Model rankings
1283 models · 5 boards · 2 sources
Best web builder
Best open model
Best from China
Most voted
Top three by Score
claude-fable-5Anthropic1,654
glm-5.2 (max)Z.ai1,593
claude-opus-4-8-thinkingAnthropic1,565
Top three open models
glm-5.2 (max)Z.ai · #2 overall1,593
glm-5.1Z.ai · #8 overall1,529
kimi-k2.6Moonshot AI · #10 overall1,513
This week's changes
MAI-Image-2.5Image · #2New
MAI-Image-2.5-FlashImage · #9New
Luna TTSSpeech · #9New
Nex-N2-ProIntelligence · #20New
Grok Build 0.1 0616Intelligence · #29New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | claude-fable-5ClosedAnthropic | 1,654 | ±16 | 2,095 | — |
| 2 | — | glm-5.2 (max)OpenZ.ai | 1,593 | ±15 | 1,994 | — |
| 3 | — | claude-opus-4-8-thinkingClosedAnthropic · 1 more variant | 1,565 | ±12 | 3,005 | — |
| 4 | — | claude-opus-4-7-thinkingClosedAnthropic · 1 more variant | 1,563 | ±8 | 7,823 | — |
| 5 | — | claude-opus-4-6-thinkingClosedAnthropic · 1 more variant | 1,542 | ±7 | 10,294 | — |
| 6 | — | seed-2.1-pro-previewClosedByteDance | 1,539 | ±15 | 1,640 | — |
| 7 | — | qwen3.7-max-20260517ClosedAlibaba | 1,530 | ±11 | 3,713 | — |
| 8 | — | glm-5.1OpenZ.ai | 1,529 | ±11 | 3,760 | — |
| 9 | — | claude-sonnet-4-6ClosedAnthropic | 1,521 | ±6 | 13,612 | — |
| 10 | — | kimi-k2.6OpenMoonshot AI | 1,513 | ±8 | 5,953 | — |
| 11 | — | gemini-3.5-flashClosedGoogle | 1,506 | ±13 | 2,217 | — |
| 12 | — | minimax-m3ClosedMiniMax | 1,505 | ±11 | 3,236 | $0.52 |
| 13 | — | gpt-5.5-xhigh (codex-harness)ClosedOpenAI | 1,502 | ±8 | 6,535 | — |
| 14 | — | claude-opus-4-5-20251101-thinking-32kClosedAnthropic | 1,490 | ±7 | 13,059 | — |
| 15 | — | gpt-5.5-high (codex-harness)ClosedOpenAI | 1,484 | ±8 | 6,726 | — |
| 16 | — | qwen3.6-max-previewClosedAlibaba | 1,483 | ±12 | 2,507 | — |
| 17 | — | kimi-k2.7-codeOpenMoonshot AI | 1,479 | ±13 | 2,281 | — |
| 18 | — | mimo-v2.5-proOpenXiaomi | 1,471 | ±8 | 6,887 | — |
| 19 | — | claude-opus-4-5-20251101ClosedAnthropic | 1,466 | ±6 | 15,305 | — |
| 20 | — | qwen3.6-plusClosedAlibaba | 1,462 | ±7 | 8,408 | — |
| 21 | — | deepseek-v4-pro-thinkingOpenDeepSeek | 1,458 | ±8 | 6,256 | — |
| 22 | — | gpt-5.4-high (codex-harness)ClosedOpenAI | 1,457 | ±17 | 1,482 | — |
| 23 | — | gpt-5.5 (codex-harness)ClosedOpenAI | 1,449 | ±8 | 6,569 | — |
| 24 | — | gemini-3.1-pro-previewClosedGoogle | 1,447 | ±6 | 12,948 | — |
| 25 | — | glm-4.7OpenZ.ai | 1,440 | ±10 | 4,883 | — |
| 26 | — | gemini-3-proClosedGoogle | 1,439 | ±7 | 17,158 | — |
| 27 | — | gpt-5.4-medium (codex-harness)ClosedOpenAI | 1,437 | ±16 | 1,449 | — |
| 28 | — | gemini-3-flashClosedGoogle · 1 more variant | 1,437 | ±7 | 13,277 | — |
| 29 | — | glm-5OpenZ.ai | 1,434 | ±8 | 6,715 | — |
| 30 | — | mimo-v2-proClosedXiaomi | 1,432 | ±8 | 6,787 | — |
| 31 | — | mimo-v2.5OpenXiaomi | 1,432 | ±8 | 5,996 | — |
| 32 | — | kimi-k2.5-thinkingOpenMoonshot AI | 1,431 | ±6 | 12,739 | — |
| 33 | — | gpt-5.4ClosedOpenAI | 1,411 | ±27 | 505 | — |
| 34 | — | kimi-k2.5-instantOpenMoonshot AI | 1,408 | ±11 | 3,610 | — |
| 35 | — | gpt-5.3-codex (codex-harness)ClosedOpenAI · 1 more variant | 1,407 | ±12 | 2,965 | — |
| 36 | — | gpt-5.2ClosedOpenAI | 1,405 | ±17 | 1,457 | — |
| 37 | — | gpt-5.4-mini-highClosedOpenAI | 1,398 | ±8 | 7,713 | — |
| 38 | — | minimax-m2.7OpenMiniMax | 1,395 | ±7 | 8,265 | — |
| 39 | — | qwen3.5-397b-a17bOpenAlibaba | 1,395 | ±6 | 11,997 | — |
| 40 | — | gpt-5-mediumClosedOpenAI | 1,394 | ±13 | 3,755 | — |
| 41 | — | minimax-m2.1-previewOpenMiniMax | 1,392 | ±8 | 9,273 | — |
| 42 | — | gpt-5.1-mediumClosedOpenAI | 1,391 | ±9 | 6,119 | — |
| 43 | — | claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic | 1,388 | ±7 | 15,741 | — |
| 44 | — | claude-opus-4-1-20250805ClosedAnthropic | 1,386 | ±9 | 8,568 | — |
| 45 | — | claude-sonnet-4-5-20250929ClosedAnthropic | 1,386 | ±6 | 18,390 | — |
| 46 | — | grok-4.20-beta-0309-reasoningClosedxAI | 1,385 | ±7 | 9,535 | — |
| 47 | — | minimax-m2.5OpenMiniMax | 1,382 | ±8 | 7,838 | — |
| 48 | — | gemma-4-31bOpenGoogle | 1,374 | ±9 | 4,802 | $0.000 |
| 49 | — | deepseek-v3.2-thinkingOpenDeepSeek · 1 more variant | 1,368 | ±8 | 7,911 | — |
| 50 | — | qwen3.5-122b-a10bOpenAlibaba | 1,364 | ±7 | 8,152 | — |
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