Model rankings
1356 models · 5 boards · 2 sources
Best web builder
Best open model
Best from China
Most voted
Top three by Score
gpt-5.6-sol-xhigh (codex-harness)OpenAI1,631
claude-fable-5Anthropic1,630
glm-5.2 (max)Z.ai1,581
Top three open models
glm-5.2 (max)Z.ai · #3 overall1,581
glm-5.1Z.ai · #11 overall1,527
kimi-k2.6Moonshot AI · #14 overall1,513
This week's changes
gpt-5.6-sol-xhigh (codex-harness)Coding · #1New
Simba 3.2Speech · #1New
GPT-5.6 Sol (max)Intelligence · #2New
GPT-5.6 Terra (max)Intelligence · #4New
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Image · #5New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | glm-5.2 (max)OpenZ.ai | 1,581 | ±10 | 4,374 | — |
| 2 | — | glm-5.1OpenZ.ai | 1,527 | ±9 | 5,517 | — |
| 3 | — | kimi-k2.6OpenMoonshot AI | 1,513 | ±7 | 9,003 | — |
| 4 | — | minimax-m3OpenMiniMax | 1,495 | ±9 | 5,832 | $0.52 |
| 5 | — | mimo-v2.5-proOpenXiaomi | 1,475 | ±7 | 9,129 | — |
| 6 | — | kimi-k2.7-codeOpenMoonshot AI | 1,471 | ±10 | 4,273 | — |
| 7 | — | deepseek-v4-pro-thinkingOpenDeepSeek · 1 more variant | 1,458 | ±7 | 8,551 | — |
| 8 | — | glm-4.7OpenZ.ai | 1,440 | ±10 | 4,885 | — |
| 9 | — | kimi-k2.5-thinkingOpenMoonshot AI | 1,433 | ±6 | 14,821 | — |
| 10 | ▲ 1 | glm-5OpenZ.ai | 1,430 | ±8 | 7,454 | — |
| 11 | ▼ 1 | mimo-v2.5OpenXiaomi | 1,430 | ±7 | 8,222 | — |
| 12 | — | kimi-k2.5-instantOpenMoonshot AI | 1,408 | ±11 | 3,613 | — |
| 13 | ▲ 1 | qwen3.5-397b-a17bOpenAlibaba | 1,397 | ±6 | 14,250 | — |
| 14 | ▼ 1 | minimax-m2.7OpenMiniMax | 1,395 | ±7 | 10,279 | — |
| 15 | — | minimax-m2.1-previewOpenMiniMax | 1,392 | ±8 | 9,275 | — |
| 16 | — | minimax-m2.5OpenMiniMax | 1,382 | ±8 | 7,864 | — |
| 17 | — | deepseek-v3.2-thinkingOpenDeepSeek · 1 more variant | 1,368 | ±8 | 7,924 | — |
| 18 | — | qwen3.5-122b-a10bOpenAlibaba | 1,364 | ±7 | 8,229 | — |
| 19 | — | hunyuan-hy3-previewOpenTencent | 1,361 | ±17 | 1,378 | — |
| 20 | — | qwen3.5-27bOpenAlibaba | 1,357 | ±8 | 7,732 | — |
| 21 | — | glm-4.6OpenZ.ai | 1,356 | ±9 | 8,350 | — |
| 22 | — | mimo-v2-flash (non-thinking)OpenXiaomi · 1 more variant | 1,337 | ±8 | 6,733 | — |
| 23 | — | kimi-k2-thinking-turboOpenMoonshot AI | 1,330 | ±6 | 15,366 | — |
| 24 | — | minimax-m2OpenMiniMax | 1,305 | ±9 | 8,404 | — |
| 25 | — | deepseek-v3.2-expOpenDeepSeek | 1,288 | ±11 | 4,872 | — |
| 26 | — | qwen3-coder-480b-a35b-instructOpenAlibaba | 1,282 | ±7 | 15,216 | — |
| 27 | — | qwen3.5-35b-a3bOpenAlibaba | 1,250 | ±16 | 1,814 | — |
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