Text · Longer Query
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,553.2107 |
| 2 | Gemini 4 Argon (High) | 1,542.0323 |
| 3 | Claude Opus 5.5 (High) | 1,533.2487 |
| 4 | Claude Fable 5.1 (Max) | 1,525.3778 |
| 5 | Claude Opus 4.6 (High) | 1,517.5332 |
| 6 | Claude Opus 5 (Max) | 1,517.1511 |
| 7 | Claude Opus 4.6 | 1,514.0039 |
| 8 | Claude Opus 5 (High) | 1,513.7504 |
| 9 | Claude Fable 5 (High) | 1,510.2438 |
| 10 | Gemini 3.8 Flash (High) | 1,508.5634 |
| 11 | Claude Opus 4.7 (High) | 1,505.1676 |
| 12 | MiMo-V2.6-Pro | 1,501.8905 |
| 13 | Claude Opus 4.7 | 1,498.9491 |
| 14 | Muse Wonder (Max) | 1,495.0651 |
| 15 | Claude Sonnet 5.5 (xHigh) | 1,494.4467 |
| 16 | Gemini 3.7 Flash (High) | 1,494.0884 |
| 17 | Kimi K3 (Max) | 1,493.4844 |
| 18 | Qwen3.8-Max | 1,488.4744 |
| 19 | Muse Spark 1.3 (Max) | 1,487.7192 |
| 20 | GPT-5.5 (High) | 1,484.1936 |
| 21 | Claude Opus 4.8 (High) | 1,484.0739 |
| 22 | GLM-5.3-Flash | 1,483.6707 |
| 23 | GLM-5.3 (Max) | 1,483.4638 |
| 24 | Gemini 3.5 Flash (High) | 1,482.8104 |
| 25 | GPT-5.5 | 1,482.3263 |
| 26 | Gemini 3.1 Pro Preview | 1,482.0616 |
| 27 | Qwen3.7-Max-Preview | 1,481.2027 |
| 28 | MiMo-V2.5-Pro | 1,481.145 |
| 29 | Claude Opus 4.8 | 1,480.0681 |
| 30 | GPT-5.6 Sol (xHigh) | 1,480.0028 |
| 31 | GLM-5.2 (Max) | 1,479.0028 |
| 32 | Claude Opus 4.5 (20251101) | 1,478.867 |
| 33 | Claude Sonnet 4.6 | 1,478.6767 |
| 34 | Claude Opus 4.5 (High, 32K, 20251101) | 1,478.2444 |
| 35 | Gemini 3.5 Flash (Medium) | 1,477.2531 |
| 36 | Qwen3.5-Max-Preview | 1,476.4131 |
| 37 | Claude Sonnet 4.5 (20250929) | 1,475.2446 |
| 38 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,474.9503 |
| 39 | Gemini 3.6 Flash (High) | 1,474.7526 |
| 40 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,473.8548 |
| 41 | Muse Spark 1.2 (xHigh) | 1,473.7984 |
| 42 | GPT-5.4 (High) | 1,473.1826 |
| 43 | Gemini 3 Pro | 1,470.973 |
| 44 | Kimi K2.6 | 1,468.293 |
| 45 | GLM-5.1 | 1,467.1801 |
| 46 | GPT-5.4 | 1,464.0184 |
| 47 | Claude Sonnet 5 (High) | 1,463.0534 |
| 48 | GPT-6.1 Sol (Max) | 1,462.9526 |
| 49 | Grok 4.5 | 1,461.8697 |
| 50 | ERNIE 5.1 | 1,461.7385 |