Text · Style Control · Longer Query
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,541.9336 |
| 2 | Gemini 4 Argon (High) | 1,538.9576 |
| 3 | Claude Opus 5.5 (High) | 1,525.2092 |
| 4 | Claude Fable 5 (High) | 1,522.1367 |
| 5 | Claude Opus 4.6 (High) | 1,521.4322 |
| 6 | Claude Opus 4.6 | 1,515.6745 |
| 7 | Claude Opus 4.7 (High) | 1,515.0139 |
| 8 | Claude Fable 5.1 (Max) | 1,511.8199 |
| 9 | Gemini 3.8 Flash (High) | 1,511.6404 |
| 10 | Claude Opus 4.7 | 1,507.4623 |
| 11 | Muse Wonder (Max) | 1,504.9617 |
| 12 | Claude Opus 5 (High) | 1,503.4543 |
| 13 | Claude Opus 4.8 (High) | 1,503.4339 |
| 14 | Kimi K3 (Max) | 1,502.9062 |
| 15 | Claude Opus 5 (Max) | 1,502.4357 |
| 16 | Gemini 3.7 Flash (High) | 1,501.0901 |
| 17 | Claude Opus 4.8 | 1,499.2568 |
| 18 | Claude Sonnet 5.5 (xHigh) | 1,498.9986 |
| 19 | Gemini 3.1 Pro Preview | 1,498.9693 |
| 20 | GPT-5.6 Sol (xHigh) | 1,497.5723 |
| 21 | Muse Spark 1.3 (Max) | 1,496.0068 |
| 22 | MiMo-V2.6-Pro | 1,494.9086 |
| 23 | Claude Opus 4.5 (High, 32K, 20251101) | 1,494.7845 |
| 24 | Claude Opus 4.5 (20251101) | 1,492.2093 |
| 25 | Claude Sonnet 4.6 | 1,492.083 |
| 26 | Qwen3.8-Max | 1,491.5199 |
| 27 | GPT-6.1 Sol (Max) | 1,491.1677 |
| 28 | Gemini 3 Pro | 1,490.2989 |
| 29 | Qwen3.7-Max-Preview | 1,490.1063 |
| 30 | Muse Spark 1.2 (xHigh) | 1,489.4048 |
| 31 | GPT-6 Astra (Max) | 1,488.0118 |
| 32 | GPT-5.5 (High) | 1,487.3636 |
| 33 | GPT-5.5 | 1,486.8656 |
| 34 | MiMo-V2.5-Pro | 1,486.0429 |
| 35 | GLM-5.3 (Max) | 1,485.9902 |
| 36 | GLM-5.2 (Max) | 1,485.6575 |
| 37 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,485.4898 |
| 38 | Gemini 3.6 Flash (High) | 1,485.2653 |
| 39 | Claude Opus 4.1 (Thinking 16K, 20250805) | 1,484.5023 |
| 40 | Gemini 3.5 Flash (High) | 1,482.3296 |
| 41 | GLM-5.3-Flash | 1,482.1844 |
| 42 | Claude Sonnet 4.5 (20250929) | 1,481.482 |
| 43 | Claude Sonnet 5 (High) | 1,481.4061 |
| 44 | Qwen3.5-Max-Preview | 1,481.0974 |
| 45 | GPT-5.4 (High) | 1,480.8559 |
| 46 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,480.661 |
| 47 | Gemini 3.5 Flash (Medium) | 1,480.6535 |
| 48 | Muse Spark 1.1 | 1,480.4234 |
| 49 | GLM-5.1 | 1,480.0035 |
| 50 | Grok 4.5 | 1,479.6733 |