Summary: LMArena launches multi-modal AI leaderboards

Why It Matters: The platform has expanded from simple text comparisons to ranking how AI models perform across images, video, coding, and web development.

What Changed:

• Added new leaderboard categories for WebDev, Vision, Text-to-Image, and Image Edit.
• Added new leaderboard categories for Search, Text-to-Video, and Image-to-Video.
• Updated the rankings to include unreleased or "frontier" models like Gemini 3, GPT-5.1, and Grok 4.1.
• Introduced a detailed "Arena Overview" table that ranks models by specific skills like Math, Coding, and Creative Writing.
• Added a "Follow us" call to action for frontier AI news.