This record is outside your history allowance. Register for 30 days or choose Plus for all available history.
Sign in / Register · PlusSummary
New hands-on experience for Arena with multiple new models (Claude Fable 5.1, Claude Opus 5, GPT-6 Sol, GPT-6-Astra, Kimi K3, Qwen 3.8 27B), as well as Agent Leaderboard improvements and the academic partner program, and the deletion of scores for some older models to indicate that the leaderboard content has been updated.
LLM generationLLM The summary is machine-generated; please refer to the original text for important information.
Permanent link
https://daily.maas.click/item/obs_ab63f3bd3272dbe41bcefd3601409eed7e015742f17dd06d0d2c32e84974e410/Source page
https://lmarena.ai/leaderboard ↗This link points to the source's official page (not content on this site).