Model rankings
1160 models · 5 boards · 2 sources
Best web builder
Best open model
Best from China
Most voted
Top three by Score
claude-opus-4-7-thinkingAnthropic1,572
claude-opus-4-6-thinkingAnthropic1,552
glm-5.1Z.ai1,534
Top three open models
glm-5.1Z.ai · #3 overall1,534
kimi-k2.6Moonshot AI · #4 overall1,529
deepseek-v4-pro-thinkingDeepSeek · #12 overall1,456
This week's changes
GPT-5.5 (xhigh)Intelligence · #1New
GPT Image 2 (high)Image · #1New
Realtime TTS 1.5 MaxSpeech · #1New
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Intelligence · #2New
kimi-k2.6Coding · #4New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | glm-5.1OpenZ.ai | 1,534 | ±13 | 2,478 | — |
| 2 | New | kimi-k2.6OpenMoonshot AI | 1,529 | ±17 | 1,408 | — |
| 3 | New | deepseek-v4-pro-thinkingOpenDeepSeek | 1,456 | ±19 | 1,066 | — |
| 4 | ▼ 2 | glm-4.7OpenZ.ai | 1,440 | ±10 | 4,880 | — |
| 5 | ▼ 2 | glm-5OpenZ.ai | 1,435 | ±9 | 5,640 | — |
| 6 | ▼ 2 | kimi-k2.5-thinkingOpenMoonshot AI | 1,430 | ±8 | 7,913 | — |
| 7 | ▼ 2 | minimax-m2.7OpenMiniMax | 1,416 | ±10 | 3,785 | — |
| 8 | ▼ 2 | kimi-k2.5-instantOpenMoonshot AI | 1,408 | ±11 | 3,611 | — |
| 9 | ▼ 2 | minimax-m2.1-previewOpenMiniMax | 1,392 | ±8 | 9,274 | — |
| 10 | ▼ 2 | qwen3.5-397b-a17bOpenAlibaba | 1,388 | ±8 | 6,715 | — |
| 11 | ▼ 2 | minimax-m2.5OpenMiniMax | 1,384 | ±8 | 7,834 | — |
| 12 | ▼ 2 | deepseek-v3.2-thinkingOpenDeepSeek | 1,368 | ±8 | 7,904 | — |
| 13 | ▼ 2 | qwen3.5-122b-a10bOpenAlibaba | 1,363 | ±9 | 5,506 | — |
| 14 | ▼ 2 | glm-4.6OpenZ.ai | 1,355 | ±9 | 8,349 | — |
| 15 | ▼ 2 | qwen3.5-27bOpenAlibaba | 1,345 | ±9 | 5,083 | — |
| 16 | ▼ 2 | mimo-v2-flash (non-thinking)OpenXiaomi | 1,337 | ±8 | 6,736 | — |
| 17 | ▼ 2 | deepseek-v3.2OpenDeepSeek | 1,332 | ±7 | 10,427 | — |
| 18 | ▼ 2 | kimi-k2-thinking-turboOpenMoonshot AI | 1,329 | ±6 | 15,346 | — |
| 19 | ▼ 2 | minimax-m2OpenMiniMax | 1,304 | ±9 | 8,401 | — |
| 20 | ▼ 2 | mimo-v2-flash (thinking)OpenXiaomi | 1,300 | ±14 | 2,096 | — |
| 21 | ▼ 2 | deepseek-v3.2-expOpenDeepSeek | 1,286 | ±11 | 4,870 | — |
| 22 | ▼ 2 | qwen3-coder-480b-a35b-instructOpenAlibaba | 1,281 | ±7 | 15,208 | — |
| 23 | ▼ 2 | qwen3.5-35b-a3bOpenAlibaba | 1,248 | ±16 | 1,814 | — |
| 24 | ▼ 2 | mistral-large-3OpenMistral | 1,223 | ±20 | 1,031 | — |
| 25 | ▼ 2 | devstral-2OpenMistral | 1,199 | ±17 | 1,582 | — |
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