About LMArena

Created by researchers from UC Berkeley, LMArena is an open platform to evaluate, benchmark, compare, and test frontier AI models. Users can chat with multiple models and compare their responses across tasks. By seeing models side by side and voting on the better response, the community shapes a public leaderboard that reflects real world performance.

The LMArena blog houses all community and product updates, as well as research and insights from community-driven model evaluation data and leaderboards.

Our Mission

To bring the best AI models to everyone, and to improve them through real-world community evaluations.

Our Vision

Create an open space to try all the best AIs and shape their future through collective feedback.

Join The Community

Discord: https://discord.gg/LMArena
X/Twitter: https://x.com/arena