Model rankings
215 models · 2 boards · 2 sources
Week of February 17, 2025
Smartest
Best open model
Best from China
Top three open models
DeepSeek R1DeepSeek · #3 overall60.2
DeepSeek V3DeepSeek · #6 overall45.7
QwQ 32B-PreviewAlibaba · #11 overall42.6
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | o3-miniClosedOpenAI | 62.9 | — | — | — |
| 2 | — | o1ClosedOpenAI | 61.9 | — | — | — |
| 3 | — | DeepSeek R1OpenDeepSeek | 60.2 | — | — | — |
| 4 | — | o1-miniClosedOpenAI | 53.8 | — | — | — |
| 5 | — | Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 46.5 | — | — | — |
| 6 | — | DeepSeek V3OpenDeepSeek | 45.7 | — | — | — |
| 7 | — | Qwen2.5 MaxClosedAlibaba | 45.3 | — | — | — |
| 8 | — | Gemini 1.5 Pro (Sep '24)ClosedGoogle | 44.6 | — | — | — |
| 9 | — | Claude 3.5 Sonnet (Oct '24)ClosedAnthropic | 44.3 | — | — | — |
| 10 | — | Gemini 2.0 Flash (Feb '25)ClosedGoogle | 44.2 | — | — | — |
| 11 | — | QwQ 32B-PreviewOpenAlibaba | 42.6 | — | — | — |
| 12 | — | Gemini 2.0 Flash-Lite (Preview)ClosedGoogle | 41.9 | — | — | — |
| 13 | — | GPT-4o (Nov '24)ClosedOpenAI | 41.5 | — | — | — |
| 14 | — | Llama 3.3 Instruct 70BOpenMeta | 41.1 | — | — | — |
| 15 | — | GPT-4o (Aug '24)ClosedOpenAI | 40.9 | — | — | — |
| 16 | — | GPT-4o (May '24)ClosedOpenAI | 40.9 | — | — | — |
| 17 | — | Llama 3.1 Instruct 405BOpenMeta | 40.5 | — | — | — |
| 18 | — | MiniMax-Text-01OpenMiniMax | 39.9 | — | — | — |
| 19 | — | Mistral Large 2 (Nov '24)OpenMistral | 38.3 | — | — | — |
| 20 | — | Pixtral LargeOpenMistral | 37.4 | — | — | — |
| 21 | — | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 37.3 | — | — | — |
| 22 | — | Nova ProClosedAmazon | 37.1 | — | — | — |
| 23 | — | Mistral Large 2 (Jul '24)OpenMistral | 36.6 | — | — | — |
| 24 | — | Qwen2.5 Coder Instruct 32BOpenAlibaba | 36.3 | — | — | — |
| 25 | — | GPT-4o miniClosedOpenAI | 35.7 | — | — | — |
| 26 | — | Llama 3.1 Instruct 70BOpenMeta | 35.4 | — | — | — |
| 27 | — | Mistral Small 3OpenMistral | 35.3 | — | — | — |
| 28 | — | Claude 3 OpusClosedAnthropic | 35.1 | — | — | — |
| 29 | — | Claude 3.5 HaikuClosedAnthropic | 34.6 | — | — | — |
| 30 | — | Qwen TurboClosedAlibaba | 33.6 | — | — | — |
| 31 | — | Jamba 1.5 LargeOpenAI21 Labs | 29.3 | — | — | — |
| 32 | — | Nova MicroClosedAmazon | 28.3 | — | — | — |
| 33 | — | Yi-LargeClosed01.AI | 27.9 | — | — | — |
| 34 | — | Llama 3 Instruct 70BOpenMeta | 27.5 | — | — | — |
| 35 | — | Mistral Small (Sep '24)OpenMistral | 27.4 | — | — | — |
| 36 | — | Llama 3.1 Instruct 8BOpenMeta | 23.7 | — | — | — |
| 37 | — | Ministral 8BOpenMistral | 22.3 | — | — | — |
| 38 | — | Llama 3.2 Instruct 11B (Vision)OpenMeta | 22.2 | — | — | — |
| 39 | — | Command-R+ (Aug '24)OpenCohere | 21.5 | — | — | — |
| 40 | — | Ministral 3BClosedMistral | 19.6 | — | — | — |
| 41 | — | Command-R (Mar '24)OpenCohere | 14.7 | — | — | — |
| 42 | — | Codestral-MambaOpenMistral | 13.9 | — | — | — |
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