Summary: LMArena launches multi-modal leaderboard categories

Why It Matters: The platform has moved beyond simple text comparisons. It now ranks how AI models perform in specific tasks like coding, video generation, and image editing. This gives users a much more detailed way to see which models are actually best for different types of work.

What Changed:

• Added new leaderboard tabs for WebDev, Vision, Text-to-Image, and Image Edit.
• Introduced rankings for Search, Text-to-Video, and Image-to-Video.
• Updated the main leaderboard with new models including Gemini 3 Pro, Grok 4.1, and GPT-5.1.
• Added a detailed "Arena Overview" table that ranks models by specific skills like Math, Creative Writing, and Coding.
• Expanded the sidebar navigation to include all new category types.