Model rankings
245 models · 2 boards · 2 sources
Smartest
Best open model
Best from China
Top three open models
DeepSeek R1DeepSeek · #3 overall60.2
DeepSeek R1 Distill Qwen 14BDeepSeek · #5 overall49.6
DeepSeek V3DeepSeek · #8 overall45.7
This week's changes
DeepSeek R1 Distill Qwen 14BIntelligence · #5New
DeepSeek R1 Distill Qwen 32BIntelligence · #10New
DeepSeek R1 Distill Llama 70BIntelligence · #13New
Qwen2.5 Instruct 72BIntelligence · #19New
Phi-4Intelligence · #20New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | DeepSeek R1OpenDeepSeek | 60.2 | — | — | — |
| 2 | New | DeepSeek R1 Distill Qwen 14BOpenDeepSeek | 49.6 | — | — | — |
| 3 | ▼ 1 | DeepSeek V3OpenDeepSeek | 45.7 | — | — | — |
| 4 | New | DeepSeek R1 Distill Qwen 32BOpenDeepSeek | 45.2 | — | — | — |
| 5 | New | DeepSeek R1 Distill Llama 70BOpenDeepSeek | 44.0 | — | — | — |
| 6 | ▼ 3 | QwQ 32B-PreviewOpenAlibaba | 42.6 | — | — | — |
| 7 | ▼ 3 | Llama 3.3 Instruct 70BOpenMeta | 41.1 | — | — | — |
| 8 | ▼ 3 | Llama 3.1 Instruct 405BOpenMeta | 40.5 | — | — | — |
| 9 | New | Qwen2.5 Instruct 72BOpenAlibaba | 40.3 | — | — | — |
| 10 | New | Phi-4OpenMicrosoft Azure | 40.2 | — | — | — |
| 11 | New | Llama 3.1 Tulu3 405BOpenAllen Institute for AI | 39.9 | — | — | — |
| 12 | ▼ 6 | MiniMax-Text-01OpenMiniMax | 39.9 | — | — | — |
| 13 | ▼ 6 | Mistral Large 2 (Nov '24)OpenMistral · 1 more variant | 38.3 | — | — | — |
| 14 | ▼ 6 | Pixtral LargeOpenMistral | 37.4 | — | — | — |
| 15 | New | Qwen2.5 Instruct 32BOpenAlibaba | 37.4 | — | — | — |
| 16 | ▼ 7 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 37.3 | — | — | — |
| 17 | ▼ 7 | Qwen2.5 Coder Instruct 32BOpenAlibaba | 36.3 | — | — | — |
| 18 | New | DeepSeek R1 Distill Llama 8BOpenDeepSeek | 35.4 | — | — | — |
| 19 | ▼ 8 | Llama 3.1 Instruct 70BOpenMeta | 35.4 | — | — | — |
| 20 | ▼ 8 | Mistral Small 3OpenMistral | 35.3 | — | — | — |
| 21 | New | Llama 3.2 Instruct 90B (Vision)OpenMeta | 33.4 | — | — | — |
| 22 | ▼ 9 | Jamba 1.5 LargeOpenAI21 Labs | 29.3 | — | — | — |
| 23 | ▼ 9 | Llama 3 Instruct 70BOpenMeta | 27.5 | — | — | — |
| 24 | ▼ 9 | Mistral Small (Sep '24)OpenMistral | 27.4 | — | — | — |
| 25 | New | Mixtral 8x22B InstructOpenMistral | 26.2 | — | — | — |
| 26 | New | Phi-3 Medium Instruct 14BOpenMicrosoft Azure | 24.5 | — | — | — |
| 27 | ▼ 11 | Llama 3.1 Instruct 8BOpenMeta | 23.7 | — | — | — |
| 28 | New | Pixtral 12B (2409)OpenMistral | 23.4 | — | — | — |
| 29 | ▼ 12 | Ministral 8BOpenMistral | 22.3 | — | — | — |
| 30 | ▼ 12 | Llama 3.2 Instruct 11B (Vision)OpenMeta | 22.2 | — | — | — |
| 31 | ▼ 12 | Command-R+ (Aug '24)OpenCohere · 1 more variant | 21.5 | — | — | — |
| 32 | New | Codestral (May '24)OpenMistral | 20.1 | — | — | — |
| 33 | New | Aya Expanse 32BOpenCohere | 20.1 | — | — | — |
| 34 | New | DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek | 20.0 | — | — | — |
| 35 | New | DBRX InstructOpenDatabricks | 19.8 | — | — | — |
| 36 | New | Mistral NeMoOpenMistral | 19.6 | — | — | — |
| 37 | New | OpenChat 3.5 (1210)OpenOpenChat | 16.3 | — | — | — |
| 38 | ▼ 18 | Codestral-MambaOpenMistral | 13.9 | — | — | — |
| 39 | New | Llama 2 Chat 7BOpenMeta | 8.3 | — | — | — |
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