LMArena

Test large language models (LLMs) by comparing their performance in real-time, side-by-side. Chat, compare, vote for the world's best AI models. Join the community shaping the public leaderboard for LLMs, image, and code models through real-world evaluation. LMArena is a platform for blind comparisons of AI models, where users vote on responses to build Elo-ranked leaderboards across tasks like text and coding. Users submit prompts, receive two anonymous responses, and vote for the better one, tie, or skip, with votes updating model scores via Elo ratings in real time. It hosts over 400 models from providers like OpenAI (GPT-5), Anthropic (Claude Sonnet 4.5), Google (Gemini 2.5), Meta, and Qwen. Core features including battles and leaderboards are free, with optional premium tiers for faster access during high traffic. Rankings derive from millions of user votes, providing human-preference insights, though they may reflect biases toward popular or polished models. Users create any prompt for battles, from simple queries to complex multi-turn workflows, tailoring evals to specific needs.