Model rankings
757 models · 5 boards · 2 sources
Smartest
Best open model
Best from China
Top three by Intelligence
GPT-5.2 (xhigh)OpenAI50.6
Claude Opus 4.5 (Reasoning)Anthropic49.1
Gemini 3 Pro Preview (high)Google47.9
Top three open models
GLM-4.7 (Reasoning)Z AI · #9 overall41.7
DeepSeek V3.2 (Reasoning)DeepSeek · #12 overall41.2
Kimi K2 ThinkingKimi · #14 overall40.3
This week's changes
GPT Image 1.5 (high)Image · #1New
FLUX.2 [max]Image · #3New
Kling O1 ProVideo · #9New
Kling 2.6 Pro (No Audio)Video · #10New
Imagen 4 UltraImage · #12New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | ▲ 1 | GPT-5.2 (xhigh)ClosedOpenAI | 50.6 | — | — | — |
| 2 | ▲ 2 | Claude Opus 4.5 (Reasoning)ClosedAnthropic | 49.1 | — | — | — |
| 3 | ▼ 2 | Gemini 3 Pro Preview (high)ClosedGoogle | 47.9 | — | — | — |
| 4 | ▲ 1 | GPT-5.1 (high)ClosedOpenAI | 47.0 | — | — | — |
| 5 | ▼ 2 | Gemini 3 Flash Preview (Reasoning)ClosedGoogle | 45.8 | — | — | — |
| 6 | ▲ 2 | GPT-5.2 (medium)ClosedOpenAI | 45.4 | — | — | — |
| 7 | — | GPT-5 (high)ClosedOpenAI | 44.1 | — | — | — |
| 8 | ▼ 2 | GPT-5 Codex (high)ClosedOpenAI | 44.0 | — | — | — |
| 9 | ▲ 15 | Claude Opus 4.5 (Non-reasoning)ClosedAnthropic | 42.5 | — | — | — |
| 10 | ▲ 7 | Claude 4.5 Sonnet (Reasoning)ClosedAnthropic | 42.4 | — | — | — |
| 11 | ▼ 1 | GPT-5 (medium)ClosedOpenAI | 41.9 | — | — | — |
| 12 | ▼ 3 | GPT-5.1 Codex (high)ClosedOpenAI | 41.6 | — | — | — |
| 13 | ▼ 1 | Grok 4ClosedxAI | 41.4 | — | — | — |
| 14 | ▲ 1 | GPT-5 mini (high)ClosedOpenAI | 40.6 | — | — | — |
| 15 | ▼ 1 | Gemini 3 Pro Preview (low)ClosedGoogle | 40.6 | — | — | — |
| 16 | ▲ 4 | GPT-5 (low)ClosedOpenAI | 38.7 | — | — | — |
| 17 | ▲ 4 | GPT-5 mini (medium)ClosedOpenAI | 38.6 | — | — | — |
| 18 | ▲ 14 | Claude 4 Sonnet (Reasoning)ClosedAnthropic | 38.3 | — | — | — |
| 19 | ▼ 3 | Grok 4.1 Fast (Reasoning)ClosedxAI | 38.2 | — | — | — |
| 20 | ▼ 1 | GPT-5.1 Codex mini (high)ClosedOpenAI | 38.0 | — | — | — |
| 21 | ▲ 13 | Claude 4.5 Haiku (Reasoning)ClosedAnthropic | 36.6 | — | — | — |
| 22 | ▲ 25 | Claude 4.5 Sonnet (Non-reasoning)ClosedAnthropic | 36.6 | — | — | — |
| 23 | ▼ 5 | Nova 2.0 Pro Preview (medium)ClosedAmazon | 35.3 | — | — | — |
| 24 | ▲ 11 | Gemini 3 Flash Preview (Non-reasoning)ClosedGoogle | 34.8 | — | — | — |
| 25 | ▼ 2 | Grok 4 Fast (Reasoning)ClosedxAI | 34.6 | — | — | — |
| 26 | ▲ 20 | Claude 3.7 Sonnet (Reasoning)ClosedAnthropic | 34.4 | — | — | — |
| 27 | ▼ 2 | Gemini 2.5 ProClosedGoogle | 34.1 | — | — | — |
| 28 | ▲ 25 | GPT-5.2 (Non-reasoning)ClosedOpenAI | 33.1 | — | — | — |
| 29 | ▼ 3 | o4-mini (high)ClosedOpenAI | 32.9 | — | — | — |
| 30 | ▼ 8 | gpt-oss-120B (high)OpenOpenAI | 32.9 | — | — | — |
| 31 | ▲ 34 | Claude 4 Sonnet (Non-reasoning)ClosedAnthropic | 32.7 | — | — | — |
| 32 | ▼ 2 | Grok 3 mini Reasoning (high)ClosedxAI | 32.4 | — | — | — |
| 33 | ▼ 4 | Nova 2.0 Pro Preview (low)ClosedAmazon | 32.2 | — | — | — |
| 34 | ▲ 2 | Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle | 30.8 | — | — | — |
| 35 | ▲ 43 | Claude 3.7 Sonnet (Non-reasoning)ClosedAnthropic | 30.6 | — | — | — |
| 36 | ▲ 38 | Claude 4.5 Haiku (Non-reasoning)ClosedAnthropic | 30.5 | — | — | — |
| 37 | ▼ 9 | Nova 2.0 Lite (medium)ClosedAmazon | 29.9 | — | — | — |
| 38 | ▼ 5 | Nova 2.0 Omni (medium)ClosedAmazon | 27.9 | — | — | — |
| 39 | ▼ 8 | Apriel-v1.6-15B-ThinkerOpenServiceNow | 27.8 | — | — | — |
| 40 | ▲ 3 | Gemini 2.5 Flash (Reasoning)ClosedGoogle | 27.2 | — | — | — |
| 41 | ▲ 28 | GPT-5.1 (Non-reasoning)ClosedOpenAI | 27.2 | — | — | — |
| 42 | ▲ 2 | GPT-5 nano (high)ClosedOpenAI | 26.7 | — | — | — |
| 43 | ▲ 5 | GPT-5 nano (medium)ClosedOpenAI | 25.8 | — | — | — |
| 44 | ▲ 24 | GPT-4.1ClosedOpenAI | 25.8 | — | — | — |
| 45 | ▲ 13 | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle | 25.6 | — | — | — |
| 46 | ▲ 15 | Grok 3ClosedxAI | 25.2 | — | — | — |
| 47 | ▲ 10 | Nova 2.0 Lite (low)ClosedAmazon | 25.0 | — | — | — |
| 48 | ▼ 7 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA | 24.7 | — | — | — |
| 49 | ▼ 9 | gpt-oss-20B (high)OpenOpenAI | 24.7 | — | — | — |
| 50 | ▲ 17 | GPT-5 (minimal)ClosedOpenAI | 24.5 | — | — | — |
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