Model rankings
291 models · 2 boards · 2 sources
Smartest
Best open model
Best from China
Top three by Intelligence
Gemini 2.5 Pro Experimental (Mar' 25)Google68.3
o3-mini (high)OpenAI65.5
o1OpenAI61.9
Top three open models
DeepSeek R1DeepSeek · #4 overall60.2
QwQ 32BAlibaba · #5 overall58.1
DeepSeek V3 0324 (Mar' 25)DeepSeek · #8 overall53.2
This week's changes
Gemini 2.5 Pro Experimental (Mar' 25)Intelligence · #1New
Gemini 2.0 Flash Thinking Experimental (Jan '25)Intelligence · #9New
GPT-4o (March 2025, chatgpt-4o-latest)Intelligence · #11Up 9
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | DeepSeek R1OpenDeepSeek | 60.2 | — | — | — |
| 2 | — | QwQ 32BOpenAlibaba | 58.1 | — | — | — |
| 3 | ▲ 1 | DeepSeek V3 0324 (Mar' 25)OpenDeepSeek · 1 more variant | 53.2 | — | — | — |
| 4 | ▼ 1 | DeepSeek R1 Distill Qwen 32BOpenDeepSeek | 51.9 | — | — | — |
| 5 | — | DeepSeek R1 Distill Qwen 14BOpenDeepSeek | 49.0 | — | — | — |
| 6 | — | DeepSeek R1 Distill Llama 70BOpenDeepSeek | 48.2 | — | — | — |
| 7 | — | Qwen2.5 MaxClosedAlibaba | 45.3 | — | — | — |
| 8 | — | QwQ 32B-PreviewOpenAlibaba | 42.6 | — | — | — |
| 9 | — | Qwen2.5 Instruct 72BOpenAlibaba | 40.4 | — | — | — |
| 10 | — | MiniMax-Text-01OpenMiniMax | 40.2 | — | — | — |
| 11 | — | Qwen2.5 Instruct 32BOpenAlibaba | 37.4 | — | — | — |
| 12 | — | Qwen2.5 Coder Instruct 32BOpenAlibaba | 36.3 | — | — | — |
| 13 | — | DeepSeek R1 Distill Llama 8BOpenDeepSeek | 34.0 | — | — | — |
| 14 | — | Qwen TurboClosedAlibaba | 33.6 | — | — | — |
| 15 | — | Qwen2 Instruct 72BOpenAlibaba | 32.6 | — | — | — |
| 16 | — | Yi-LargeClosed01.AI | 27.9 | — | — | — |
| 17 | — | Qwen2.5 Coder Instruct 7BOpenAlibaba | 26.7 | — | — | — |
| 18 | — | DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek | 19.2 | — | — | — |
Intelligence over time
Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi