Model rankings
347 models · 2 boards · 2 sources
Smartest
Best open model
Best from China
Top three by Intelligence
o4-mini (high)OpenAI69.8
Gemini 2.5 Pro Preview (Mar' 25)Google68.9
o3OpenAI66.8
Top three open models
Qwen3 235B A22B (Reasoning)Alibaba · #6 overall62.3
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA · #8 overall60.8
DeepSeek R1DeepSeek · #10 overall60.2
This week's changes
Qwen2.5 TurboIntelligence · #70New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 60.8 | — | — | — |
| 2 | — | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 51.2 | — | — | — |
| 3 | — | Llama 4 MaverickOpenMeta | 50.5 | — | — | — |
| 4 | — | Llama 4 ScoutOpenMeta | 43.0 | — | — | — |
| 5 | — | Llama 3.3 Instruct 70BOpenMeta | 41.1 | — | — | — |
| 6 | — | Llama 3.1 Instruct 405BOpenMeta | 40.5 | — | — | — |
| 7 | — | Phi-4OpenMicrosoft Azure | 40.2 | — | — | — |
| 8 | — | Gemma 3 27B InstructOpenGoogle | 37.6 | — | — | — |
| 9 | — | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 37.3 | — | — | — |
| 10 | — | Llama 3.1 Instruct 70BOpenMeta | 35.4 | — | — | — |
| 11 | — | Gemma 3 12B InstructOpenGoogle | 33.8 | — | — | — |
| 12 | — | Llama 3.2 Instruct 90B (Vision)OpenMeta | 33.4 | — | — | — |
| 13 | — | Llama 3 Instruct 70BOpenMeta | 27.5 | — | — | — |
| 14 | — | Phi-4 Multimodal InstructOpenMicrosoft Azure | 26.9 | — | — | — |
| 15 | — | Phi-4 Mini InstructOpenMicrosoft Azure | 26.0 | — | — | — |
| 16 | — | Phi-3 Medium Instruct 14BOpenMicrosoft Azure | 24.5 | — | — | — |
| 17 | — | Gemma 3 4B InstructOpenGoogle | 24.5 | — | — | — |
| 18 | — | Llama 3.1 Instruct 8BOpenMeta | 23.7 | — | — | — |
| 19 | — | Gemma 2 9BOpenGoogle | 22.2 | — | — | — |
| 20 | — | Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 22.1 | — | — | — |
| 21 | — | Llama 3 Instruct 8BOpenMeta | 21.5 | — | — | — |
| 22 | — | Llama 2 Chat 13BOpenMeta | 19.9 | — | — | — |
| 23 | — | DBRX InstructOpenDatabricks | 19.8 | — | — | — |
| 24 | — | Llama 3.2 Instruct 3BOpenMeta | 19.5 | — | — | — |
| 25 | — | Llama 3.2 Instruct 1BOpenMeta | 9.7 | — | — | — |
| 26 | — | 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