Chatbot Arena (LMArena) chatbot-arena Leaderboard
Crowdsourced head-to-head LLM comparison - Elo rating from human preference votes · Metric: Elo (higher is better) · 🟢 Updated 17h ago
| # | Model | Elo | Paper |
|---|---|---|---|
| 1 | gpt-5.5 | 1542.64 | — |
| 2 | qwen3.5-max-preview | 1537.31 | — |
| 3 | claude-opus-4-6 | 1535.88 | — |
| 4 | claude-opus-4-6-thinking | 1533.76 | — |
| 5 | gemini-3.5-flash-medium | 1533.14 | — |
| 6 | gpt-5.5-high | 1532.12 | — |
| 7 | kimi-k2.6 | 1531.39 | — |
| 8 | gemini-3-pro | 1528.50 | — |
| 9 | gemini-3.1-pro-preview | 1528.17 | — |
| 10 | qwen3.7-max-preview | 1526.07 | — |
| 11 | gpt-5.6-sol-xhigh | 1525.06 | — |
| 12 | claude-opus-4-7-thinking | 1519.32 | — |
| 13 | gpt-5.4-high | 1518.39 | — |
| 14 | muse-spark-1.1 | 1518.23 | — |
| 15 | glm-5.1 | 1517.72 | — |
| 16 | glm-5 | 1517.56 | — |
| 17 | claude-fable-5 | 1517.35 | — |
| 18 | claude-opus-4-7 | 1516.42 | — |
| 19 | gemini-3.5-flash-high | 1516.37 | — |
| 20 | grok-4.5 | 1515.51 | — |
| 21 | gemini-3-flash | 1513.00 | — |
| 22 | glm-5.2 (max) | 1512.50 | — |
| 23 | qwen3.7-plus | 1510.50 | — |
| 24 | gpt-5.4 | 1508.80 | — |
| 25 | gemini-2.5-pro | 1506.18 | — |
| 26 | Claude Opus 4.7 | 1395.00 | — |
| 27 | GPT-5 | 1382.00 | — |
| 28 | Claude Sonnet 4.6 | 1378.00 | — |
| 29 | Gemini 2.5 Pro | 1370.00 | — |
| 30 | GPT-4o (2024-11-20) | 1340.00 | — |
| 31 | DeepSeek-V3 | 1330.00 | link |
| 32 | Claude Haiku 4.5 | 1310.00 | — |
| 33 | Qwen 2.5 Max | 1290.00 | — |
| 34 | Claude 3.5 Sonnet | 1280.00 | — |
| 35 | Llama 4 405B Instruct | 1280.00 | — |
| 36 | Gemini 1.5 Pro (2024-02) | 1275.00 | — |
| 37 | Llama 3 70B Instruct | 1208.00 | link |
| 38 | Mixtral 8x22B Instruct | 1148.00 | — |
| 39 | Chatbot Arena (introducing) | 0.00 | link |