/blog/longcat-2.0","reviewed-html","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-22","2026-08-22",null,"ba34f8b4ea4d653be512b5bc807a296f4042671ea8ecaef4817c3f12c742ee7c","Meituan LongCat source terms","Meituan LongCat (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::meta-ai-blog","meta-ai-blog","refresh","Meta · meta-ai-blog","Meta","https://ai.meta.com/blog/","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-30","2026-08-30",null,"e67b752e2beec2c74214fe75e4e887917a8df84e0d7e13a6f350942c9953b325","Meta source terms","Meta (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:db365c9480c0bfbf0eea97fd323170926378eea89a625c536c65016bd92b4ece; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:9158cda19ff5982f21db43a0a3da2adf291d9afdc8c6652e21325805a4480f27, parser output is 1, and classification is expected-content-change."],["refresh::meta-llama-github","meta-llama-github","refresh","Meta · meta-llama-github","Meta","https://github.com/meta-llama","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"ffa59982903cd4e3e43931bdd3a21aba554de4491aefd003156e475cf6fc3653","Meta source terms","Meta (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::meta-llama-huggingface","meta-llama-huggingface","refresh","Meta · meta-llama-huggingface","Meta","https://huggingface.co/meta-llama","reviewed-html","official-provider","schema-drift","identity|lifecycle|specification",null,"2026-08-08","2026-08-15",null,"37b23266a40bf4c8b3cb2c4888f0bdcdebd76f0d4c0093518d5bf85b2410a367","Meta source terms","Meta (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:c554ca73c1e297c7600af558f6c778860c916c7225b30de269fd04ec8014fba8 to adapter:2.0.0:0b523411d04a27d1db6dbd0c24a85b64d322a50d1a6f88cbdad65a489d539f80."],["refresh::meta-muse-spark-1-2-deepswe-chart","meta-muse-spark-1-2-deepswe-chart","refresh","Meta Superintelligence Labs · meta-muse-spark-1-2-deepswe-chart","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/deepswe-1-1-v1.png","reviewed-html","official-provider","not-modified","source|configuration|benchmark-version|result|verification",null,"2026-08-30","2026-08-30",null,"0ebec95b54d11055c6f082083e09a91d00fbccffaea8254f303d9ef5e9c80d3b","Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::meta-muse-spark-1-2-gdpval-chart","meta-muse-spark-1-2-gdpval-chart","refresh","Meta Superintelligence Labs · meta-muse-spark-1-2-gdpval-chart","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/gdpval-aa-v2-v1.png","reviewed-html","official-provider","not-modified","source|configuration|benchmark-version|result|verification",null,"2026-08-30","2026-08-30",null,"117bbec957da7d5f3595ae1dbe6eed71a06657924800ba08a66e71743ce7a27f","Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::meta-muse-spark-1-2-internal-coding-chart","meta-muse-spark-1-2-internal-coding-chart","refresh","Meta Superintelligence Labs · meta-muse-spark-1-2-internal-coding-chart","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/meta-internal-coding-bench-v1.png","reviewed-html","official-provider","not-modified","source|configuration|benchmark-version|result|verification",null,"2026-08-30","2026-08-30",null,"31a5649e7e552d52f3ae4bc83ce4898e404016325131d685c643b827de87b35f","Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::meta-muse-spark-1-2-mcp-atlas-chart","meta-muse-spark-1-2-mcp-atlas-chart","refresh","Meta Superintelligence Labs · meta-muse-spark-1-2-mcp-atlas-chart","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/mcp-atlas-v1.png","reviewed-html","official-provider","not-modified","source|configuration|benchmark-version|result|verification",null,"2026-08-30","2026-08-30",null,"fbb8f33c75c7081f9e623ba3fb04cff2d78b3973f9c6917f116429dd059602d9","Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::meta-muse-spark-1-2-release","meta-muse-spark-1-2-release","refresh","Meta Superintelligence Labs · meta-muse-spark-1-2-release","Meta Superintelligence Labs","https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2","reviewed-html","official-provider","complete","source|configuration|benchmark-version|result|verification",null,"2026-08-30","2026-08-30",null,"7008b139b8cabaf7ebdcb002f2f80a0f02916ac1f310f8e240baf04555b9fcf3","Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:a1ee8d1ff155e13fb258412eccdd4bb7684c3fb0859490cc96451fa775b2c5c4; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:9f0787bfcf5da9a174e14c4fe48289784941ecfc3e53b2ea5df16cd93b659d5f, parser output is 1, and classification is expected-content-change."],["refresh::meta-muse-spark-1-2-terminal-bench-chart","meta-muse-spark-1-2-terminal-bench-chart","refresh","Meta Superintelligence Labs · meta-muse-spark-1-2-terminal-bench-chart","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/terminal-bench-2-1-v1.png","reviewed-html","official-provider","not-modified","source|configuration|benchmark-version|result|verification",null,"2026-08-30","2026-08-30",null,"86cd698d4da69f0a9272c6a1379ef9f6ac8af6ac72ab9ea0835fcab1f19a7e41","Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::azure-foundry-models","azure-foundry-models","refresh","Microsoft · azure-foundry-models","Microsoft","https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure","reviewed-html","official-provider","complete","provider-surface|model-offering|availability|pricing",null,"2026-08-23","2026-08-23",null,"bf414ace15afd2dc8501841b1c85e20dda40bb309c409aba878ed097b3af2794","Microsoft source terms","Microsoft (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:aee588d4a05aa400710a93e7ceaf6fd7f114397074351e3e23dac1929be729b4; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:3a507454ab9097c2cd2964a81bdc9305e8f9aa2d22b8a493a7a78cf73972a819, parser output is 1, and classification is expected-content-change."],["refresh::azure-foundry-updates","azure-foundry-updates","refresh","Microsoft · azure-foundry-updates","Microsoft","https://learn.microsoft.com/en-us/azure/foundry/whats-new-foundry","reviewed-html","official-provider","complete","identity|lifecycle|availability",null,"2026-08-30","2026-08-30",null,"80a31be291494894c49bbe4a5c46ce3e8ca1a133cb5ea4365c8fee4820fa594a","Microsoft source terms","Microsoft (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:79ad5c45cf35780da22ea94f6830d149ad9365164b272c7d3b0daf2975328c32; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:c729520e6e15ed5cc54c4a85d15eb76de498d4f60c75d388183397025059542b, parser output is 1, and classification is expected-content-change."],["refresh::microsoft-ai-blog","microsoft-ai-blog","refresh","Microsoft · microsoft-ai-blog","Microsoft","https://microsoft.ai/blog/","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-23","2026-08-23",null,"1d915aa671fde7160c0433843468f80e7621822ee880cf6807fabaef36745471","Microsoft source terms","Microsoft (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:8a95ceaa9b6eb935c2f53a9581fe7e29e225f6bbcc3d1241b18e649a0a995fc9; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:a746417d78f3e95062ec7ce07e87735ee31e6e4a073666cbd3c2e43149aa0ea0, parser output is 1, and classification is expected-content-change."],["refresh::microsoft-huggingface","microsoft-huggingface","refresh","Microsoft · microsoft-huggingface","Microsoft","https://huggingface.co/microsoft","reviewed-html","official-provider","schema-drift","identity|lifecycle|specification",null,"2026-08-08","2026-08-15",null,"6f464063f82b1e22dc21ffa44f0b9f5558dc037e3ea88e0c0066e67f6821b19e","Microsoft source terms","Microsoft (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:e70806f6729e845241910cb9cead181c724cc2726bdbb4ae8576a9e86cbfe3b5 to adapter:2.0.0:da50d477ab2411942547c376dd57d7ebcb4b5c7e55d395fd26156d0969240b16."],["refresh::minimax-blog","minimax-blog","refresh","MiniMax · minimax-blog","MiniMax","https://www.minimax.io/blog","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-31","2026-08-31",null,"0cb69c0d5a823127a5ff96408ba028ca9ec4ca40e24fd7bb16e2c64382a09612","MiniMax source terms","MiniMax (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:dca3b18d33e4e34e05a70a0ed7b654143ae0e5ffea0164b5a5c9ab9b581b2473; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:915bb42befa75f4780b7b4cb6f7e24cd17b3f36a7b49128aafe0914781c3d200, parser output is 1, and classification is expected-content-change."],["refresh::minimax-github","minimax-github","refresh","MiniMax · minimax-github","MiniMax","https://github.com/MiniMax-AI","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"61137d4d538d8744136ba46ba5cfb14be5aea6ad9c535df359880a82d5267475","MiniMax source terms","MiniMax (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::minimax-huggingface","minimax-huggingface","refresh","MiniMax · minimax-huggingface","MiniMax","https://huggingface.co/MiniMaxAI","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"8eb82a57d29f131015a99b1e4d56ca1271872ca400ac79235f16455dba8acf5f","MiniMax source terms","MiniMax (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:7dc046d447cf49603c6604140d8382c397d103b4d9076d678110e4d1d562fc7e; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:06e2088e197ad99349a95008bc90c49ea5c31c9f62c766f158042dd13a594eb1, parser output is 1, and classification is expected-content-change."],["refresh::minimax-release-notes","minimax-release-notes","refresh","MiniMax · minimax-release-notes","MiniMax","https://platform.minimax.io/docs/release-notes/models","reviewed-html","official-provider","not-modified","identity|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"b5c2b50189f3e068a07d43f0caeadc754d0129d8893206a9fa07247d8c15d838","MiniMax source terms","MiniMax (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::mistral-changelog","mistral-changelog","refresh","Mistral AI · mistral-changelog","Mistral AI","https://docs.mistral.ai/resources/changelogs","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-23","2026-08-23",null,"13b2df07e0fbf1876d74109e0f9aad1ddfb5d2fb0319f7f5039cb424e909b19a","Mistral AI source terms","Mistral AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:a275259048e97eb4dee0a8071e024e7032a9d017faef077b421acd47790a25d1; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:bee8f31f8b8c93e497afd9907046327578575910edab0c466d0da18dc7c701d6, parser output is 1, and classification is expected-content-change."],["refresh::mistral-models","mistral-models","refresh","Mistral AI · mistral-models","Mistral AI","https://docs.mistral.ai/models/overview","reviewed-html","official-provider","not-modified","identity|lifecycle|specification",null,"2026-08-30","2026-08-30",null,"bac937f44d172b7f1ca3238339044abcaf164835fd5e8ad015cab95e330feffe","Mistral AI source terms","Mistral AI (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | Conditional request returned 304; the prior immutable snapshot remains authoritative and extraction was skipped."],["refresh::mistral-news","mistral-news","refresh","Mistral AI · mistral-news","Mistral AI","https://mistral.ai/news/","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-30","2026-08-30",null,"49e0ace6ea08549f72089c861a0c57b0a582c6e925ab7e532279ba18afe83165","Mistral AI source terms","Mistral AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:c5a5c5cd16395f3d62c222b3f56d8bb95e1b956c75d3350e38dcdf79c9d186f0; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:e5a416d4286c7374208d57220e1a07c0f829f7286c13201c4ae35ef575f64545, parser output is 1, and classification is expected-content-change."],["refresh::mmmu","mmmu","refresh","MMMU · mmmu","MMMU","https://mmmu-benchmark.github.io/","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"4f00a8c6523a84776718e95e4f1a1e0277868e8315505257276718952dd464bd","MMMU source terms","MMMU (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::models-dev-api","models-dev-api","refresh","models.dev · models-dev-api","models.dev","https://models.dev/api.json","json","independent-registry","complete","identity|specification|pricing|discovery",null,"2026-08-15","2026-08-15",null,"b6142cedfe63e6badd497ec70de90610387ae23e0a0a6f860f0844b7b55b6bd9","models.dev source terms","models.dev (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::models-dev-catalogue","models-dev-catalogue","refresh","models.dev · models-dev-catalogue","models.dev","https://models.dev/catalog.json","json","independent-registry","schema-drift","identity|specification|pricing|discovery",null,"2026-08-15","2026-08-15",null,"14304aed00a2ed482bd3b676c029eb81b8d9113f94b5a8d3d38436e044a63142","models.dev source terms","models.dev (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","every-refresh","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:f309633f71c7d8df22b89b895a4e1a7c6d171f60500ee811f2a143f7be7afece to adapter:2.0.0:bd74359b10a609ea96cb65b58fb9a3b60a71b8a3cf74ee90f211ad4cd2f49bd8."],["refresh::models-dev-models","models-dev-models","refresh","models.dev · models-dev-models","models.dev","https://models.dev/models.json","json","independent-registry","complete","identity|specification|pricing|discovery",null,"2026-08-18","2026-08-18",null,"2f85327d54c4c5d1bdd90ec0dcc0a5ba01e6a7a3580d5854866e84f016d7ca09","models.dev source terms","models.dev (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::moonshot-blog","moonshot-blog","refresh","Moonshot AI · moonshot-blog","Moonshot AI","https://www.kimi.ai/blog/","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-30","2026-08-30",null,"e97a09cc0fde109698674f533ce42fda6db81231cbb8158c426edbb6c5a25b54","Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:6d9c13f35e80558de5e0e93c792ab67de9a65be6ddeaadc93774858ad684a5c2; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:fcd8a80f66935c912eb0c5bb516df68948cea5fb2faedcc97b18f0dc726cfe40, parser output is 1, and classification is moved-source."],["refresh::moonshot-github","moonshot-github","refresh","Moonshot AI · moonshot-github","Moonshot AI","https://github.com/MoonshotAI","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"9acc81d63f061de81047dcbab6e36f899977f1ae640b5f551d68a7eb90a51ffb","Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::moonshot-huggingface","moonshot-huggingface","refresh","Moonshot AI · moonshot-huggingface","Moonshot AI","https://huggingface.co/moonshotai","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"d77b6cde6da5b1cff8a77118bfd240de48206f87f8cf764659a3c2c0aecdedd5","Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::moonshot-kimi-k3-official","moonshot-kimi-k3-official","refresh","Moonshot AI · moonshot-kimi-k3-official","Moonshot AI","https://www.kimi.ai/blog/kimi-k3","reviewed-html","official-provider","complete","identity|lifecycle|specification|licence|pricing|verification",null,"2026-08-20","2026-08-20",null,"cf89d33303866b0f33ab43d99dafbcbed7fbc68230d67acc7119acdb5d9f357c","Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","reviewed-model-metadata-1.0.0 | Manual review admitted metadata only; ranking and capability evidence are out of scope."],["refresh::moonshot-kimi-k3-repository","moonshot-kimi-k3-repository","refresh","Moonshot AI · moonshot-kimi-k3-repository","Moonshot AI","https://github.com/MoonshotAI/Kimi-K3","github-api","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-20","2026-08-20",null,"5dee38c76cd469d5e616a6126d709b405f76fc180ceda0c8d35450ef84e71295","Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","reviewed-model-metadata-1.0.0 | Manual review admitted metadata only; ranking and capability evidence are out of scope."],["refresh::moonshot-platform-docs","moonshot-platform-docs","refresh","Moonshot AI · moonshot-platform-docs","Moonshot AI","https://platform.kimi.ai/docs/overview","reviewed-html","official-provider","complete","identity|specification|pricing",null,"2026-08-30","2026-08-30",null,"bd1cefb3b9e7fc35b19cb82a4356a5e5bbd2dbb27ffab0c176611db36b974dce","Moonshot AI source terms","Moonshot AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:2c28851c9e563e1ddb73e34d36f771054dcb052dca0c2c832b7194ef8128c3a0; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:c88add2e56fe9d954c1defc353b555adeed2cfbcec9e526fbe657a3f99ef2f95, parser output is 1, and classification is expected-content-change."],["refresh::nvidia-huggingface","nvidia-huggingface","refresh","NVIDIA · nvidia-huggingface","NVIDIA","https://huggingface.co/nvidia","reviewed-html","official-provider","schema-drift","identity|lifecycle|specification",null,"2026-08-08","2026-08-15",null,"c57404d5be3329273f83d91768bc52a85e8eac4d7ff6e5303859313f8472716c","NVIDIA source terms","NVIDIA (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:ae63f4ceb69e471effaed6bdad9782c7a0e997bf7380a57a439d369b74b01d62 to adapter:2.0.0:5a3b94b1e7155131c24e3211940307eed720022225488f1089991a3267b52655."],["refresh::nvidia-model-catalogue","nvidia-model-catalogue","refresh","NVIDIA · nvidia-model-catalogue","NVIDIA","https://build.nvidia.com/models","reviewed-html","official-provider","complete","provider-surface|model-offering|availability",null,"2026-08-23","2026-08-23",null,"2eb550bb34f913f962546cb4adbef3f9017469f65b9c9cbc5cea53820f7e84d3","NVIDIA source terms","NVIDIA (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:f05fa9ff3dd888dde7e8f57fb0f06bb7aafbf38f0f32cb72fdd0841284c2efe1; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:dbd65a699799ca0a185980ca54b946e53ac21bcdf2cd4e7593fc6a6e96b482e6, parser output is 1, and classification is expected-content-change."],["refresh::openai-changelog","openai-changelog","refresh","OpenAI · openai-changelog","OpenAI","https://developers.openai.com/api/docs/changelog","reviewed-html","official-provider","not-modified","identity|lifecycle|specification|pricing",null,"2026-08-31","2026-08-31",null,"b84ea31607f902041592263bf78ae5763e63c977eca7b9e70a65f339e72c7dae","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | Conditional request returned 304; the prior immutable snapshot remains authoritative and extraction was skipped."],["refresh::openai-gpt-5-1-model","openai-gpt-5-1-model","refresh","OpenAI · openai-gpt-5-1-model","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.1","reviewed-html","official-provider","complete","identity|configuration|lifecycle|specification|availability|pricing|verification",null,"2026-08-31","2026-08-31",null,"953b076f16181e14a1407e91e671cae30e52b205eab97b2c7c1f97ec468fbdf9","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::openai-gpt-5-2-codex-model","openai-gpt-5-2-codex-model","refresh","OpenAI · openai-gpt-5-2-codex-model","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.2-codex","reviewed-html","official-provider","complete","identity|configuration|lifecycle|specification|availability|pricing|verification",null,"2026-08-31","2026-08-31",null,"fbdf62b6a668508caa259ebfec2cdb6c9c3cb9b2e29cb1f451ca5cef5b8f455c","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::openai-gpt-5-4-nano-model","openai-gpt-5-4-nano-model","refresh","OpenAI · openai-gpt-5-4-nano-model","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.4-nano","reviewed-html","official-provider","complete","identity|configuration|lifecycle|specification|availability|pricing|verification",null,"2026-08-31","2026-08-31",null,"ff525f1a15b4e4c18719165025c24f825125b48403fc0316850424b846616000","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::openai-gpt-5-codex-model","openai-gpt-5-codex-model","refresh","OpenAI · openai-gpt-5-codex-model","OpenAI","https://developers.openai.com/api/docs/models/gpt-5-codex","reviewed-html","official-provider","complete","identity|configuration|lifecycle|specification|availability|pricing|verification",null,"2026-08-31","2026-08-31",null,"26e7b773cedecdbe1811ad6d86cc54b3738c31bcf393b8736f63f269eca6b42c","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::openai-gpt-oss-120b-model","openai-gpt-oss-120b-model","refresh","OpenAI · openai-gpt-oss-120b-model","OpenAI","https://developers.openai.com/api/docs/models/gpt-oss-120b","reviewed-html","official-provider","complete","identity|lifecycle|specification|licence|availability|verification",null,"2026-08-31","2026-08-31",null,"7642a3ad8497ae5a8f0efefc6863dd84c5a082f23a823218dfacae34617f2e56","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::openai-model-catalogue","openai-model-catalogue","refresh","OpenAI · openai-model-catalogue","OpenAI","https://developers.openai.com/api/docs/models/all","reviewed-html","official-provider","not-modified","identity|configuration|lifecycle|specification|availability",null,"2026-08-31","2026-08-31",null,"7d3b704fb1fb2f64e51ca7d2b9d4ec5c5f185e6861a7b3dedc4a4d89aa6dee2a","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::openai-news","openai-news","refresh","OpenAI · openai-news","OpenAI","https://openai.com/news/","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-31","2026-08-31",null,"a0de3f06b6fb59cf966132cce6d7c0cf50d84b6ad83ca37eaea3d76115004299","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:c60e99656005874c6a23519c40f7b5cf7608ad5498226e77ed94487b43a1a726; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:ede7c0922902d58fa73233d0a7a94559f5ec4f9ff67f306cdc9404e2aecd618f, parser output is 1, and classification is expected-content-change."],["refresh::openai-pricing","openai-pricing","refresh","OpenAI · openai-pricing","OpenAI","https://developers.openai.com/api/docs/pricing","reviewed-html","official-provider","not-modified","pricing",null,"2026-08-31","2026-08-31",null,"e1975d9c39f1a0880ab9d7375081679f2edc2331050f1b9ae518a311fafea938","OpenAI source terms","OpenAI (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | Conditional request returned 304; the prior immutable snapshot remains authoritative and extraction was skipped."],["refresh::openrouter-models","openrouter-models","refresh","OpenRouter · openrouter-models","OpenRouter","https://openrouter.ai/api/v1/models?output_modalities=all","json","marketplace-operator","complete","provider-surface|model-offering|pricing|availability|discovery",null,"2026-08-20","2026-08-20",null,"5d07f8b228ffdd2d3ba0a9847999dc3bed6fdad41c6f738a474ecc3397bea8f2","OpenRouter source terms","OpenRouter (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","permanent-refresh-2.1.0"],["refresh::osworld-20","osworld-20","refresh","OSWorld · osworld-20","OSWorld","https://osworld-v2.xlang.ai/","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"7aa01dafa368ba27afb33338534fda8e2f553b2c960f92376db22f7c54daa078","OSWorld source terms","OSWorld (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::osworld-20-repo","osworld-20-repo","refresh","OSWorld · osworld-20-repo","OSWorld","https://github.com/xlang-ai/OSWorld-V2","github-api","official-benchmark","schema-drift","benchmark|benchmark-version|result",null,"2026-08-08","2026-08-15",null,"fe45449875d9dc13e87f7e6d2a246e22e5897e6a473af4731e1c770c712e9a8f","OSWorld source terms","OSWorld (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","release-triggered","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:46e7f40ffac9137f47f17a368f7bab724244bd6e29b1567cbbd70c54d25fec52 to adapter:2.0.0:8771c8e6e10e50929eeb6aa8a3fc241be5c9b2713a42bc40df0c3396c68573ef."],["refresh::osworld-v1","osworld-v1","refresh","OSWorld · osworld-v1","OSWorld","https://os-world.github.io/","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"bf37e00ce23e8c5472d485a6eb3b291ffa2de220b44040402516e41cbc48c516","OSWorld source terms","OSWorld (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0 | The final redirect target http://osworld-v1.xlang.ai/ is not HTTPS; the canonical HTTPS URL remains authoritative."],["refresh::poolside-laguna-xs-2-1-model-card","poolside-laguna-xs-2-1-model-card","refresh","Poolside · poolside-laguna-xs-2-1-model-card","Poolside","https://huggingface.co/poolside/Laguna-XS-2.1","reviewed-html","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-22","2026-08-22",null,"73ac07cdef79bebb4e8ad5a12e542c0395ae3822a7fcb2293b902022af83113f","Poolside source terms","Poolside (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::poolside-laguna-xs-2-1-release","poolside-laguna-xs-2-1-release","refresh","Poolside · poolside-laguna-xs-2-1-release","Poolside","https://poolside.ai/blog/introducing-laguna-xs-2-1","reviewed-html","official-provider","complete","identity|lifecycle|specification|availability|verification",null,"2026-08-22","2026-08-22",null,"6d29543011391f863b8edfb7a343892646c1d6be3242391d88bbfa573d1a8dcd","Poolside source terms","Poolside (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::qwen-3-8-27b-huggingface","qwen-3-8-27b-huggingface","refresh","Qwen · qwen-3-8-27b-huggingface","Qwen","https://huggingface.co/api/models/Qwen/Qwen3.8-27B","json","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-22","2026-08-22",null,"45cb4ba1e90aeb986fb25df8cbc84ae5741f48843a4d8a066bfdecca34a06f22","Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","reviewed-model-metadata-1.0.0 | Metadata only: no capability, benchmark, scoring or ranking evidence was admitted."],["refresh::qwen-3-8-max-huggingface","qwen-3-8-max-huggingface","refresh","Qwen · qwen-3-8-max-huggingface","Qwen","https://huggingface.co/api/models/Qwen/Qwen3.8-2.4T-A95B","json","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-20","2026-08-20",null,"097b8ba1517cb6964bf99027b439269f0da9808034a8431e96e7183bd96609c0","Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","complete","warning","every-refresh","reviewed-model-metadata-1.0.0 | Manual review admitted metadata only; ranking and capability evidence are out of scope."],["refresh::qwen-blog","qwen-blog","refresh","Qwen · qwen-blog","Qwen","https://qwen.ai/blog","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-30","2026-08-30",null,"ca8b2c44b30ddd2627c5c971b196c0bf3cf32afeaa876d6513d3f48b5a2b5f09","Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:bc66226d04e027112da61b7f5aca9b237fe87a88c3e019bd61f1846236e80206; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:043148a4fb55324938f76424b396dcffaf97ca975d480cb1bf2d32b716daf6f0, parser output is 1, and classification is expected-content-change."],["refresh::qwen-github","qwen-github","refresh","Qwen · qwen-github","Qwen","https://github.com/QwenLM","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"a39482d7b0bf7a101c1f7cb7b898a2e4278c3cd169e3df4cca40f25de516f5ee","Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::qwen-huggingface","qwen-huggingface","refresh","Qwen · qwen-huggingface","Qwen","https://huggingface.co/Qwen","reviewed-html","official-provider","schema-drift","identity|lifecycle|specification",null,"2026-08-08","2026-08-15",null,"b26cfbf8e5c9a26983ed17eb17b9a1aa997ad661c02182e9746de955489311b7","Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:45f92fcddeb20a3285023c97315e5bd0a922e921a447b0654af41bbd8a100245 to adapter:2.0.0:a9b7c45d3195c0b4ee556199e2c1069a55b0f387cbaac8bafc6ed98d252d10e4."],["refresh::qwen-modelscope","qwen-modelscope","refresh","Qwen · qwen-modelscope","Qwen","https://modelscope.cn/organization/qwen","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"acac931882024941c797605e8a86588ed0fcb03e8435176ad525265f94d98cad","Qwen source terms","Qwen (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::sakana-feed","sakana-feed","refresh","Sakana AI · sakana-feed","Sakana AI","https://sakana.ai/feed.xml","atom","official-provider","complete","identity|lifecycle|discovery",null,"2026-08-30","2026-08-30",null,"952cbf9126e8a18eb6cfe7f703e157a1f4f012606918ba643ba2957a4e8cc558","Sakana AI source terms","Sakana AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:bbefb190069525b11fbb15bd60d17f373801d23a5f974049d3c7c8beb4e24243; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:3819a5e62fd525d9a324b8ce89fff35edaf0d443f78bbe793a1b4f968468ac7e, parser output is 10, and classification is expected-content-change."],["refresh::sakana-huggingface","sakana-huggingface","refresh","Sakana AI · sakana-huggingface","Sakana AI","https://huggingface.co/SakanaAI","reviewed-html","official-provider","schema-drift","identity|lifecycle|specification",null,"2026-08-08","2026-08-15",null,"1d3a152167669a0f419ccf604d6b7ace81474904c0f511a5c564d3d79b318dd5","Sakana AI source terms","Sakana AI (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:04c6d64909294c1d460719bd118baa6142ab2de2747b38b0294c3b0789d0d4af to adapter:2.0.0:44ae95f4faf631bcdb9d58acad2c46445d1362eaf704add66be105ca31d295fb."],["refresh::scale-seal","scale-seal","refresh","Scale AI · scale-seal","Scale AI","https://labs.scale.com/leaderboard","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"c1b0b8fc23f0790a325c132ed8c517c3fa11dfbfa160d0c90d347c6234af673f","Scale AI source terms","Scale AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::tau-bench-current","tau-bench-current","refresh","Sierra Research · tau-bench-current","Sierra Research","https://tau-bench.com/","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"b59dca6082acdf19492d122360418832efe048cc5aab630e0bbb6719b108c235","Sierra Research source terms","Sierra Research (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0 | The final redirect target http://taubench.com/ is not HTTPS; the canonical HTTPS URL remains authoritative."],["refresh::tau-bench-legacy","tau-bench-legacy","refresh","Sierra Research · tau-bench-legacy","Sierra Research","https://github.com/sierra-research/tau-bench","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"fc964446fcef944ed9b735a14efaffba09fd09a07bc12e33721df87ddc73210b","Sierra Research source terms","Sierra Research (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::tau2-bench-repo","tau2-bench-repo","refresh","Sierra Research · tau2-bench-repo","Sierra Research","https://github.com/sierra-research/tau2-bench","github-api","official-benchmark","schema-drift","benchmark|benchmark-version|result",null,"2026-08-08","2026-08-15",null,"b6e50ed00f8f2e455ef498b657b87855c77bc5d2c9485a063221b6f0b4953ec8","Sierra Research source terms","Sierra Research (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","release-triggered","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:5b65e4cf84f5ea5494a657c03477238dd352797cb96215aa5dbabdfb6c820991 to adapter:2.0.0:662fd8de62c5bb8901fd6e08c9c06d6860d0ce6551d757ecae3992e0fee09582."],["refresh::stepfun-github","stepfun-github","refresh","StepFun · stepfun-github","StepFun","https://github.com/stepfun-ai","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"a24077f596221b620a4e409cda29fa319a916739fd111eefc5b46aea175db21c","StepFun source terms","StepFun (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::stepfun-huggingface","stepfun-huggingface","refresh","StepFun · stepfun-huggingface","StepFun","https://huggingface.co/stepfun-ai","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"a453299ae97a1164ec8f6470b98e44e4dd776c5dd1085639f391b87aa04c51a9","StepFun source terms","StepFun (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::swe-bench-results","swe-bench-results","refresh","SWE-bench · swe-bench-results","SWE-bench","https://github.com/SWE-bench/experiments","github-api","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-23","2026-08-23",null,"ce0486fd96d2786d60575c7e4da371e6b8b39caf1ac30dd6a6c220405321e896","SWE-bench source terms","SWE-bench (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:2c31a9bc326dba9e9f34c15f7b82f1690f9ea5265c989c7aa57357e37406965d; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:4035d6960b348477b0e3276a2b9b905ceb7e7fc9bc3a11aa577e609d96968911, parser output is 6, and classification is structural-change."],["refresh::swe-bench-site","swe-bench-site","refresh","SWE-bench · swe-bench-site","SWE-bench","https://www.swebench.com/","reviewed-html","official-benchmark","schema-drift","benchmark|benchmark-version|result",null,"2026-08-08","2026-08-15",null,"c9043b06f15c37becc1bcfa1d42b509a4439762f675eadab43e6bef40adace98","SWE-bench source terms","SWE-bench (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:b95d9217dbccc55958f4422b7b22bcb4269a8c2c402716ce742bbb68a085f39f to adapter:2.0.0:cb0e01c7cc53d5a3fa7a9f381a2b61fd78ce60b2fa9e1601e3a483ce4b4fcd44."],["refresh::tencent-hunyuan-github","tencent-hunyuan-github","refresh","Tencent Hunyuan · tencent-hunyuan-github","Tencent Hunyuan","https://github.com/Tencent-Hunyuan","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"e62995b39f21f745faddfa8d02311a294f9b83e6adfd64ce2a0970977f7f5a41","Tencent Hunyuan source terms","Tencent Hunyuan (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::tencent-hunyuan-huggingface","tencent-hunyuan-huggingface","refresh","Tencent Hunyuan · tencent-hunyuan-huggingface","Tencent Hunyuan","https://huggingface.co/tencent","reviewed-html","official-provider","schema-drift","identity|lifecycle|specification",null,"2026-08-08","2026-08-15",null,"51b521f009c81df3a2ed53c5f5b07eda50fc40ad252507b51cd0199a441ccdb4","Tencent Hunyuan source terms","Tencent Hunyuan (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:7cbb4e8a1d22c57f48fd25676e5dc2273c53e2ed4d818bf83fcadbbbd5f69efe to adapter:2.0.0:b542f21ddee67cd135cb129a2626b10f31ea21f9c64c92ab2e6855e266c1f3ee."],["refresh::terminal-bench-21","terminal-bench-21","refresh","Terminal-Bench · terminal-bench-21","Terminal-Bench","https://www.tbench.ai/leaderboard/terminal-bench/2.1","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"7259079b840513a4cd0968b56161d22f3556022eb3bc3e0ac13fed76e96ded47","Terminal-Bench source terms","Terminal-Bench (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::terminal-bench-21-repo","terminal-bench-21-repo","refresh","Terminal-Bench · terminal-bench-21-repo","Terminal-Bench","https://github.com/harbor-framework/terminal-bench-2-1","github-api","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-30","2026-08-30",null,"e9a4b08dd159e9b9eda3ed4027e5f024a8f73d11c732968a6e65734b78c3fb0a","Terminal-Bench source terms","Terminal-Bench (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:dc357bfbda169aa99492575c5301078aefdb6e4d017649396fc4adf387d8bc9a; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:b57f741c2dfdb61248be2df10ce4b8fed829443b1fb7d6674b631d03cb3bd45e, parser output is 1, and classification is expected-content-change."],["refresh::thinking-machines-news","thinking-machines-news","refresh","Thinking Machines Lab · thinking-machines-news","Thinking Machines Lab","https://thinkingmachines.ai/news/","reviewed-html","official-provider","complete","identity|lifecycle",null,"2026-08-30","2026-08-30",null,"0d073d3f471997dfe006321504ac6386b998d87504d020647399f857dd336d90","Thinking Machines Lab source terms","Thinking Machines Lab (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:38f90d12ecb7fe0e47bf9b5d1bfde05a16fb94108fe34a48e63afeeff32bc8b4; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:b638de2bb6f93588f346e3f3da8bd9003d41e5a06c64191ec17a7d2c395ceab2, parser output is 1, and classification is expected-content-change."],["refresh::thudm-legacy","thudm-legacy","refresh","THUDM · thudm-legacy","THUDM","https://github.com/THUDM","reviewed-html","official-provider","schema-drift","identity|specification",null,"2026-08-08","2026-08-15",null,"c09bdcd926b39a2df9ff404e2a7fb991ef31e1e3a3944a2acd8080997e60b734","THUDM source terms","THUDM (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:73db55af5d3da7b195ac881ab119d79d398cde1ffd11c20b91d5e221c1014c6d to adapter:2.0.0:de5150b1735eb2a6918094bd0c618b386fb1725107a5498a2cf309a91fc37987."],["refresh::upstage-solar-open2-250b-model-card","upstage-solar-open2-250b-model-card","refresh","Upstage · upstage-solar-open2-250b-model-card","Upstage","https://huggingface.co/upstage/Solar-Open2-250B","reviewed-html","official-provider","complete","identity|lifecycle|specification|licence|verification",null,"2026-08-22","2026-08-22",null,"6d4c877ff4b6e9ddcd9b5476a12aa665ead578f66c65a9b082759dd5ce328f02","Upstage source terms","Upstage (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::vals-ai","vals-ai","refresh","Vals AI · vals-ai","Vals AI","https://www.vals.ai/benchmarks","reviewed-html","official-benchmark","schema-drift","benchmark|benchmark-version|result",null,"2026-08-08","2026-08-15",null,"0b71dd5e0acc131ed430934d2ee8ee51f01df95254d069471c1a829b2a4e4ed4","Vals AI source terms","Vals AI (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","weekly","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:e567a45ca04352c02e391d4aa23508192e18d0aaa6198b359be7fbdc8371fc67 to adapter:2.0.0:90e383c41256c53105713a1bcd8f003aa091297c073444db3e7a5d5133359f00."],["refresh::video-mme-v1","video-mme-v1","refresh","Video-MME · video-mme-v1","Video-MME","https://video-mme.github.io/home_page.html","reviewed-html","official-benchmark","complete","benchmark|benchmark-version|result",null,"2026-08-15","2026-08-15",null,"02b88dcf1268ac331b79a3db7c1bdb1dde1d9f2389f424340ef6082c98adbe6d","Video-MME source terms","Video-MME (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::video-mme-v2","video-mme-v2","refresh","Video-MME · video-mme-v2","Video-MME","https://github.com/MME-Benchmarks/Video-MME-v2","github-api","official-benchmark","schema-drift","benchmark|benchmark-version|result",null,"2026-08-08","2026-08-15",null,"bd99620136fd50be08ff27c0f883fe602b6c001d054bf9065d4e73b4f408de5d","Video-MME source terms","Video-MME (source data remains attributed to its owner/evaluator).","unknown","schema-drift","warning","release-triggered","permanent-refresh-2.1.0 | Adapter-visible schema changed from adapter:2.0.0:d8ef3a6603f13605ecb1a7d28fd5d475d5d6559f4f025275e27287e0719daf41 to adapter:2.0.0:d938b1999a9b3ab7b8534a373272d2c6a3cd3ee9fd13908240d52687521900d6."],["refresh::xai-models","xai-models","refresh","xAI · xai-models","xAI","https://docs.x.ai/developers/models","reviewed-html","official-provider","complete","identity|configuration|lifecycle|specification|availability",null,"2026-08-31","2026-08-31",null,"4650d23a94d0a21a7752730768e59aac7f5a8a68243e9eb4b5a8999303031b68","xAI source terms","xAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:46fd0a42d0afbe714e60a1b47be6dfb7bcc2a136238c0c78ff7aec9646546547; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:be265a1a3f44019e82136fbe0892add02b4bcc25081b86119dbd06f1f325ada6, parser output is 1, and classification is expected-content-change."],["refresh::xai-pricing","xai-pricing","refresh","xAI · xai-pricing","xAI","https://docs.x.ai/developers/pricing","reviewed-html","official-provider","complete","pricing",null,"2026-08-31","2026-08-31",null,"3d7d1efff959b52bc063d0854a58c2262080835b83da202934cc0c31bddebc27","xAI source terms","xAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:7932253ffdc30a379d139dbc10770b5e23a887b8de55fa0983dc4801c0a64ae4; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:253fc92cc2936843781d3e6841f035beb53b6c8692619d1bb1f25dcea7305cff, parser output is 1, and classification is expected-content-change."],["refresh::xai-release-notes","xai-release-notes","refresh","xAI · xai-release-notes","xAI","https://docs.x.ai/developers/release-notes","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"d177a3af82e1e87439b12677d652cba78516661415e1ef9311c919a2b5202121","xAI source terms","xAI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","release-triggered","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:772ae7b07fe991dd02d563703a631e2f69738805e56ef2ec8aa945b5a0fa4de1; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:8147d02b75f4e744b6180c311593cc4c9f6723c2d6a0a63e342f9249a3ead211, parser output is 1, and classification is expected-content-change."],["refresh::xiaomi-mimo-github","xiaomi-mimo-github","refresh","Xiaomi MiMo · xiaomi-mimo-github","Xiaomi MiMo","https://github.com/XiaomiMiMo","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"c16579f4474f1be93f3d79f69a588d629cf07b0469186287c6ffb4e98e89c46b","Xiaomi MiMo source terms","Xiaomi MiMo (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::xiaomi-mimo-huggingface","xiaomi-mimo-huggingface","refresh","Xiaomi MiMo · xiaomi-mimo-huggingface","Xiaomi MiMo","https://huggingface.co/XiaomiMiMo","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-15","2026-08-15",null,"6c7aa57c73850f1dd6fddb7ca59c6ed4a617af17da165447b0396250a48f0a8f","Xiaomi MiMo source terms","Xiaomi MiMo (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0"],["refresh::zai-github","zai-github","refresh","Z.AI · zai-github","Z.AI","https://github.com/zai-org","github-api","official-provider","complete","identity|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"9238d02f24bfe7e79211fc77c23d6fd268a93e9ff799e6d78f4146c14f3cf7ee","Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:98a435d7a7b76afbe124b05a477022301f4fc73681fe5c5b2b4dee35fa87acf8; the v2 shape matched, the stable semantic fingerprint is semantic:semantic-structure-v1:09fa689ad3deb89858f16e6d8711128336f4b49f7cf982dced811d4ec223e548, parser output is 1, and classification is expected-content-change."],["refresh::zai-huggingface","zai-huggingface","refresh","Z.AI · zai-huggingface","Z.AI","https://huggingface.co/zai-org","reviewed-html","official-provider","complete","identity|lifecycle|specification",null,"2026-08-31","2026-08-31",null,"34c050ef5cbe1d4a171d109105396370e1da0430f7d42f5f94c0f9429df56255","Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","complete","warning","weekly","permanent-refresh-2.1.0 | Fresh shadow parse replayed adapter:2.0.0:3ff711961f1d77efd959456f208094be16a9bcd403d490d9804e7e291e6ab5aa; the v2 shape changed, the stable semantic fingerprint is semantic:semantic-structure-v1:9d9bbe8f17016344964fdd2e856c9234308b949e7e930fb35f3be10a717c41a9, parser output is 1, and classification is expected-content-change."],["refresh::zai-openapi","zai-openapi","refresh","Z.AI · zai-openapi","Z.AI","https://docs.z.ai/openapi.json","json","official-provider","not-modified","identity|configuration|specification|availability",null,"2026-08-31","2026-08-31",null,"bde781ffff7e402e4e99ee33eae3092da232369c1d54ccb46101acde4910947f","Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","every-refresh","permanent-refresh-2.1.0 | Conditional request returned 304; the prior immutable snapshot remains authoritative and extraction was skipped."],["refresh::zai-pricing","zai-pricing","refresh","Z.AI · zai-pricing","Z.AI","https://docs.z.ai/guides/overview/pricing","reviewed-html","official-provider","not-modified","pricing",null,"2026-08-31","2026-08-31",null,"6ad34d270a866c7a0e8ec545ee6427bac292ebea9d688038135901de31383586","Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["refresh::zai-release-notes","zai-release-notes","refresh","Z.AI · zai-release-notes","Z.AI","https://docs.z.ai/release-notes/new-released","reviewed-html","official-provider","not-modified","identity|lifecycle",null,"2026-08-31","2026-08-31",null,"f7cf44b48bb783b3eff8e10a36904a9cd00af86dc25981431db9afd895f05e18","Z.AI source terms","Z.AI (source data remains attributed to its owner/evaluator).","unknown","not-modified","warning","release-triggered","permanent-refresh-2.1.0 | SHA-256 matched the prior immutable snapshot; extraction was skipped."],["production::openrouter-models-api-2026-08-01","openrouter-models-api-2026-08-01","route availability|context|maximum output|modalities|route pricing|new model discovery","OpenRouter model catalogue — 2026-08-01","OpenRouter","https://openrouter.ai/api/v1/models","independent-registry","independent-registry","source-checked","route availability|context|maximum output|modalities|route pricing|new model discovery","2026-08-01",null,"2026-08-01",null,null,null,null,null,"source-checked",null,null,"Canonical, newly listed route records can add unranked model variants and route pricing. OpenRouter is not treated as a primary benchmark or provider-pricing source."],["production::anthropic-claude-opus-5-system-card","anthropic-claude-opus-5-system-card","safety evaluations|alignment audit|cyber and biology safeguards","Claude Opus 5 System Card","Anthropic","https://www.anthropic.com/claude-opus-5-system-card","official-model-card","official-model-card","source-checked","safety evaluations|alignment audit|cyber and biology safeguards","2026-07-24",null,"2026-07-24",null,null,null,null,null,"source-checked",null,null,null],["source-manifest::anthropic-api-release-notes","anthropic-api-release-notes","source-manifest","Anthropic · anthropic-api-release-notes","Anthropic","https://platform.claude.com/docs/en/release-notes/api","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"379ae9f9b9718fd65730b1ed626bc926132f45afbd75350ebebab9b75b195849",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to anthropic-api-release-notes-v1."],["source-manifest::anthropic-claude-opus-5-docs","anthropic-claude-opus-5-docs","source-manifest","Anthropic · anthropic-claude-opus-5-docs","Anthropic","https://platform.claude.com/docs/en/about-claude/models/whats-new-opus-5","source-manifest",null,"complete",null,null,null,"2026-07-24",null,null,null,null,null,"complete",null,null,"Manually reviewed structured facts from official Anthropic launch materials; no protected page copy retained beyond sourced scores and model identity."],["source-manifest::anthropic-claude-opus-5-launch","anthropic-claude-opus-5-launch","source-manifest","Anthropic · anthropic-claude-opus-5-launch","Anthropic","https://www.anthropic.com/news/claude-opus-5","source-manifest",null,"complete",null,null,null,"2026-07-24",null,null,null,null,null,"complete",null,null,"Manually reviewed structured facts from official Anthropic launch materials; no protected page copy retained beyond sourced scores and model identity."],["source-manifest::anthropic-claude-opus-5-system-card","anthropic-claude-opus-5-system-card","source-manifest","Anthropic · anthropic-claude-opus-5-system-card","Anthropic","https://www.anthropic.com/claude-opus-5-system-card","source-manifest",null,"complete",null,null,null,"2026-07-24",null,null,null,null,null,"complete",null,null,"Manually reviewed structured facts from official Anthropic launch materials; no protected page copy retained beyond sourced scores and model identity."],["source-manifest::anthropic-fable-mythos-5","anthropic-fable-mythos-5","source-manifest","Anthropic · anthropic-fable-mythos-5","Anthropic","https://platform.claude.com/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"62610acf4e4f3abeb99fd68ab2d5b1b1123d6391b88572c6b2f5fcba634b6419",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::anthropic-models-2026-07-24","anthropic-models-2026-07-24","source-manifest","Anthropic · anthropic-models-2026-07-24","Anthropic","https://platform.claude.com/docs/en/about-claude/models/overview","source-manifest",null,"complete",null,null,null,"2026-07-24",null,null,null,null,null,"complete",null,null,"Manually reviewed structured facts from official Anthropic launch materials; no protected page copy retained beyond sourced scores and model identity."],["source-manifest::anthropic-pricing-2026-07-24","anthropic-pricing-2026-07-24","source-manifest","Anthropic · anthropic-pricing-2026-07-24","Anthropic","https://platform.claude.com/docs/en/about-claude/pricing","source-manifest",null,"complete",null,null,null,"2026-07-24",null,null,null,null,null,"complete",null,null,"Manually reviewed structured facts from official Anthropic launch materials; no protected page copy retained beyond sourced scores and model identity."],["source-manifest::arena-leaderboard","arena-leaderboard","source-manifest","Arena · arena-leaderboard","Arena","https://arena.ai/leaderboard","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"0af038261ed194faf45f5b2a4d1698730257a81658fc4e5e18dfa33f336de888",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to arena-leaderboard-exact-v1."],["source-manifest::aa-claude-opus-48-max","aa-claude-opus-48-max","source-manifest","Artificial Analysis · aa-claude-opus-48-max","Artificial Analysis","https://artificialanalysis.ai/models/claude-opus-4-8","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"d420ca6377979052393796d6ac3b48f3b805461a01a2e30e87ff70e66410c5ee",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::aa-gemini-35-flash-medium","aa-gemini-35-flash-medium","source-manifest","Artificial Analysis · aa-gemini-35-flash-medium","Artificial Analysis","https://artificialanalysis.ai/models/gemini-3-5-flash-medium","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"c14de158281029903d61ce3bc2f86f375925300b189d58b1c7481463929c6e8b",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::aa-gpt-55-xhigh","aa-gpt-55-xhigh","source-manifest","Artificial Analysis · aa-gpt-55-xhigh","Artificial Analysis","https://artificialanalysis.ai/models/gpt-5-5/","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"c79a7296e8c1095d639cf3d6abcb89776492432beaab741d3375f5ce9eb5483b",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::aa-grok-45-high","aa-grok-45-high","source-manifest","Artificial Analysis · aa-grok-45-high","Artificial Analysis","https://artificialanalysis.ai/models/grok-4-5","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"b39c5b00c160885938fc8865e14e895a8edd1ab9aa65390da73ea996f954d15d",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::aa-hle-leaderboard","aa-hle-leaderboard","source-manifest","Artificial Analysis · aa-hle-leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/humanitys-last-exam","source-manifest",null,"complete",null,null,null,"2026-07-16",null,"refresh-2026-07-16-aa-hle-leaderboard",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::aa-llm-models-api","aa-llm-models-api","source-manifest","Artificial Analysis · aa-llm-models-api","Artificial Analysis","https://artificialanalysis.ai/api/v2/data/llms/models","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"9e88d0edd730735f19b1b3b120997aae6175888bdfce640b4b488fae3cb700f5",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to aa-llm-models-v2."],["source-manifest::aa-math-500","aa-math-500","source-manifest","Artificial Analysis · aa-math-500","Artificial Analysis","https://artificialanalysis.ai/evaluations/math-500","source-manifest",null,"complete",null,null,null,"2026-07-16",null,"refresh-2026-07-16-aa-math-500",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::aa-model-hy3","aa-model-hy3","source-manifest","Artificial Analysis · aa-model-hy3","Artificial Analysis","https://artificialanalysis.ai/models/hy3","source-manifest",null,"complete",null,null,null,"2026-07-16",null,"refresh-2026-07-16-aa-model-hy3",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::aa-model-muse-spark-1-1","aa-model-muse-spark-1-1","source-manifest","Artificial Analysis · aa-model-muse-spark-1-1","Artificial Analysis","https://artificialanalysis.ai/models/muse-spark-1-1","source-manifest",null,"complete",null,null,null,"2026-07-16",null,"refresh-2026-07-16-aa-model-muse-spark-1-1",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::aa-speech-to-speech","aa-speech-to-speech","source-manifest","Artificial Analysis · aa-speech-to-speech","Artificial Analysis","https://artificialanalysis.ai/speech-to-speech","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"ebc6ea9201513da86210f40e55af03e8d1672b7d7ac9e64a0463097d78b8b7ad",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to aa-speech-to-speech-v1."],["source-manifest::aa-standard-leaderboard","aa-standard-leaderboard","source-manifest","Artificial Analysis · aa-standard-leaderboard","Artificial Analysis","https://artificialanalysis.ai/leaderboards/models","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"16403f504d5f05c25fa05870a6b45c4801fc6ef81c3be62f0e748a090539738b",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to aa-standard-leaderboard-exact-v1."],["source-manifest::artificial-analysis-data-api-2026-07-27","artificial-analysis-data-api-2026-07-27","source-manifest","Artificial Analysis · artificial-analysis-data-api-2026-07-27","Artificial Analysis","https://artificialanalysis.ai/api/v2/data/llms/models","source-manifest",null,"complete",null,null,null,"2026-07-27",null,"8f6cc7f4b368e3161a4caf316970c85abcd11495bafbaf24f6531ab47d3f8707",null,null,null,"complete",null,null,"Authenticated exact-variant API facts normalized locally; raw response not retained."],["source-manifest::artificial-analysis-data-api-2026-08-01","artificial-analysis-data-api-2026-08-01","source-manifest","Artificial Analysis · artificial-analysis-data-api-2026-08-01","Artificial Analysis","https://artificialanalysis.ai/api/v2/data/llms/models","source-manifest",null,"complete",null,null,null,"2026-08-01",null,"30e778b9ef3849aa37da3da46e95b018444ad363f2b32717b9dfbbf32c4dd4af",null,null,null,"complete",null,null,"Authenticated exact-variant API facts normalized locally; raw response not retained."],["source-manifest::artificial-analysis-free-api-2026-07-21","artificial-analysis-free-api-2026-07-21","source-manifest","Artificial Analysis · artificial-analysis-free-api-2026-07-21","Artificial Analysis","https://artificialanalysis.ai/data-api/docs","source-manifest",null,"complete",null,null,null,"2026-07-21",null,"ef6121b9661d8ec0aa376b3b47398cfb0fc36b6709e451ca1cafee018501d0be",null,null,null,"complete",null,null,"Normalized Free API facts only; raw responses not retained."],["source-manifest::artificial-analysis-methodology","artificial-analysis-methodology","source-manifest","Artificial Analysis · artificial-analysis-methodology","Artificial Analysis","https://artificialanalysis.ai/methodology","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"e1f57a1d2ad055f102e859719ac948cfad7deb3a9b03a537a4f00c10451a8045",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::benchlm-leaderboard-2026-07-16","benchlm-leaderboard-2026-07-16","source-manifest","BenchLM · benchlm-leaderboard-2026-07-16","BenchLM","https://benchlm.ai/api/data/leaderboard?mode=bench-align-v5&limit=300","source-manifest",null,"complete",null,null,null,"2026-07-16",null,"refresh-2026-07-16-benchlm-leaderboard-2026-07-16",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::benchlm-public-dataset-2026-07-21","benchlm-public-dataset-2026-07-21","source-manifest","BenchLM · benchlm-public-dataset-2026-07-21","BenchLM","https://benchlm.ai/embed","source-manifest",null,"complete",null,null,null,"2026-07-21",null,"bf34950090c41d28e1ee1f52c1b6bfed6eeabc50f3d0d14da8eb836c2d3e7eff",null,null,null,"complete",null,null,"Public JSON/CSV snapshot with composite values separated from benchmark evidence."],["source-manifest::benchlm-public-dataset-2026-07-27","benchlm-public-dataset-2026-07-27","source-manifest","BenchLM · benchlm-public-dataset-2026-07-27","BenchLM","https://benchlm.ai/data/leaderboard.json","source-manifest",null,"complete",null,null,null,"2026-07-27",null,"9885fdd674e6be4e54c0e685176259b6bfa158544314b9084e03073d638223af",null,null,null,"complete",null,null,"Five live public JSON datasets reconciled; composites separated from reference-only benchmark evidence."],["source-manifest::benchlm-public-dataset-2026-08-01","benchlm-public-dataset-2026-08-01","source-manifest","BenchLM · benchlm-public-dataset-2026-08-01","BenchLM","https://benchlm.ai/data/leaderboard.json","source-manifest",null,"complete",null,null,null,"2026-08-01",null,"691acfedfefe4646c6ea36981fa8ed0245fec6132bc3393ac5ae9e56217c8198",null,null,null,"complete",null,null,"Seven live public JSON datasets reconciled; composites separated from reference-only benchmark evidence."],["source-manifest::epoch-ai-datasets-2026-08-01","epoch-ai-datasets-2026-08-01","source-manifest","Epoch AI · epoch-ai-datasets-2026-08-01","Epoch AI","https://epoch.ai/data/ai_models.zip","source-manifest",null,"complete",null,null,null,"2026-08-01",null,"29108acf2f6401dc2cc7e7a3354bb814d26557be42fcad1d7bbd12f07e6a9322",null,null,null,"complete",null,null,"Model and benchmark ZIP payloads hashed as historical/reference inputs; heterogeneous records not admitted as direct frontier rows."],["source-manifest::epoch-benchmark-data","epoch-benchmark-data","source-manifest","Epoch AI · epoch-benchmark-data","Epoch AI","https://epoch.ai/data/benchmark_data.zip","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"f062da3b37cee0f5ae2c3abca9e6a5b68e1b4f61dfbb9c44b74b0fb296f01fc0",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to epoch-benchmark-archive-v1."],["source-manifest::epoch-model-data","epoch-model-data","source-manifest","Epoch AI · epoch-model-data","Epoch AI","https://epoch.ai/data/ai_models.zip","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"fe81b4c5eb6ded153a3d33b59b7b3af9018437dc6c722e8cbcfcc59426e282c4",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to epoch-model-archive-v1."],["source-manifest::frontiermath","frontiermath","source-manifest","Epoch AI · frontiermath","Epoch AI","https://epoch.ai/frontiermath","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"76217d0540fd5c2f2e94790566d86f3619db4997a43e6010c3c03df9629d0c6b",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to frontiermath-exact-v1."],["source-manifest::gaia","gaia","source-manifest","GAIA · gaia","GAIA","https://huggingface.co/spaces/gaia-benchmark/leaderboard","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"8250bf0e3d847f2046d9f99338e00c68983df39200b4f8fa9d6c53f50b8fee25",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to gaia-exact-v1."],["source-manifest::google-gemini-35-model-card","google-gemini-35-model-card","source-manifest","Google DeepMind · google-gemini-35-model-card","Google DeepMind","https://deepmind.google/models/model-cards/gemini-3-5-flash/","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"d7b4ab298c81a3d8129f59246e5c2a38a463ff2927092066ab06803548f9b7b3",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::huggingface-text-generation-2026-08-01","huggingface-text-generation-2026-08-01","source-manifest","Hugging Face · huggingface-text-generation-2026-08-01","Hugging Face","https://huggingface.co/api/models?pipeline_tag=text-generation&sort=lastModified&direction=-1&limit=100","source-manifest",null,"complete",null,null,null,"2026-08-01",null,"43eb5a3246cacf3ed6842593f34d8b7d14c4feddef50fc652d883708a5981ab9",null,null,null,"complete",null,null,"Recent text-generation model feed and OpenAPI reference checked for discovery only."],["source-manifest::i2i-bench-paper","i2i-bench-paper","source-manifest","I2I-Bench · i2i-bench-paper","I2I-Bench","https://openaccess.thecvf.com/content/CVPR2026/html/Wang_I2I-Bench_A_Comprehensive_Benchmark_Suite_for_Image-to-Image_Editing_Models_CVPR_2026_paper.html","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"23468b64796a987fd8c8b53ae43f2397a7aac1274cede83b37d3a08d5469b92e",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to i2i-bench-paper-exact-v1."],["source-manifest::litellm-model-prices-2026-08-01","litellm-model-prices-2026-08-01","source-manifest","LiteLLM · litellm-model-prices-2026-08-01","LiteLLM","https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json","source-manifest",null,"complete",null,null,null,"2026-08-01",null,"ba37bb46dc4662f4bfed71db90168644ef917713fa073bd397775376d55a6b1c",null,null,null,"complete",null,null,"Pricing and context registry retained for conflict detection only."],["source-manifest::meta-muse-spark-1-1-eval","meta-muse-spark-1-1-eval","source-manifest","Meta · meta-muse-spark-1-1-eval","Meta","https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report","source-manifest",null,"complete",null,null,null,"2026-07-16",null,"refresh-2026-07-16-meta-muse-spark-1-1-eval",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::minimax-m3","minimax-m3","source-manifest","MiniMax · minimax-m3","MiniMax","https://www.minimax.io/models/text/m3","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"61e8056d571b7baf9774a476f75d957065529a38782e9712b9ed94f58faaae73",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::minimax-m3-pricing","minimax-m3-pricing","source-manifest","MiniMax · minimax-m3-pricing","MiniMax","https://platform.minimax.io/subscribe/token-plan?tab=api-enterprise","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"da065648be9e42f4560dc78e3f531fcb9d9cbb8e81fd575722cfdc1fd6f28220",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::models-dev-api-2026-07-27","models-dev-api-2026-07-27","source-manifest","models.dev · models-dev-api-2026-07-27","models.dev","https://models.dev/api.json","source-manifest",null,"complete",null,null,null,"2026-07-27",null,"ee9717714365449d9deec7ff808d494a8d724031389320de232c9150973f2de1",null,null,null,"complete",null,null,"Exact provider/model-ID matches; missing metadata filled without overwriting provider-owned values."],["source-manifest::models-dev-api-2026-08-01","models-dev-api-2026-08-01","source-manifest","models.dev · models-dev-api-2026-08-01","models.dev","https://models.dev/api.json","source-manifest",null,"complete",null,null,null,"2026-08-01",null,"694e4b9d683beed0439fd23087b14dd4ac1c2fad37fc8697ca674800bf9cac17",null,null,null,"complete",null,null,"Exact provider/model-ID matches across models.json, api.json and catalog.json; missing metadata filled without overwriting provider-owned values."],["source-manifest::nvidia-nemotron","nvidia-nemotron","source-manifest","NVIDIA · nvidia-nemotron","NVIDIA","https://developer.nvidia.com/topics/ai/nemotron","source-manifest",null,"failed",null,null,null,"2026-08-03",null,"bcdd7abbb45a6445b72666a9fa8576b96a0bb99136c2606e7f62e91e84c110ca",null,null,null,"failed",null,null,"verified-refresh-1.0.0; candidate admission restricted to nvidia-nemotron-v1."],["source-manifest::openai-deprecations","openai-deprecations","source-manifest","OpenAI · openai-deprecations","OpenAI","https://developers.openai.com/api/docs/deprecations","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"0a66c25eb1537f8e53e1e435f3c5058256065b8724350b6b227698693f64d249",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to openai-deprecations-v1."],["source-manifest::openai-gpt-53-codex","openai-gpt-53-codex","source-manifest","OpenAI · openai-gpt-53-codex","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.3-codex","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"c91ab91294f96784f8cd97ffe6ce0dcf51ee73b66923c2374fe15b26992fb20e",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::openai-gpt-54","openai-gpt-54","source-manifest","OpenAI · openai-gpt-54","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.4","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"9f1ec083c536fab8b898e414c54a5831b0a8c4daa5cfb17712808890c4467ffb",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::openai-gpt-55","openai-gpt-55","source-manifest","OpenAI · openai-gpt-55","OpenAI","https://developers.openai.com/api/docs/models/gpt-5.5","source-manifest",null,"complete",null,null,null,"2026-07-15",null,"3bb0029464d2b0f4802a5f1ca1c07f119ee4374f4d7f75e02313b1bd2eef04d2",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::openrouter-models-api-2026-08-01","openrouter-models-api-2026-08-01","source-manifest","OpenRouter · openrouter-models-api-2026-08-01","OpenRouter","https://openrouter.ai/api/v1/models","source-manifest",null,"complete",null,null,null,"2026-08-01",null,"ab96873964d38c257f815c6a475a164644e313a23979ac705d0793f643ede8ce",null,null,null,"complete",null,null,"Canonical newly listed variants and route metadata retained as discovery and pricing cross-check evidence."],["source-manifest::osworld","osworld","source-manifest","OSWorld · osworld","OSWorld","https://os-world.github.io/","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"bf37e00ce23e8c5472d485a6eb3b291ffa2de220b44040402516e41cbc48c516",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to osworld-exact-v1."],["source-manifest::qwen38-release","qwen38-release","source-manifest","Qwen · qwen38-release","Qwen","https://qwen.ai/blog?id=qwen3.8","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"5020fef550b259a2db636b269026887e1155382613824228a0fd3ca78aa7a730",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to qwen38-release-v1."],["source-manifest::sakana-news","sakana-news","source-manifest","Sakana AI · sakana-news","Sakana AI","https://sakana.ai/news/","source-manifest",null,"failed",null,null,null,"2026-08-03",null,"59b46d3c46fac56fd888824fd29738bcf59d07bc5d23207371e1ee9d69b7630d",null,null,null,"failed",null,null,"verified-refresh-1.0.0; candidate admission restricted to sakana-news-v1."],["source-manifest::tau-bench","tau-bench","source-manifest","Sierra Research · tau-bench","Sierra Research","https://github.com/sierra-research/tau-bench","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"ba8c730a4e524163f4c35e5d7e455fb860c9fb0912b2a985faa29b4e582f4de3",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to tau-bench-exact-v1."],["source-manifest::swe-bench-experiments","swe-bench-experiments","source-manifest","SWE-bench · swe-bench-experiments","SWE-bench","https://github.com/SWE-bench/experiments","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"2a31997c4a495bea65af20b177f1bba8972b90ef0de9d1eee6fe685036b6a51e",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to swe-bench-experiments-git-v1."],["source-manifest::swe-bench-experiments-2026-08-01","swe-bench-experiments-2026-08-01","source-manifest","SWE-bench · swe-bench-experiments-2026-08-01","SWE-bench","https://github.com/SWE-bench/experiments","source-manifest",null,"complete",null,null,null,"2026-08-01",null,"5e278b8edb2cd06c07e3b0151a4548fbd4181ad15ed177deba85d3e2d7950130",null,null,null,"complete",null,null,"Repository page and main-tree snapshot checked for experiment discovery; incomplete configurations remain reference-only."],["source-manifest::tencent-hy3-hf","tencent-hy3-hf","source-manifest","Tencent Hy Team · tencent-hy3-hf","Tencent Hy Team","https://huggingface.co/tencent/Hy3","source-manifest",null,"complete",null,null,null,"2026-07-16",null,"refresh-2026-07-16-tencent-hy3-hf",null,null,null,"complete",null,null,"Manually reviewed structured facts only; no protected page copy retained."],["source-manifest::video-mme","video-mme","source-manifest","Video-MME · video-mme","Video-MME","https://video-mme.github.io/home_page.html","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"02b88dcf1268ac331b79a3db7c1bdb1dde1d9f2389f424340ef6082c98adbe6d",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to video-mme-exact-v1."],["source-manifest::xai-docs","xai-docs","source-manifest","xAI · xai-docs","xAI","https://docs.x.ai/","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"9668972089e82d287812f1edf4a654d11399ed96bc58207b2959bb1f47687a1b",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to xai-docs-v1."],["source-manifest::xai-news","xai-news","source-manifest","xAI · xai-news","xAI","https://x.ai/news","source-manifest",null,"failed",null,null,null,"2026-08-03",null,"d430997a5e33788948d1dc10118ae4e0f107a81d9bc2eaa6fe93a151b2b2fb0d",null,null,null,"failed",null,null,"verified-refresh-1.0.0; candidate admission restricted to xai-news-v1."],["source-manifest::zai-blog","zai-blog","source-manifest","Z.AI · zai-blog","Z.AI","https://z.ai/blog","source-manifest",null,"failed",null,null,null,"2026-08-03",null,"59b46d3c46fac56fd888824fd29738bcf59d07bc5d23207371e1ee9d69b7630d",null,null,null,"failed",null,null,"verified-refresh-1.0.0; candidate admission restricted to zai-blog-v1."],["source-manifest::zai-docs","zai-docs","source-manifest","Z.AI · zai-docs","Z.AI","https://docs.z.ai/","source-manifest",null,"complete",null,null,null,"2026-08-03",null,"674699f1b41905d0f055ad5e8c77acceeba11371f17b550ae77577a300829267",null,null,null,"complete",null,null,"verified-refresh-1.0.0; candidate admission restricted to zai-docs-v1."],["production::refresh-meta-muse-spark-1-2-deepswe-chart","refresh-meta-muse-spark-1-2-deepswe-chart","source|configuration|benchmark-version|result|verification","Meta Superintelligence Labs permanent refresh source","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/deepswe-1-1-v1.png","official-docs","official-docs","source-checked","source|configuration|benchmark-version|result|verification",null,null,"2026-08-15",null,null,"Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Adapter meta-muse-spark-1-2-deepswe-chart-reviewed-html@2.0.0; role release-triggered."],["production::refresh-meta-muse-spark-1-2-gdpval-chart","refresh-meta-muse-spark-1-2-gdpval-chart","source|configuration|benchmark-version|result|verification","Meta Superintelligence Labs permanent refresh source","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/gdpval-aa-v2-v1.png","official-docs","official-docs","source-checked","source|configuration|benchmark-version|result|verification",null,null,"2026-08-15",null,null,"Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Adapter meta-muse-spark-1-2-gdpval-chart-reviewed-html@2.0.0; role release-triggered."],["production::refresh-meta-muse-spark-1-2-internal-coding-chart","refresh-meta-muse-spark-1-2-internal-coding-chart","source|configuration|benchmark-version|result|verification","Meta Superintelligence Labs permanent refresh source","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/meta-internal-coding-bench-v1.png","official-docs","official-docs","source-checked","source|configuration|benchmark-version|result|verification",null,null,"2026-08-15",null,null,"Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Adapter meta-muse-spark-1-2-internal-coding-chart-reviewed-html@2.0.0; role release-triggered."],["production::refresh-meta-muse-spark-1-2-mcp-atlas-chart","refresh-meta-muse-spark-1-2-mcp-atlas-chart","source|configuration|benchmark-version|result|verification","Meta Superintelligence Labs permanent refresh source","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/mcp-atlas-v1.png","official-docs","official-docs","source-checked","source|configuration|benchmark-version|result|verification",null,null,"2026-08-15",null,null,"Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Adapter meta-muse-spark-1-2-mcp-atlas-chart-reviewed-html@2.0.0; role release-triggered."],["production::refresh-meta-muse-spark-1-2-release","refresh-meta-muse-spark-1-2-release","source|configuration|benchmark-version|result|verification","Meta Superintelligence Labs permanent refresh source","Meta Superintelligence Labs","https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2","official-docs","official-docs","source-checked","source|configuration|benchmark-version|result|verification",null,null,"2026-08-30",null,null,"Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Adapter meta-muse-spark-1-2-release-reviewed-html@2.0.0; role release-triggered."],["production::refresh-meta-muse-spark-1-2-terminal-bench-chart","refresh-meta-muse-spark-1-2-terminal-bench-chart","source|configuration|benchmark-version|result|verification","Meta Superintelligence Labs permanent refresh source","Meta Superintelligence Labs","https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/terminal-bench-2-1-v1.png","official-docs","official-docs","source-checked","source|configuration|benchmark-version|result|verification",null,null,"2026-08-15",null,null,"Meta Superintelligence Labs source terms","Meta Superintelligence Labs (source data remains attributed to its owner/evaluator).","metadata-only","source-checked",null,null,"Adapter meta-muse-spark-1-2-terminal-bench-chart-reviewed-html@2.0.0; role release-triggered."],["production::refresh-epoch-benchmarks","refresh-epoch-benchmarks","source|external-identity|configuration|benchmark-version|result|verification","Epoch AI permanent refresh source","Epoch AI","https://epoch.ai/data/benchmarks.csv","independent-lab","independent-lab","source-checked","source|external-identity|configuration|benchmark-version|result|verification",null,null,"2026-09-01",null,null,"Epoch AI source terms","Epoch AI (source data remains attributed to its owner/evaluator).","allowed","source-checked",null,null,"Adapter epoch-benchmark-csv-v3@3.0.0; explicit Top-10 independent-evidence admission review; dataset SHA-256 903548a14073ce55416cf60f8301e29afddf825759b2e48907869a462fe1b1b2."],["production::anthropic-opus-4-7-docs-2026-08-29","anthropic-opus-4-7-docs-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Claude Opus 4.7 official model and effort documentation","Anthropic","https://platform.claude.com/docs/en/models/opus-4-7/overview","official-docs","official-docs","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification",null,null,"2026-08-29",null,null,null,null,"metadata-only","source-checked",null,null,"Official model, context, output, adaptive effort, API availability and direct-pricing documentation. The ranked max-effort configuration remains distinct from the API default effort."],["production::anthropic-opus-4-7-release-2026-08-29","anthropic-opus-4-7-release-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Claude Opus 4.7 official release","Anthropic","https://www.anthropic.com/news/claude-opus-4-7","official-provider-evaluation","official-provider-evaluation","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","2026-04-16",null,"2026-08-29",null,"0e396f09526fc4e81b0f9d493a61a40461ea97aea067715d0d769d6ab9ad3455",null,null,"metadata-only","source-checked",null,null,"Official launch source for the Opus 4.7 model identity and adaptive-reasoning release."],["production::gemma-4-26b-a4b-model-card-2026-08-29","gemma-4-26b-a4b-model-card-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Gemma 4 26B A4B official model card","Google","https://huggingface.co/google/gemma-4-26B-A4B-it","official-model-card","official-model-card","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","2026-04-02",null,"2026-08-29",null,"4f463225c4fe49ec120115b0f9bb6713ff1556293a909903ffdae3df7bf974da",null,null,"metadata-only","source-checked",null,null,"Official model card for exact identity, 25.2B total and 3.8B active parameters, context, image input, configurable thinking, licence and tool use."],["production::mistral-medium-3-5-model-card-2026-08-29","mistral-medium-3-5-model-card-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Mistral Medium 3.5 128B official model card","Mistral AI","https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","official-model-card","official-model-card","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","2026-04-29",null,"2026-08-29",null,"6d14ac4dba5a4c8b3d652ea67742ee1b41e424772194b8088cd62603d5032465",null,null,"metadata-only","source-checked",null,null,"Official model card for exact identity, dense 128B architecture, 256K context, image input, configurable reasoning, tool use and licence."],["production::mistral-medium-3-5-api-docs-2026-08-29","mistral-medium-3-5-api-docs-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Mistral Medium 3.5 official API and pricing documentation","Mistral AI","https://docs.mistral.ai/models/mistral-medium-3-5-26-04","official-docs","official-docs","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","2026-04-29",null,"2026-08-29",null,"49048e9178fcc9712360b5ce23adaeec11fa240057e9880e8607a0909867f26d",null,null,"metadata-only","source-checked",null,null,"Official direct API availability and list pricing for Mistral Medium 3.5."],["production::kimi-k2-5-model-card-2026-08-29","kimi-k2-5-model-card-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Kimi K2.5 official model card and evaluation table","Moonshot AI","https://huggingface.co/moonshotai/Kimi-K2.5","official-model-card","official-model-card","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","2026-01-27",null,"2026-08-29",null,"1b04bed9c6c25894171c0ab5e0b4c4d57667698a654dbfd5a6c1649b922810a5",null,null,"metadata-only","source-checked",null,null,"Official model card for exact identity, 1T total and 32B active parameters, multimodal thinking configuration, licence, tools and provider-run benchmark results."],["production::qwen3-5-122b-a10b-model-card-2026-08-29","qwen3-5-122b-a10b-model-card-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Qwen3.5-122B-A10B official model card","Qwen","https://huggingface.co/Qwen/Qwen3.5-122B-A10B","official-model-card","official-model-card","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","2026-03-04",null,"2026-08-29",null,"1775bb720398d6107cce3da0c3129abfd24ec639fd9853d5134df1e5c6118a4d",null,null,"metadata-only","source-checked",null,null,"Official model card for exact identity, 122B total and 10B active parameters, native context, modalities, thinking control, licence and tools."],["production::qwen3-5-397b-a17b-model-card-2026-08-29","qwen3-5-397b-a17b-model-card-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Qwen3.5-397B-A17B official model card","Qwen","https://huggingface.co/Qwen/Qwen3.5-397B-A17B","official-model-card","official-model-card","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","2026-02-16",null,"2026-08-29",null,"bda4b24e975f65ac677985306ddbad33362e65064637660654c8bb7dea7edf50",null,null,"metadata-only","source-checked",null,null,"Official model card for exact identity, 397B total and 17B active parameters, native context, modalities, thinking control, licence and tools."],["production::qwen3-6-35b-a3b-model-card-2026-08-29","qwen3-6-35b-a3b-model-card-2026-08-29","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","Qwen3.6-35B-A3B official model card","Qwen","https://huggingface.co/Qwen/Qwen3.6-35B-A3B","official-model-card","official-model-card","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|pricing|model-offering|provider-surface|result|verification","2026-04-15",null,"2026-08-29",null,"c4ddaa065649ff6352648f64747a16eda31726f3e34add94ce04abb461c77b75",null,null,"metadata-only","source-checked",null,null,"Official model card for identity, architecture, parameters, native context, modalities, thinking control, licence, tools and provider benchmark tables."],["production::google-gemma-4-12b-model-card-2026-08-30","google-gemma-4-12b-model-card-2026-08-30","source|identity|configuration|lifecycle|specification|availability|licence|result|verification","Gemma 4 12B official model card","Google","https://huggingface.co/google/gemma-4-12B","official-model-card","official-model-card","source-checked","source|identity|configuration|lifecycle|specification|availability|licence|result|verification","2026-05-23",null,"2026-08-30",null,"131e26f7f1fa69445dc4b0ab98a2251811f8c3128426bf09fcef6ac5ee16e7e4",null,null,"metadata-only","source-checked",null,null,"Official Google model card for Gemma 4 12B Unified identity, 256K context, text/image/audio/video input, configurable thinking, Apache-2.0 weights, function calling, and provider evaluation metadata. The provider table is not promoted into scoring without an exact compatible evaluation tuple."],["production::longcat-quickstart-docs-2026-08-29","longcat-quickstart-docs-2026-08-29","specification|availability|verification","LongCat 2.0 API limits and access documentation","LongCat","https://longcat.chat/platform/docs/","official-docs","official-docs","source-checked","specification|availability|verification",null,null,"2026-08-29",null,"b179bff97b17b4ae622be862ba5ebaad526e0a70152904f045e622183a774dc6",null,null,"metadata-only","source-checked",null,null,"Current first-party LongCat API documentation checked during the saturation pass."],["production::refresh-litellm-pricing-context","refresh-litellm-pricing-context","specification|pricing|discovery","LiteLLM permanent refresh source","LiteLLM","https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json","independent-registry","independent-registry","source-checked","specification|pricing|discovery",null,null,"2026-08-07",null,null,"LiteLLM source terms","LiteLLM (source data remains attributed to its owner/evaluator).","unknown","source-checked",null,null,"Adapter litellm-corroboration-v2@2.0.0; role corroboration."],["production::artificial-analysis-free-api-2026-07-21","artificial-analysis-free-api-2026-07-21","stable model identity|pricing|runtime observations|display-only composite indices","Artificial Analysis Free API — 21 July 2026","Artificial Analysis","https://artificialanalysis.ai/data-api/docs","independent-lab","independent-lab","source-checked","stable model identity|pricing|runtime observations|display-only composite indices","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,"Free API data requires attribution. Raw API payloads are not committed and composite indices never enter the Lumina Power Index."],["production::swe-marathon-site","swe-marathon-site","SWE Marathon completion rate","SWE Marathon","Abundant AI","https://www.swe-marathon.org/","official-leaderboard","official-leaderboard","source-checked","SWE Marathon completion rate",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::benchlm-gemini-3-5-flash-lite","benchlm-gemini-3-5-flash-lite","synced AA evaluation rows|provider-reported rows","Gemini 3.5 Flash-Lite on BenchLM","BenchLM","https://benchlm.ai/models/gemini-3-5-flash-lite","independent-lab","independent-lab","source-checked","synced AA evaluation rows|provider-reported rows","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::benchlm-gemini-3-6-flash","benchlm-gemini-3-6-flash","synced AA evaluation rows|provider-reported rows","Gemini 3.6 Flash on BenchLM","BenchLM","https://benchlm.ai/models/gemini-3-6-flash","independent-lab","independent-lab","source-checked","synced AA evaluation rows|provider-reported rows","2026-07-21",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::meta-muse-spark-1-2-methodology-2026-08-05","meta-muse-spark-1-2-methodology-2026-08-05","Terminal-Bench 2.1|DeepSWE 1.1|GDPval-AA v2|MCP Atlas|Meta Internal Coding Bench|evaluation harnesses|reasoning setting","Muse Spark 1.2 Evaluation Methodology","Meta Superintelligence Labs","https://research.meta.ai/static/muse-spark-1-2-methodology","official-provider-evaluation","official-provider-evaluation","source-checked","Terminal-Bench 2.1|DeepSWE 1.1|GDPval-AA v2|MCP Atlas|Meta Internal Coding Bench|evaluation harnesses|reasoning setting","2026-08-05",null,"2026-08-05",null,null,null,null,null,"source-checked",null,null,"Provider methodology report separating Muse Code, Artificial Analysis, Scale AI, and Meta-internal harnesses. All published Muse Spark 1.2 evaluations use xhigh reasoning."],["production::benchlm-terminal-bench-2026-07-20","benchlm-terminal-bench-2026-07-20","Terminal-Bench accuracy","Terminal-Bench 2.0 Leaderboard & Scores — July 2026","BenchLM","https://benchlm.ai/benchmarks/terminalBench","independent-lab","independent-lab","source-checked","Terminal-Bench accuracy","2026-07-20",null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::aa-terminalbench-hard","aa-terminalbench-hard","Terminal-Bench Hard accuracy","Terminal-Bench Hard Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/terminalbench-hard","independent-lab","independent-lab","source-checked","Terminal-Bench Hard accuracy","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["arena::text-to-image::overall::9a311991c5c12dae0886ade59553f881b21948fb0a63caa894f926afddae3539","9a311991c5c12dae0886ade59553f881b21948fb0a63caa894f926afddae3539","text-to-image","Arena text-to-image overall leaderboard snapshot","Arena Intelligence","https://arena.ai/leaderboard/text-to-image/","official-live-page","official-benchmark","verified-primary-owner-page","ranking","2026-08-25",null,"2026-08-30","9a311991c5c12dae0886ade59553f881b21948fb0a63caa894f926afddae3539","9a311991c5c12dae0886ade59553f881b21948fb0a63caa894f926afddae3539",null,"Arena Intelligence (source-native ranking evidence).","metadata-only","verified-primary-owner-page",null,null,null],["production::lmarena-text-to-image-live-2026-08-09","lmarena-text-to-image-live-2026-08-09","text-to-image model identity|Arena Score|external votes|confidence interval|preliminary status","LMArena Text-to-Image Arena Overall leaderboard","LMArena","https://arena.ai/leaderboard/text-to-image","official-leaderboard","official-leaderboard","source-checked","text-to-image model identity|Arena Score|external votes|confidence interval|preliminary status","2026-08-07",null,"2026-08-09",null,null,"LMArena source terms","LMArena","metadata-only","source-checked",null,null,"Official live-page supplement used only for exact identities not yet present in the pinned immutable Parquet revision."],["arena::text_to_video::overall::51d09b2e834b9d94fe15308531b8b039446fb33a","51d09b2e834b9d94fe15308531b8b039446fb33a","text-to-video","Arena text-to-video overall leaderboard snapshot","lmarena-ai/leaderboard-dataset","https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/51d09b2e834b9d94fe15308531b8b039446fb33a/text_to_video/latest-00000-of-00001.parquet","immutable-parquet","official-benchmark","verified-primary","ranking","2026-08-27",null,"2026-08-30","51d09b2e834b9d94fe15308531b8b039446fb33a",null,null,"lmarena-ai/leaderboard-dataset (source-native ranking evidence).","metadata-only","verified-primary",null,null,null],["production::cybench-official","cybench-official","Unguided % Solved","Cybench official leaderboard","Cybench authors","https://cybench.github.io/","official-leaderboard","official-leaderboard","source-checked","Unguided % Solved","2026-07-14",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::videommmu-official","videommmu-official","video multimodal understanding benchmark definition","Video-MMMU project site","Video-MMMU","https://videommmu.github.io/","official-leaderboard","official-leaderboard","source-checked","video multimodal understanding benchmark definition",null,null,"2026-07-21",null,null,null,null,null,"source-checked",null,null,null],["production::webvoyager-source","webvoyager-source","WebVoyager success","WebVoyager benchmark","WebVoyager authors","https://github.com/MinorJerry/WebVoyager","official-docs","official-docs","source-checked","WebVoyager success",null,null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-tau2-bench","aa-tau2-bench","τ² success rate","τ²-Bench Telecom Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/tau2-bench","independent-lab","independent-lab","source-checked","τ² success rate","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null],["production::aa-tau3-banking","aa-tau3-banking","τ³-Banking success rate","τ³-Banking Leaderboard","Artificial Analysis","https://artificialanalysis.ai/evaluations/tau3-banking","independent-lab","independent-lab","source-checked","τ³-Banking success rate","2026-07-15",null,"2026-07-15",null,null,null,null,null,"source-checked",null,null,null]],"stableKey":"sourceKey","table":"sources"}