Model rankings
716 models · 4 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three open models
gpt-oss-120B (high)OpenAI · #12 overall58.0
DeepSeek V3.1 Terminus (Reasoning)DeepSeek · #13 overall57.7
Qwen3 235B A22B 2507 (Reasoning)Alibaba · #14 overall57.5
This week's changes
Magpie MultilingualSpeech · #17Up 11
Octave 2Speech · #20Up 5
Sonic English (Oct '24)Speech · #21Up 3
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | GPT-5 Codex (high)ClosedOpenAI | 68.5 | $3.4 | — | — |
| 2 | — | GPT-5 (high)ClosedOpenAI | 68.5 | $3.4 | — | — |
| 3 | — | GPT-5 (medium)ClosedOpenAI | 66.4 | $3.4 | — | — |
| 4 | — | o3ClosedOpenAI | 65.5 | $3.5 | — | — |
| 5 | — | Grok 4ClosedxAI | 65.3 | $6.0 | — | — |
| 6 | — | o3-proClosedOpenAI | 65.3 | $35 | — | — |
| 7 | — | GPT-5 mini (high)ClosedOpenAI | 64.3 | $0.69 | — | — |
| 8 | — | Claude 4.5 Sonnet (Reasoning)ClosedAnthropic | 62.7 | $6.0 | — | — |
| 9 | — | GPT-5 (low)ClosedOpenAI | 61.8 | $3.4 | — | — |
| 10 | — | GPT-5 mini (medium)ClosedOpenAI | 60.8 | $0.69 | — | — |
| 11 | — | Grok 4 Fast (Reasoning)ClosedxAI | 60.3 | $0.28 | — | — |
| 12 | — | Gemini 2.5 ProClosedGoogle | 59.6 | $3.4 | — | — |
| 13 | — | o4-mini (high)ClosedOpenAI | 59.6 | $1.9 | — | — |
| 14 | — | Claude 4.1 Opus (Reasoning)ClosedAnthropic | 59.3 | $30 | — | — |
| 15 | — | Grok 3 mini Reasoning (high)ClosedxAI | 57.1 | $0.35 | — | — |
| 16 | — | Claude 4 Sonnet (Reasoning)ClosedAnthropic | 56.5 | $6.0 | — | — |
| 17 | — | Qwen3 MaxClosedAlibaba | 55.2 | $2.4 | — | — |
| 18 | — | Claude 4.5 Haiku (Reasoning)ClosedAnthropic | 54.6 | $2.0 | — | — |
| 19 | — | Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle | 54.4 | $0.85 | — | — |
| 20 | — | Claude 4 Opus (Reasoning)ClosedAnthropic | 54.2 | $30 | — | — |
| 21 | — | Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle | 54.1 | $3.4 | — | — |
| 22 | — | Gemini 2.5 Pro Preview (May' 25)ClosedGoogle | 53.2 | $3.4 | — | — |
| 23 | — | Magistral Medium 1.2ClosedMistral | 52.1 | $2.8 | — | — |
| 24 | — | Gemini 2.5 Flash (Reasoning)ClosedGoogle | 51.2 | $0.85 | — | — |
| 25 | — | GPT-5 nano (high)ClosedOpenAI | 51.0 | $0.14 | — | — |
| 26 | — | o3-mini (high)ClosedOpenAI | 50.8 | $1.9 | — | — |
| 27 | — | Claude 3.7 Sonnet (Reasoning)ClosedAnthropic | 49.9 | $6.0 | — | — |
| 28 | — | Claude 4.5 Sonnet (Non-reasoning)ClosedAnthropic | 49.6 | $6.0 | — | — |
| 29 | — | GPT-5 nano (medium)ClosedOpenAI | 49.3 | $0.14 | — | — |
| 30 | — | Grok Code Fast 1ClosedxAI | 48.7 | $0.53 | — | — |
| 31 | — | Qwen3 Max (Preview)ClosedAlibaba | 48.6 | $2.4 | — | — |
| 32 | — | o3-miniClosedOpenAI | 48.1 | $1.9 | — | — |
| 33 | — | o1-proClosedOpenAI | 48.0 | $263 | — | — |
| 34 | — | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle | 47.9 | $0.18 | — | — |
| 35 | — | o1ClosedOpenAI | 47.2 | $26 | — | — |
| 36 | — | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle | 46.7 | $0.85 | — | — |
| 37 | — | Sonar Reasoning ProClosedPerplexity | 46.3 | $0.000 | — | — |
| 38 | — | Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle | 45.8 | $0.000 | — | — |
| 39 | — | Grok 3ClosedxAI | 45.3 | $6.0 | — | — |
| 40 | — | o1-previewClosedOpenAI | 44.9 | $29 | — | — |
| 41 | — | Claude 4.1 Opus (Non-reasoning)ClosedAnthropic | 44.6 | $30 | — | — |
| 42 | — | Claude 4 Sonnet (Non-reasoning)ClosedAnthropic | 44.4 | $6.0 | — | — |
| 43 | — | GPT-5 (minimal)ClosedOpenAI | 43.5 | $3.4 | — | — |
| 44 | — | GPT-4.1ClosedOpenAI | 43.4 | $3.5 | — | — |
| 45 | — | GPT-4.1 miniClosedOpenAI | 42.5 | $0.70 | — | — |
| 46 | — | Claude 4 Opus (Non-reasoning)ClosedAnthropic | 42.3 | $30 | — | — |
| 47 | — | GPT-5 (ChatGPT)ClosedOpenAI | 41.8 | $3.4 | — | — |
| 48 | — | Claude 4.5 Haiku (Non-reasoning)ClosedAnthropic | 41.7 | $2.0 | — | — |
| 49 | — | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)ClosedGoogle | 41.6 | $0.18 | — | — |
| 50 | — | GPT-5 mini (minimal)ClosedOpenAI | 41.6 | $0.69 | — | — |
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