Model rankings
1190 models · 5 boards · 2 sources
Best web builder
Best open model
Best from China
Most voted
Top three by Score
claude-opus-4-7-thinkingAnthropic1,571
claude-opus-4-6-thinkingAnthropic1,548
glm-5.1Z.ai1,534
Top three open models
glm-5.1Z.ai · #3 overall1,534
kimi-k2.6Moonshot AI · #5 overall1,526
mimo-v2.5-proXiaomi · #9 overall1,475
This week's changes
gpt-5.5-high (codex-harness)Coding · #7New
Grok 4.3Intelligence · #8New
mimo-v2.5-proCoding · #9New
DeepSeek V4 Pro (Reasoning, Max Effort)Intelligence · #13New
gpt-5.5 (codex-harness)Coding · #15New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | glm-5.1OpenZ.ai | 1,534 | ±11 | 3,412 | — |
| 2 | — | kimi-k2.6OpenMoonshot AI | 1,526 | ±14 | 2,130 | — |
| 3 | New | mimo-v2.5-proOpenXiaomi | 1,475 | ±12 | 2,681 | — |
| 4 | ▼ 1 | qwen3.6-plusClosedAlibaba | 1,467 | ±11 | 3,716 | — |
| 5 | ▼ 1 | deepseek-v4-pro-thinkingOpenDeepSeek | 1,455 | ±16 | 1,469 | — |
| 6 | New | mimo-v2.5OpenXiaomi | 1,444 | ±15 | 1,570 | — |
| 7 | ▼ 2 | glm-4.7OpenZ.ai | 1,440 | ±10 | 4,883 | — |
| 8 | ▼ 2 | glm-5OpenZ.ai | 1,437 | ±8 | 6,393 | — |
| 9 | ▼ 2 | kimi-k2.5-thinkingOpenMoonshot AI | 1,430 | ±7 | 8,721 | — |
| 10 | ▼ 2 | mimo-v2-proClosedXiaomi | 1,430 | ±9 | 4,869 | — |
| 11 | ▼ 2 | minimax-m2.7OpenMiniMax | 1,411 | ±10 | 4,502 | — |
| 12 | ▼ 2 | kimi-k2.5-instantOpenMoonshot AI | 1,408 | ±11 | 3,609 | — |
| 13 | ▼ 2 | minimax-m2.1-previewOpenMiniMax | 1,392 | ±8 | 9,279 | — |
| 14 | ▼ 2 | qwen3.5-397b-a17bOpenAlibaba | 1,387 | ±8 | 7,601 | — |
| 15 | ▼ 2 | minimax-m2.5OpenMiniMax | 1,383 | ±8 | 7,857 | — |
| 16 | ▼ 2 | deepseek-v3.2-thinkingOpenDeepSeek | 1,368 | ±8 | 7,918 | — |
| 17 | ▼ 2 | qwen3.5-122b-a10bOpenAlibaba | 1,363 | ±8 | 6,318 | — |
| 18 | ▼ 2 | glm-4.6OpenZ.ai | 1,355 | ±9 | 8,354 | — |
| 19 | ▼ 2 | qwen3.5-27bOpenAlibaba | 1,350 | ±9 | 5,905 | — |
| 20 | ▼ 2 | mimo-v2-flash (non-thinking)OpenXiaomi | 1,337 | ±8 | 6,734 | — |
| 21 | ▼ 2 | deepseek-v3.2OpenDeepSeek | 1,332 | ±7 | 10,480 | — |
| 22 | ▼ 2 | kimi-k2-thinking-turboOpenMoonshot AI | 1,330 | ±6 | 15,371 | — |
| 23 | ▼ 2 | minimax-m2OpenMiniMax | 1,304 | ±9 | 8,403 | — |
| 24 | ▼ 2 | mimo-v2-flash (thinking)OpenXiaomi | 1,300 | ±14 | 2,096 | — |
| 25 | ▼ 2 | deepseek-v3.2-expOpenDeepSeek | 1,286 | ±11 | 4,871 | — |
| 26 | ▼ 2 | qwen3-coder-480b-a35b-instructOpenAlibaba | 1,281 | ±7 | 15,218 | — |
| 27 | ▼ 2 | qwen3.5-35b-a3bOpenAlibaba | 1,248 | ±16 | 1,815 | — |
| 28 | ▼ 2 | qwen3.5-flashClosedAlibaba | 1,236 | ±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