Model rankings
315 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)Google67.8
o3OpenAI66.8
Top three open models
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA · #7 overall60.8
DeepSeek R1DeepSeek · #9 overall60.2
QwQ 32BAlibaba · #10 overall58.1
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | o4-mini (high)ClosedOpenAI | 69.8 | — | — | — |
| 2 | — | Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle | 67.8 | — | — | — |
| 3 | — | o3ClosedOpenAI | 66.8 | — | — | — |
| 4 | — | Grok 3 mini Reasoning (high)ClosedxAI | 66.7 | — | — | — |
| 5 | — | o3-mini (high)ClosedOpenAI · 1 more variant | 65.5 | — | — | — |
| 6 | — | o1ClosedOpenAI | 61.9 | — | — | — |
| 7 | — | Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle | 60.5 | — | — | — |
| 8 | — | Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant | 57.4 | — | — | — |
| 9 | — | o1-miniClosedOpenAI | 53.8 | — | — | — |
| 10 | — | GPT-4.1 miniClosedOpenAI | 52.9 | — | — | — |
| 11 | — | GPT-4.1ClosedOpenAI | 52.6 | — | — | — |
| 12 | — | Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle | 52.3 | — | — | — |
| 13 | — | Grok 3ClosedxAI | 50.6 | — | — | — |
| 14 | — | GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 2 more variants | 50.3 | — | — | — |
| 15 | — | Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 49.2 | — | — | — |
| 16 | — | Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant | 48.1 | — | — | — |
| 17 | — | Qwen2.5 MaxClosedAlibaba | 45.3 | — | — | — |
| 18 | — | Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant | 44.6 | — | — | — |
| 19 | — | Claude 3.5 Sonnet (Oct '24)ClosedAnthropic | 44.4 | — | — | — |
| 20 | — | SonarClosedPerplexity | 43.4 | — | — | — |
| 21 | — | Sonar ProClosedPerplexity | 42.7 | — | — | — |
| 22 | — | Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle | 41.4 | — | — | — |
| 23 | — | GPT-4.1 nanoClosedOpenAI | 41.0 | — | — | — |
| 24 | — | Grok 2 (Dec '24)ClosedxAI | 39.2 | — | — | — |
| 25 | — | Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant | 39.0 | — | — | — |
| 26 | — | Grok BetaClosedxAI | 37.5 | — | — | — |
| 27 | — | Nova ProClosedAmazon | 37.1 | — | — | — |
| 28 | — | GPT-4o miniClosedOpenAI | 35.7 | — | — | — |
| 29 | — | Claude 3 OpusClosedAnthropic | 35.1 | — | — | — |
| 30 | — | Claude 3.5 HaikuClosedAnthropic | 34.7 | — | — | — |
| 31 | — | Qwen TurboClosedAlibaba | 33.6 | — | — | — |
| 32 | — | Nova LiteClosedAmazon | 32.5 | — | — | — |
| 33 | — | Gemini 1.5 Flash-8BClosedGoogle | 30.8 | — | — | — |
| 34 | — | Nova MicroClosedAmazon | 28.3 | — | — | — |
| 35 | — | Yi-LargeClosed01.AI | 27.9 | — | — | — |
| 36 | — | Claude 3 SonnetClosedAnthropic | 27.8 | — | — | — |
| 37 | — | Codestral (Jan '25)ClosedMistral | 27.6 | — | — | — |
| 38 | — | Mistral Large (Feb '24)ClosedMistral | 26.4 | — | — | — |
| 39 | — | Claude 2.1ClosedAnthropic | 24.1 | — | — | — |
| 40 | — | Mistral Small (Feb '24)ClosedMistral | 22.9 | — | — | — |
| 41 | — | Mistral MediumClosedMistral | 22.8 | — | — | — |
| 42 | — | LFM 40BClosedLiquid AI | 21.7 | — | — | — |
| 43 | — | Gemini 1.0 ProClosedGoogle | 20.6 | — | — | — |
| 44 | — | Ministral 3BClosedMistral | 19.6 | — | — | — |
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