Model rankings
532 models · 3 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three open models
gpt-oss-120BOpenAI · #9 overall57.9
Qwen3 235B A22B 2507 (Reasoning)Alibaba · #10 overall57.5
Qwen3 Next 80B A3B (Reasoning)Alibaba · #13 overall54.3
This week's changes
Qwen3 Next 80B A3B (Reasoning)Intelligence · #13New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | GPT-5 (high)ClosedOpenAI | 66.7 | $3.4 | — | — |
| 2 | — | GPT-5 (medium)ClosedOpenAI | 66.3 | $3.4 | — | — |
| 3 | — | Grok 4ClosedxAI | 65.3 | $6.0 | — | — |
| 4 | — | o3-proClosedOpenAI | 65.3 | $35 | — | — |
| 5 | — | o3ClosedOpenAI | 65.2 | $3.5 | — | — |
| 6 | — | GPT-5 mini (high)ClosedOpenAI | 62.3 | $0.69 | — | — |
| 7 | — | GPT-5 (low)ClosedOpenAI | 61.7 | $3.4 | — | — |
| 8 | — | GPT-5 mini (medium)ClosedOpenAI | 60.8 | $0.69 | — | — |
| 9 | — | Gemini 2.5 ProClosedGoogle | 59.6 | $3.4 | — | — |
| 10 | — | Claude 4.1 Opus (Extended Thinking)ClosedAnthropic | 59.3 | $30 | — | — |
| 11 | — | o4-mini (high)ClosedOpenAI | 59.0 | $1.9 | — | — |
| 12 | — | Grok 3 mini Reasoning (high)ClosedxAI | 57.1 | $0.35 | — | — |
| 13 | — | Claude 4 Sonnet (Extended Thinking)ClosedAnthropic | 56.5 | $6.0 | — | — |
| 14 | — | Claude 4 Opus (Extended Thinking)ClosedAnthropic | 54.2 | $30 | — | — |
| 15 | — | Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle | 54.1 | $3.4 | — | — |
| 16 | — | Gemini 2.5 Pro Preview (May' 25)ClosedGoogle | 53.2 | $3.4 | — | — |
| 17 | — | Gemini 2.5 Flash (Reasoning)ClosedGoogle | 51.2 | $0.85 | — | — |
| 18 | — | o3-mini (high)ClosedOpenAI | 50.8 | $1.9 | — | — |
| 19 | — | Grok Code Fast 1ClosedxAI | 48.7 | $0.53 | — | — |
| 20 | — | Qwen3 Max (Preview)ClosedAlibaba | 48.6 | $2.4 | — | — |
| 21 | — | GPT-5 nano (high)ClosedOpenAI | 48.5 | $0.14 | — | — |
| 22 | — | o3-miniClosedOpenAI | 48.1 | $1.9 | — | — |
| 23 | — | o1-proClosedOpenAI | 48.0 | $263 | — | — |
| 24 | — | GPT-5 nano (medium)ClosedOpenAI | 47.7 | $0.14 | — | — |
| 25 | — | o1ClosedOpenAI | 47.2 | $26 | — | — |
| 26 | — | Sonar Reasoning ProClosedPerplexity | 46.3 | $0.000 | — | — |
| 27 | — | Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle | 45.8 | $0.000 | — | — |
| 28 | — | o1-previewClosedOpenAI | 44.9 | $29 | — | — |
| 29 | — | Claude 4.1 OpusClosedAnthropic | 44.6 | $30 | — | — |
| 30 | — | Claude 4 SonnetClosedAnthropic | 44.4 | $6.0 | — | — |
| 31 | — | GPT-5 (minimal)ClosedOpenAI | 43.5 | $3.4 | — | — |
| 32 | — | GPT-4.1ClosedOpenAI | 43.4 | $3.5 | — | — |
| 33 | — | Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic | 42.7 | $6.0 | — | — |
| 34 | — | GPT-4.1 miniClosedOpenAI | 42.5 | $0.70 | — | — |
| 35 | — | Claude 4 OpusClosedAnthropic | 42.3 | $30 | — | — |
| 36 | — | GPT-5 mini (minimal)ClosedOpenAI | 41.6 | $0.69 | — | — |
| 37 | — | Grok 3 Reasoning BetaClosedxAI | 41.4 | $0.000 | — | — |
| 38 | — | Gemini 2.5 FlashClosedGoogle | 40.4 | $0.85 | — | — |
| 39 | — | Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle | 40.1 | $0.18 | — | — |
| 40 | — | o1-miniClosedOpenAI | 39.2 | $1.9 | — | — |
| 41 | — | GPT-4.5 (Preview)ClosedOpenAI | 38.4 | $0.000 | — | — |
| 42 | — | Solar Pro 2 (Reasoning)ClosedUpstage | 37.7 | $0.50 | — | — |
| 43 | — | Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle | 37.7 | $0.000 | — | — |
| 44 | — | Solar Pro 2 (Preview) (Reasoning)ClosedUpstage | 36.1 | $0.000 | — | — |
| 45 | — | Grok 3ClosedxAI | 36.0 | $6.0 | — | — |
| 46 | — | GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI | 35.6 | $7.5 | — | — |
| 47 | — | Mistral Medium 3.1ClosedMistral | 35.4 | $0.80 | — | — |
| 48 | — | Mistral Medium 3ClosedMistral | 34.7 | $0.80 | — | — |
| 49 | — | Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 34.6 | $0.000 | — | — |
| 50 | — | Sonar ReasoningClosedPerplexity | 34.2 | $2.0 | — | — |
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