{"schemaVersion":1,"checkedAt":"2026-11-05T06:35:30.773Z","boards":[{"id":"arena-text","title":"Text","category":"Language models","metric":"Arena score","models":419,"publishedAt":"2026-10-28","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-text-style-control","title":"Text · style controlled","category":"Language models","metric":"Arena score","models":419,"publishedAt":"2026-10-28","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-text-factuality","title":"Text · factuality","category":"Language models","metric":"Arena score","models":188,"publishedAt":"2026-10-28","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-webdev","title":"Web development","category":"Coding and agents","metric":"Arena score","models":150,"publishedAt":"2026-10-28","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-agent","title":"Agent Arena","category":"Coding and agents","metric":"IPS score","models":58,"publishedAt":"2026-11-04","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-agent-bash-reliability","title":"Agents · bash reliability","category":"Coding and agents","metric":"IPS score","models":58,"publishedAt":"2026-11-04","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-agent-bash-recovery-steps","title":"Agents · bash recovery (historical)","category":"Coding and agents","metric":"IPS score","models":52,"publishedAt":"2026-10-08","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-agent-praise-complaint","title":"Agents · praise and complaints","category":"Coding and agents","metric":"IPS score","models":58,"publishedAt":"2026-11-04","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-agent-steerability","title":"Agents · steerability","category":"Coding and agents","metric":"IPS score","models":58,"publishedAt":"2026-11-04","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-agent-task-outcome-explicit","title":"Agents · explicit task outcomes","category":"Coding and agents","metric":"IPS score","models":58,"publishedAt":"2026-11-04","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-agent-tool-hallucination","title":"Agents · tool hallucination signal","category":"Coding and agents","metric":"IPS score","models":58,"publishedAt":"2026-11-04","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-search","title":"Search","category":"Search and documents","metric":"Arena score","models":42,"publishedAt":"2026-10-13","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-search-style-control","title":"Search · style controlled","category":"Search and documents","metric":"Arena score","models":42,"publishedAt":"2026-10-13","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-search-factuality","title":"Search · factuality","category":"Search and documents","metric":"Arena score","models":40,"publishedAt":"2026-10-13","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-document","title":"Documents","category":"Search and documents","metric":"Arena score","models":44,"publishedAt":"2026-09-13","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-document-style-control","title":"Documents · style controlled","category":"Search and documents","metric":"Arena score","models":44,"publishedAt":"2026-09-13","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-vision","title":"Vision","category":"Vision","metric":"Arena score","models":167,"publishedAt":"2026-10-19","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-vision-style-control","title":"Vision · style controlled","category":"Vision","metric":"Arena score","models":167,"publishedAt":"2026-10-19","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-text-to-image","title":"Text to image","category":"Images","metric":"Arena score","models":84,"publishedAt":"2026-11-04","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-image-edit","title":"Image editing","category":"Images","metric":"Arena score","models":63,"publishedAt":"2026-11-04","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-text-to-video","title":"Text to video","category":"Video","metric":"Arena score","models":48,"publishedAt":"2026-09-22","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-image-to-video","title":"Image to video","category":"Video","metric":"Arena score","models":48,"publishedAt":"2026-09-22","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"arena-video-edit","title":"Video editing","category":"Video","metric":"Arena score","models":10,"publishedAt":"2026-08-27","fetchedAt":"2026-11-05T06:35:05.520Z","publisher":"Arena (lmarena-ai)","status":"fresh"},{"id":"music-vocal","title":"Music · vocals","category":"Music","metric":"Music Arena score","models":9,"publishedAt":"2026-07-31","fetchedAt":"2026-11-05T06:35:06.964Z","publisher":"Carnegie Mellon University · Music Arena","status":"fresh"},{"id":"music-instrumental","title":"Music · instrumental","category":"Music","metric":"Music Arena score","models":15,"publishedAt":"2026-07-31","fetchedAt":"2026-11-05T06:35:06.964Z","publisher":"Carnegie Mellon University · Music Arena","status":"fresh"},{"id":"reranking-computerscience","title":"Reranking · Computer science","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-energy","title":"Reranking · Energy","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-financeen","title":"Reranking · Finance (English documents)","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-financefr","title":"Reranking · Finance (French documents)","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-hr","title":"Reranking · Human resources","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-industrial","title":"Reranking · Industry","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-nuclear","title":"Reranking · Nuclear","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-pharmaceuticals","title":"Reranking · Pharmaceuticals","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-physics","title":"Reranking · Physics","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"},{"id":"reranking-telecom","title":"Reranking · Telecom","category":"Rerankers","metric":"nDCG@10 × 100","models":8,"publishedAt":null,"fetchedAt":"2026-11-05T06:35:30.674Z","publisher":"MTEB / embeddings-benchmark","status":"fresh"}],"comparisons":[{"title":"Language models and task rankings","href":"/","models":434,"asOf":"2026-11-05","description":"Capability, uncertainty, provider offers and workload prices."},{"title":"Image models","href":"/images/","models":90,"asOf":"2026-11-05","description":"Independent scores alongside available prices and their conditions."},{"title":"Video models","href":"/video/","models":61,"asOf":"2026-11-05","description":"Independent scores alongside available prices and their conditions."},{"title":"Embedding models","href":"/embeddings/","models":57,"asOf":"2026-11-05","description":"Independent scores alongside available prices and their conditions."}],"external":[{"id":"speech-recognition","title":"Speech recognition","category":"Speech and audio","href":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","publisher":"Hugging Face Open ASR Leaderboard","metric":"Word error rate; lower is better","note":"Read the current results on the official versioned board. Compare the same language and test sets; these scores are not imported into Undominated."},{"id":"speech-generation","title":"Speech generation","category":"Speech and audio","href":"https://huggingface.co/spaces/hf-audio/open_tts_leaderboard","publisher":"Hugging Face Open TTS Leaderboard","metric":"Speech intelligibility, voice similarity and speed","note":"Read the current results on the official board. These objective metrics measure different properties; they are not a single human preference score. Scores are not imported here."}]}