Model rankings
262 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 32BDeepSeek · #6 overall51.0
DeepSeek R1 Distill Qwen 14BDeepSeek · #8 overall49.0
This week's changes
Claude 3.7 Sonnet (Extended Thinking)Intelligence · #4New
Qwen2 Instruct 72BIntelligence · #39New
Claude 3 SonnetIntelligence · #45New
Qwen2.5 Coder Instruct 7BIntelligence · #51New
Claude 2.1Intelligence · #53New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Llama 3.3 Instruct 70BOpenMeta | 41.1 | — | — | — |
| 2 | — | Llama 3.1 Instruct 405BOpenMeta | 40.5 | — | — | — |
| 3 | — | Phi-4OpenMicrosoft Azure | 40.2 | — | — | — |
| 4 | — | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 37.3 | — | — | — |
| 5 | — | Llama 3.1 Instruct 70BOpenMeta | 35.4 | — | — | — |
| 6 | — | Llama 3.2 Instruct 90B (Vision)OpenMeta | 33.4 | — | — | — |
| 7 | — | Llama 3 Instruct 70BOpenMeta | 27.5 | — | — | — |
| 8 | — | Phi-3 Medium Instruct 14BOpenMicrosoft Azure | 24.5 | — | — | — |
| 9 | — | Llama 3.1 Instruct 8BOpenMeta | 23.7 | — | — | — |
| 10 | — | Llama 3.2 Instruct 11B (Vision)OpenMeta | 22.2 | — | — | — |
| 11 | — | DBRX InstructOpenDatabricks | 19.8 | — | — | — |
| 12 | New | Llama 3.2 Instruct 3BOpenMeta | 19.5 | — | — | — |
| 13 | New | Llama 3.2 Instruct 1BOpenMeta | 9.7 | — | — | — |
| 14 | ▼ 2 | 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