Summary: LMArena adds multimodal leaderboards and GPT-5.1

Why It Matters: The platform has expanded from simple text comparisons to ranking AI models across video, image editing, and search. It also reveals the first public rankings for unreleased or new models like GPT-5.1 and Gemini 3.

What Changed:

• Added new specialized leaderboards for WebDev, Vision, Text-to-Image, Image Edit, Search, Text-to-Video, and Image-to-Video.
• Updated the rankings to include new model versions such as gemini-3-pro, grok-4.1, and gpt-5.1-high.
• Introduced a "Leaderboard Overview" page that provides a snapshot of all different AI categories in one place.
• Added a "Compact View" and detailed category rankings for specific skills like Coding, Math, and Creative Writing.