Model rankings
340 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
Qwen3 8B (Reasoning)Intelligence · #22New
Mistral Medium 3Intelligence · #29New
Qwen3 4B (Reasoning)Intelligence · #32New
Qwen3 1.7B (Reasoning)Intelligence · #54New
Qwen3 0.6B (Reasoning)Intelligence · #95New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Qwen3 235B A22B (Reasoning)OpenAlibaba · 1 more variant | 62.3 | — | — | — |
| 2 | — | DeepSeek R1OpenDeepSeek | 60.2 | — | — | — |
| 3 | — | Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant | 59.2 | — | — | — |
| 4 | — | QwQ 32BOpenAlibaba | 58.1 | — | — | — |
| 5 | — | Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant | 55.7 | — | — | — |
| 6 | — | Qwen3 30B A3B (Reasoning)OpenAlibaba · 1 more variant | 55.6 | — | — | — |
| 7 | — | DeepSeek V3 0324 (Mar' 25)OpenDeepSeek · 1 more variant | 53.2 | — | — | — |
| 8 | — | DeepSeek R1 Distill Qwen 32BOpenDeepSeek | 51.9 | — | — | — |
| 9 | New | Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant | 51.4 | — | — | — |
| 10 | ▼ 1 | DeepSeek R1 Distill Qwen 14BOpenDeepSeek | 49.0 | — | — | — |
| 11 | ▼ 1 | DeepSeek R1 Distill Llama 70BOpenDeepSeek | 48.2 | — | — | — |
| 12 | New | Qwen3 4B (Reasoning)OpenAlibaba · 1 more variant | 47.3 | — | — | — |
| 13 | ▼ 2 | Qwen2.5 MaxClosedAlibaba | 45.3 | — | — | — |
| 14 | ▼ 2 | QwQ 32B-PreviewOpenAlibaba | 42.6 | — | — | — |
| 15 | ▼ 2 | Qwen2.5 Instruct 72BOpenAlibaba | 40.4 | — | — | — |
| 16 | ▼ 2 | MiniMax-Text-01OpenMiniMax | 40.2 | — | — | — |
| 17 | New | Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant | 38.2 | — | — | — |
| 18 | ▼ 3 | Qwen2.5 Instruct 32BOpenAlibaba | 37.4 | — | — | — |
| 19 | ▼ 3 | Qwen2.5 Coder Instruct 32BOpenAlibaba | 36.3 | — | — | — |
| 20 | ▼ 3 | DeepSeek R1 Distill Llama 8BOpenDeepSeek | 34.0 | — | — | — |
| 21 | ▼ 3 | Qwen TurboClosedAlibaba | 33.6 | — | — | — |
| 22 | ▼ 3 | Qwen2 Instruct 72BOpenAlibaba | 32.6 | — | — | — |
| 23 | ▼ 3 | Yi-LargeClosed01.AI | 27.9 | — | — | — |
| 24 | ▼ 3 | Qwen2.5 Coder Instruct 7BOpenAlibaba | 26.7 | — | — | — |
| 25 | New | Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant | 23.2 | — | — | — |
| 26 | ▼ 4 | 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