Summary:
Arena Leaderboard adds video and image benchmarks
Why It Matters:
The platform is expanding beyond text and code to rank how well AI models handle visual media like video generation and image editing.
What Changed:
- Changed the page title to "Arena Leaderboard | Compare & Benchmark the Best Frontier AI Models."
- Added a new navigation menu for specific model categories.
- Launched new leaderboard sections for Text-to-Video and Image-to-Video.
- Added ranking categories for Document analysis, Text-to-Image, and Image Editing.
- Updated the main ranking table with new performance metrics like "Longer Query" and "Hard Prompts."
- Listed several unreleased or future model versions in the rankings (e.g., GPT-5.2, Claude 4.6).