Model rankings
1275 models · 5 boards · 2 sources
Best web builder
Best open model
Best from China
Most voted
Top three by Score
claude-fable-5Anthropic1,665
claude-opus-4-7-thinkingAnthropic1,566
claude-opus-4-8-thinkingAnthropic1,559
Top three open models
glm-5.1Z.ai · #6 overall1,532
kimi-k2.6Moonshot AI · #9 overall1,515
mimo-v2.5-proXiaomi · #16 overall1,468
This week's changes
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Intelligence · #1New
claude-fable-5Coding · #1New
HiDream-O1-Image-1.5Image · #3New
MAI-Image-2.5-Flash (Foundry)Image · #8New
MAI-Image-2.5 (Foundry)Image · #12New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | qwen3.7-max-20260517ClosedAlibaba | 1,534 | ±12 | 2,867 | — |
| 2 | — | glm-5.1OpenZ.ai | 1,532 | ±11 | 3,608 | — |
| 3 | — | minimax-m3ClosedMiniMax | 1,521 | ±14 | 2,148 | $0.52 |
| 4 | — | kimi-k2.6OpenMoonshot AI | 1,515 | ±9 | 5,104 | — |
| 5 | — | qwen3.6-max-previewClosedAlibaba | 1,484 | ±12 | 2,503 | — |
| 6 | — | mimo-v2.5-proOpenXiaomi | 1,468 | ±9 | 5,966 | — |
| 7 | — | qwen3.6-plusClosedAlibaba | 1,464 | ±8 | 7,454 | — |
| 8 | — | deepseek-v4-pro-thinkingOpenDeepSeek | 1,462 | ±9 | 5,311 | — |
| 9 | — | glm-4.7OpenZ.ai | 1,440 | ±10 | 4,881 | — |
| 10 | — | mimo-v2.5OpenXiaomi | 1,435 | ±9 | 5,045 | — |
| 11 | — | glm-5OpenZ.ai | 1,435 | ±8 | 6,569 | — |
| 12 | — | mimo-v2-proClosedXiaomi | 1,433 | ±8 | 6,786 | — |
| 13 | — | kimi-k2.5-thinkingOpenMoonshot AI | 1,430 | ±6 | 11,857 | — |
| 14 | — | kimi-k2.5-instantOpenMoonshot AI | 1,408 | ±11 | 3,610 | — |
| 15 | — | minimax-m2.7OpenMiniMax | 1,395 | ±8 | 7,438 | — |
| 16 | — | qwen3.5-397b-a17bOpenAlibaba | 1,395 | ±6 | 10,992 | — |
| 17 | — | minimax-m2.1-previewOpenMiniMax | 1,392 | ±8 | 9,276 | — |
| 18 | — | minimax-m2.5OpenMiniMax | 1,382 | ±8 | 7,830 | — |
| 19 | — | deepseek-v3.2-thinkingOpenDeepSeek | 1,368 | ±8 | 7,910 | — |
| 20 | — | qwen3.5-122b-a10bOpenAlibaba | 1,365 | ±7 | 8,151 | — |
| 21 | — | hunyuan-hy3-previewOpenTencent | 1,364 | ±17 | 1,353 | — |
| 22 | — | qwen3.5-27bOpenAlibaba | 1,357 | ±8 | 7,661 | — |
| 23 | — | glm-4.6OpenZ.ai | 1,355 | ±9 | 8,350 | — |
| 24 | — | mimo-v2-flash (non-thinking)OpenXiaomi | 1,337 | ±8 | 6,727 | — |
| 25 | — | deepseek-v3.2OpenDeepSeek | 1,332 | ±7 | 10,467 | — |
| 26 | — | kimi-k2-thinking-turboOpenMoonshot AI | 1,329 | ±6 | 15,344 | — |
| 27 | — | minimax-m2OpenMiniMax | 1,305 | ±9 | 8,398 | — |
| 28 | — | mimo-v2-flash (thinking)OpenXiaomi | 1,300 | ±14 | 2,097 | — |
| 29 | — | deepseek-v3.2-expOpenDeepSeek | 1,287 | ±11 | 4,873 | — |
| 30 | — | qwen3-coder-480b-a35b-instructOpenAlibaba | 1,282 | ±7 | 15,208 | — |
| 31 | — | qwen3.5-35b-a3bOpenAlibaba | 1,249 | ±16 | 1,815 | — |
| 32 | — | qwen3.5-flashClosedAlibaba | 1,237 | ±17 | 1,562 | — |
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