Summary: LMSYS Arena adds video and image generation leaderboards

Why It Matters: The platform is expanding beyond text to rank how AI models handle visual media like video and images. This gives users a central place to see which models are currently winning in the "frontier" AI space across all formats.

What Changed:

• Added new leaderboard categories for Text-to-Image, Image Edit, Text-to-Video, and Image-to-Video.
• Updated the site title to include "Frontier AI Models."
• Introduced a "Leaderboard Overview" page that shows snapshots of model performance across text, vision, and code.
• Added detailed ranking tables for new models including Claude 4.6, Gemini 3.1, and Grok 4.1.
• Updated navigation to include specific tabs for different model capabilities.