LMArena Elo
18 models ranked
LMArena (formerly LMSYS Chatbot Arena) is the largest human-preference leaderboard in AI. Blind side-by-side battles between models are voted on by millions of real users, and the results feed a Bradley-Terry Elo rating — the same system chess players know. It captures what people actually prefer to talk to, which no automated benchmark can fully replicate.
Scores from LMArena
| # | Model | ||
|---|---|---|---|
| 1 | GPT-5 | OpenAI | 100 |
| 2 | Claude 4 Opus | Anthropic | 100 |
| 3 | Gemini 2.5 Pro | 99 | |
| 4 | Cursor Tab | Anysphere | 98 |
| 5 | Llama 4 405B | Meta | 97 |
| 6 | Claude Code | Anthropic | 97 |
| 7 | Grok 3 | xAI | 96 |
| 8 | Qwen3 235B | Alibaba | 95 |
| 9 | DeepSeek V3 | DeepSeek | 94 |
| 10 | GitHub Copilot | GitHub | 94 |
| 11 | Mistral Large 3 | Mistral | 93 |
| 12 | Claude 4 Sonnet | Anthropic | 92 |
| 13 | Aider | Aider | 91 |
| 14 | Command R+ | Cohere | 90 |
| 15 | Codeium Windsurf | Codeium | 90 |
| 16 | Gemini 2.5 Flash | 89 | |
| 17 | GPT-4o mini | OpenAI | 87 |
| 18 | Continue Dev | Continue | 86 |
AIRank aggregates these results from the public sources listed on each page. We do not run our own evaluations, and we normalize raw results to a 0–100 scale so tables are comparable.
FAQ
Frequently asked questions
What is LMArena Elo?
LMArena (formerly LMSYS Chatbot Arena) is the largest human-preference leaderboard in AI. Blind side-by-side battles between models are voted on by millions of real users, and the results feed a Bradley-Terry Elo rating — the same system chess players know. It captures what people actually prefer to talk to, which no automated benchmark can fully replicate. The LMArena Elo results shown here come from the public scores published by the benchmark’s own team and re-aggregated through sources such as LMArena.
How are benchmark scores computed?
Each benchmark reports its results on its own native scale — percentages, pass@1 rates or Elo points. We normalize every benchmark to a shared 0–100 scale using min-max scaling over the models we track, so tables are comparable across benchmarks. The underlying numbers always come from the public results published by the benchmark maintainers, never from proprietary or self-run evaluations.
Why do the same models rank differently across benchmarks?
Benchmarks measure different skills. GPQA tests graduate-level science knowledge, HumanEval and SWE-Bench measure coding ability, and MATH covers step-by-step problem solving. A model can be excellent at code and average at science — that is exactly why we keep a separate leaderboard for each benchmark instead of merging everything into one score.