Model rankings
1319 models · 5 boards · 2 sources
Best web builder
Best open model
Best from China
Most voted
Top three by Score
claude-fable-5Anthropic1,653
glm-5.2 (max)Z.ai1,584
claude-opus-4-8-thinkingAnthropic1,561
Top three open models
glm-5.2 (max)Z.ai · #2 overall1,584
glm-5.1Z.ai · #9 overall1,523
kimi-k2.6Moonshot AI · #11 overall1,514
This week's changes
Reve 2.0Image · #2New
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Intelligence · #5New
claude-sonnet-5-thinkingCoding · #5New
Fish Audio S2.1 ProSpeech · #15New
OpenAudio S1 MiniSpeech · #50New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | glm-5.2 (max)OpenZ.ai | 1,584 | ±12 | 3,015 | — |
| 2 | — | glm-5.1OpenZ.ai | 1,523 | ±10 | 4,589 | — |
| 3 | — | kimi-k2.6OpenMoonshot AI | 1,514 | ±8 | 6,851 | — |
| 4 | New | minimax-m3OpenMiniMax | 1,501 | ±10 | 4,509 | $0.52 |
| 5 | — | mimo-v2.5-proOpenXiaomi | 1,473 | ±8 | 7,887 | — |
| 6 | ▼ 2 | kimi-k2.7-codeOpenMoonshot AI | 1,471 | ±11 | 3,315 | — |
| 7 | ▼ 1 | deepseek-v4-pro-thinkingOpenDeepSeek | 1,457 | ±8 | 7,330 | — |
| 8 | New | deepseek-v4-proOpenDeepSeek | 1,446 | ±8 | 6,533 | — |
| 9 | ▼ 2 | glm-4.7OpenZ.ai | 1,440 | ±10 | 4,882 | — |
| 10 | — | kimi-k2.5-thinkingOpenMoonshot AI | 1,431 | ±6 | 13,777 | — |
| 11 | ▼ 2 | mimo-v2.5OpenXiaomi | 1,430 | ±8 | 7,019 | — |
| 12 | ▼ 4 | glm-5OpenZ.ai | 1,430 | ±8 | 7,374 | — |
| 13 | ▼ 2 | kimi-k2.5-instantOpenMoonshot AI | 1,408 | ±11 | 3,611 | — |
| 14 | ▼ 2 | minimax-m2.7OpenMiniMax | 1,396 | ±7 | 9,230 | — |
| 15 | ▼ 2 | qwen3.5-397b-a17bOpenAlibaba | 1,396 | ±6 | 13,069 | — |
| 16 | ▼ 2 | minimax-m2.1-previewOpenMiniMax | 1,391 | ±8 | 9,273 | — |
| 17 | ▼ 2 | minimax-m2.5OpenMiniMax | 1,381 | ±8 | 7,856 | — |
| 18 | ▼ 2 | gemma-4-31bOpenGoogle | 1,371 | ±9 | 5,472 | $0.000 |
| 19 | ▼ 2 | deepseek-v3.2-thinkingOpenDeepSeek | 1,368 | ±8 | 7,919 | — |
| 20 | ▼ 2 | qwen3.5-122b-a10bOpenAlibaba | 1,364 | ±7 | 8,166 | — |
| 21 | ▼ 2 | hunyuan-hy3-previewOpenTencent | 1,361 | ±17 | 1,352 | — |
| 22 | ▼ 2 | gemma-4-26b-a4bOpenGoogle | 1,359 | ±16 | 1,508 | — |
| 23 | ▼ 2 | qwen3.5-27bOpenAlibaba | 1,356 | ±8 | 7,673 | — |
| 24 | ▼ 2 | glm-4.6OpenZ.ai | 1,355 | ±9 | 8,351 | — |
| 25 | ▼ 2 | mimo-v2-flash (non-thinking)OpenXiaomi | 1,336 | ±8 | 6,729 | — |
| 26 | ▼ 2 | deepseek-v3.2OpenDeepSeek | 1,332 | ±7 | 10,479 | — |
| 27 | ▼ 2 | kimi-k2-thinking-turboOpenMoonshot AI | 1,330 | ±6 | 15,363 | — |
| 28 | ▼ 2 | minimax-m2OpenMiniMax | 1,305 | ±9 | 8,397 | — |
| 29 | ▼ 2 | mimo-v2-flash (thinking)OpenXiaomi | 1,301 | ±14 | 2,098 | — |
| 30 | ▼ 2 | laguna-xs.2OpenPoolside | 1,299 | ±12 | 3,307 | — |
| 31 | ▼ 2 | deepseek-v3.2-expOpenDeepSeek | 1,288 | ±11 | 4,874 | — |
| 32 | ▼ 2 | qwen3-coder-480b-a35b-instructOpenAlibaba | 1,281 | ±7 | 15,214 | — |
| 33 | ▼ 2 | mistral-medium-3.5OpenMistral | 1,269 | ±15 | 2,030 | $3.0 |
| 34 | ▼ 2 | qwen3.5-35b-a3bOpenAlibaba | 1,249 | ±16 | 1,814 | — |
| 35 | ▼ 2 | trinity-large-thinkingOpen | 1,243 | ±19 | 1,313 | — |
| 36 | ▼ 2 | mistral-large-3OpenMistral | 1,224 | ±20 | 1,034 | — |
| 37 | ▼ 2 | granite-4.1-8bOpenIBM | 1,200 | ±18 | 1,727 | — |
| 38 | ▼ 2 | devstral-2OpenMistral | 1,200 | ±17 | 1,588 | — |
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