Model rankings
285 models · 2 boards · 2 sources
Smartest
Best open model
Best from China
Top three open models
DeepSeek R1DeepSeek · #3 overall60.2
QwQ 32BAlibaba · #4 overall58.1
DeepSeek R1 Distill Qwen 32BDeepSeek · #7 overall51.9
This week's changes
QwQ 32BIntelligence · #4New
Reka Flash 3Intelligence · #12New
Command AIntelligence · #26New
Gemma 3 27B InstructIntelligence · #30New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | o3-mini (high)ClosedOpenAI | 65.5 | — | — | — |
| 2 | — | o3-miniClosedOpenAI | 62.9 | — | — | — |
| 3 | — | o1ClosedOpenAI | 61.9 | — | — | — |
| 4 | — | Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic | 57.4 | — | — | — |
| 5 | — | o1-miniClosedOpenAI | 53.8 | — | — | — |
| 6 | — | Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 49.2 | — | — | — |
| 7 | — | Claude 3.7 Sonnet (Standard)ClosedAnthropic | 48.2 | — | — | — |
| 8 | — | Gemini 2.0 Flash (Feb '25)ClosedGoogle | 48.1 | — | — | — |
| 9 | — | Gemini 1.5 Pro (Sep '24)ClosedGoogle | 44.6 | — | — | — |
| 10 | — | Claude 3.5 Sonnet (Oct '24)ClosedAnthropic | 44.3 | — | — | — |
| 11 | — | SonarClosedPerplexity | 44.1 | — | — | — |
| 12 | — | Sonar ProClosedPerplexity | 42.8 | — | — | — |
| 13 | — | Gemini 2.0 Flash-Lite (Preview)ClosedGoogle | 41.9 | — | — | — |
| 14 | — | GPT-4o (Nov '24)ClosedOpenAI | 41.5 | — | — | — |
| 15 | New | Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle | 41.4 | — | — | — |
| 16 | ▼ 1 | Llama 3.3 Instruct 70BOpenMeta | 41.1 | — | — | — |
| 17 | ▼ 1 | GPT-4o (ChatGPT)ClosedOpenAI | 41.1 | — | — | — |
| 18 | ▼ 1 | GPT-4o (Aug '24)ClosedOpenAI | 40.9 | — | — | — |
| 19 | ▼ 1 | GPT-4o (May '24)ClosedOpenAI | 40.9 | — | — | — |
| 20 | ▼ 1 | Llama 3.1 Instruct 405BOpenMeta | 40.5 | — | — | — |
| 21 | ▼ 1 | Phi-4OpenMicrosoft Azure | 40.2 | — | — | — |
| 22 | New | Gemma 3 27B InstructOpenGoogle | 37.6 | — | — | — |
| 23 | ▼ 2 | Grok BetaClosedxAI | 37.5 | — | — | — |
| 24 | ▼ 2 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 37.3 | — | — | — |
| 25 | ▼ 2 | Nova ProClosedAmazon | 37.1 | — | — | — |
| 26 | ▼ 2 | GPT-4o miniClosedOpenAI | 35.7 | — | — | — |
| 27 | ▼ 2 | Llama 3.1 Instruct 70BOpenMeta | 35.4 | — | — | — |
| 28 | ▼ 2 | Claude 3 OpusClosedAnthropic | 35.1 | — | — | — |
| 29 | ▼ 2 | Claude 3.5 HaikuClosedAnthropic | 34.6 | — | — | — |
| 30 | ▼ 2 | Gemini 1.5 Pro (May '24)ClosedGoogle | 33.7 | — | — | — |
| 31 | ▼ 2 | Llama 3.2 Instruct 90B (Vision)OpenMeta | 33.4 | — | — | — |
| 32 | ▼ 2 | Nova LiteClosedAmazon | 32.5 | — | — | — |
| 33 | ▼ 2 | Gemini 1.5 Flash (May '24)ClosedGoogle | 28.4 | — | — | — |
| 34 | ▼ 2 | Nova MicroClosedAmazon | 28.3 | — | — | — |
| 35 | ▼ 2 | Claude 3 SonnetClosedAnthropic | 27.8 | — | — | — |
| 36 | ▼ 2 | Llama 3 Instruct 70BOpenMeta | 27.5 | — | — | — |
| 37 | ▼ 2 | Phi-3 Medium Instruct 14BOpenMicrosoft Azure | 24.5 | — | — | — |
| 38 | ▼ 2 | Claude 2.1ClosedAnthropic | 24.1 | — | — | — |
| 39 | ▼ 2 | Llama 3.1 Instruct 8BOpenMeta | 23.7 | — | — | — |
| 40 | ▼ 2 | Phi-4 Multimodal InstructOpenMicrosoft Azure | 23.0 | — | — | — |
| 41 | ▼ 2 | Phi-4 Mini InstructOpenMicrosoft Azure | 22.8 | — | — | — |
| 42 | ▼ 2 | Llama 3.2 Instruct 11B (Vision)OpenMeta | 22.2 | — | — | — |
| 43 | ▼ 2 | Llama 3 Instruct 8BOpenMeta | 21.5 | — | — | — |
| 44 | ▼ 2 | LFM 40BClosedLiquid AI | 21.0 | — | — | — |
| 45 | ▼ 2 | DBRX InstructOpenDatabricks | 19.8 | — | — | — |
| 46 | ▼ 2 | Llama 3.2 Instruct 3BOpenMeta | 19.5 | — | — | — |
| 47 | ▼ 2 | Llama 3.2 Instruct 1BOpenMeta | 9.7 | — | — | — |
| 48 | ▼ 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