Model rankings
906 models · 5 boards · 2 sources
Best web builder
Best open model
Best from China
Most voted
Top three by Score
claude-opus-4-5-20251101-thinking-32kAnthropic1,512
claude-opus-4-5-20251101Anthropic1,479
gemini-3-proGoogle1,471
Top three open models
minimax-m2.1-previewMiniMax · #5 overall1,445
glm-4.7Z.ai · #6 overall1,441
glm-4.6Z.ai · #13 overall1,366
This week's changes
Speech 2.6 HDSpeech · #2New
Speech 2.6 TurboSpeech · #3New
minimax-m2.1-previewCoding · #5New
Multilingual v2Speech · #7New
GLM-4.7 (Reasoning)Intelligence · #8New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | New | minimax-m2.1-previewOpenMiniMax | 1,445 | ±10 | 3,980 | — |
| 2 | ▼ 1 | glm-4.7OpenZ.ai | 1,441 | ±13 | 2,270 | — |
| 3 | ▼ 1 | glm-4.6OpenZ.ai | 1,366 | ±9 | 7,921 | — |
| 4 | ▼ 1 | deepseek-v3.2-thinkingOpenDeepSeek | 1,361 | ±15 | 1,753 | — |
| 5 | — | mimo-v2-flash (non-thinking)OpenXiaomi | 1,342 | ±15 | 1,555 | — |
| 6 | ▼ 2 | kimi-k2-thinking-turboOpenMoonshot AI | 1,337 | ±9 | 7,336 | — |
| 7 | ▼ 1 | minimax-m2OpenMiniMax | 1,313 | ±9 | 8,023 | — |
| 8 | ▼ 1 | deepseek-v3.2-expOpenDeepSeek | 1,290 | ±10 | 5,162 | — |
| 9 | — | deepseek-v3.2OpenDeepSeek | 1,286 | ±13 | 2,155 | — |
| 10 | ▼ 2 | qwen3-coder-480b-a35b-instructOpenAlibaba | 1,285 | ±9 | 8,199 | — |
| 11 | ▼ 1 | mistral-large-3OpenMistral | 1,222 | ±20 | 1,027 | — |
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