Model rankings
288 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
Llama 3.3 Nemotron Super 49B v1Intelligence · #29New
Grok 2 (Dec '24)Intelligence · #30New
Mistral Small 3.1Intelligence · #41New
Gemini 1.5 Flash-8BIntelligence · #50New
Gemma 2 9BIntelligence · #71New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | o3-mini (high)ClosedOpenAI · 1 more variant | 65.5 | — | — | — |
| 2 | — | o1ClosedOpenAI | 61.9 | — | — | — |
| 3 | — | Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant | 57.4 | — | — | — |
| 4 | — | o1-miniClosedOpenAI | 53.8 | — | — | — |
| 5 | — | Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 49.2 | — | — | — |
| 6 | — | Gemini 2.0 Flash (Feb '25)ClosedGoogle | 48.1 | — | — | — |
| 7 | — | Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant | 44.6 | — | — | — |
| 8 | — | Claude 3.5 Sonnet (Oct '24)ClosedAnthropic | 44.4 | — | — | — |
| 9 | — | SonarClosedPerplexity | 43.4 | — | — | — |
| 10 | — | Sonar ProClosedPerplexity | 42.7 | — | — | — |
| 11 | ▲ 1 | GPT-4o (Nov '24)ClosedOpenAI · 1 more variant | 41.5 | — | — | — |
| 12 | ▼ 1 | Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle | 41.4 | — | — | — |
| 13 | — | Llama 3.3 Instruct 70BOpenMeta | 41.1 | — | — | — |
| 14 | — | Llama 3.1 Instruct 405BOpenMeta | 40.5 | — | — | — |
| 15 | — | Phi-4OpenMicrosoft Azure | 40.2 | — | — | — |
| 16 | New | Llama 3.3 Nemotron Super 49B v1OpenNVIDIA | 39.3 | — | — | — |
| 17 | New | Grok 2 (Dec '24)ClosedxAI | 39.2 | — | — | — |
| 18 | ▼ 2 | Gemma 3 27B InstructOpenGoogle | 37.6 | — | — | — |
| 19 | ▼ 2 | Grok BetaClosedxAI | 37.5 | — | — | — |
| 20 | ▼ 2 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 37.3 | — | — | — |
| 21 | ▼ 2 | Nova ProClosedAmazon | 37.1 | — | — | — |
| 22 | ▼ 2 | GPT-4o miniClosedOpenAI | 35.7 | — | — | — |
| 23 | ▼ 2 | Llama 3.1 Instruct 70BOpenMeta | 35.4 | — | — | — |
| 24 | ▼ 2 | Claude 3 OpusClosedAnthropic | 35.1 | — | — | — |
| 25 | ▼ 2 | Claude 3.5 HaikuClosedAnthropic | 34.7 | — | — | — |
| 26 | ▼ 2 | Llama 3.2 Instruct 90B (Vision)OpenMeta | 33.4 | — | — | — |
| 27 | ▼ 2 | Nova LiteClosedAmazon | 32.5 | — | — | — |
| 28 | New | Gemini 1.5 Flash-8BClosedGoogle | 30.8 | — | — | — |
| 29 | ▼ 3 | Gemini 1.5 Flash (May '24)ClosedGoogle | 28.5 | — | — | — |
| 30 | ▼ 3 | Nova MicroClosedAmazon | 28.3 | — | — | — |
| 31 | ▼ 3 | Claude 3 SonnetClosedAnthropic | 27.8 | — | — | — |
| 32 | ▼ 3 | Llama 3 Instruct 70BOpenMeta | 27.5 | — | — | — |
| 33 | — | Phi-4 Multimodal InstructOpenMicrosoft Azure | 26.9 | — | — | — |
| 34 | — | Phi-4 Mini InstructOpenMicrosoft Azure | 26.0 | — | — | — |
| 35 | ▼ 5 | Phi-3 Medium Instruct 14BOpenMicrosoft Azure | 24.5 | — | — | — |
| 36 | ▼ 5 | Claude 2.1ClosedAnthropic | 24.1 | — | — | — |
| 37 | ▼ 5 | Llama 3.1 Instruct 8BOpenMeta | 23.7 | — | — | — |
| 38 | New | Gemma 2 9BOpenGoogle | 22.2 | — | — | — |
| 39 | New | Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 22.1 | — | — | — |
| 40 | ▼ 3 | LFM 40BClosedLiquid AI | 21.7 | — | — | — |
| 41 | ▼ 5 | Llama 3 Instruct 8BOpenMeta | 21.5 | — | — | — |
| 42 | New | Gemini 1.0 ProClosedGoogle | 20.6 | — | — | — |
| 43 | New | Llama 2 Chat 13BOpenMeta | 19.9 | — | — | — |
| 44 | ▼ 6 | DBRX InstructOpenDatabricks | 19.8 | — | — | — |
| 45 | ▼ 6 | Llama 3.2 Instruct 3BOpenMeta | 19.5 | — | — | — |
| 46 | ▼ 6 | Llama 3.2 Instruct 1BOpenMeta | 9.7 | — | — | — |
| 47 | ▼ 6 | 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