LLM Leaderboard
Ranked by LMSYS Chatbot Arena ELO and performance indicators.
Model Leaderboard
Rankings based on Chatbot Arena ELO scores. Click column headers to sort. Data reflects latest benchmark results.
| # | Model | Provider | Arena Score |
|---|---|---|---|
| 1 | Claude 4 OpusTOP 3 | Anthropic | 1389 |
| 2 | GPT-5TOP 3 | OpenAI | 1381 |
| 3 | Gemini 2.5 ProTOP 3 | 1375 | |
| 4 | DeepSeek R1 | DeepSeek | 1362 |
| 5 | Llama 4 Maverick | Meta | 1348 |
| 6 | Grok 3 | xAI | 1341 |
| 7 | Mistral Large 3 | Mistral AI | 1329 |
| 8 | Qwen 3 235B | Alibaba | 1318 |
| 9 | Claude 3.5 Sonnet | Anthropic | 1305 |
| 10 | Phi-4 | Microsoft | 1278 |
Source: LMSYS Chatbot Arena • Updated dynamically • Scores are approximate