Text · Hard Prompts (English)
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,545.1093 |
| 2 | Gemini 4 Argon (High) | 1,539.2419 |
| 3 | Claude Opus 5.5 (High) | 1,539.1297 |
| 4 | Claude Opus 4.6 (High) | 1,530.4493 |
| 5 | Claude Opus 4.6 | 1,526.8369 |
| 6 | Claude Fable 5.1 (Max) | 1,523.3689 |
| 7 | Claude Opus 5 (Max) | 1,523.31 |
| 8 | MiMo-V2.6-Pro | 1,519.9216 |
| 9 | Claude Opus 5 (High) | 1,518.4732 |
| 10 | Muse Wonder (Max) | 1,509.7817 |
| 11 | Claude Fable 5 (High) | 1,509.5452 |
| 12 | Claude Opus 4.7 (High) | 1,508.1377 |
| 13 | Qwen3.8-Max | 1,504.7311 |
| 14 | Gemini 3.8 Flash (High) | 1,504.1206 |
| 15 | Claude Sonnet 5.5 (xHigh) | 1,501.447 |
| 16 | Claude Opus 4.7 | 1,500.605 |
| 17 | Muse Spark 1.3 (Max) | 1,499.5747 |
| 18 | GLM-5.3 (Max) | 1,496.8051 |
| 19 | Kimi K3 (Max) | 1,496.1153 |
| 20 | MiMo-V2.5-Pro | 1,493.8724 |
| 21 | Claude Sonnet 4.6 | 1,493.285 |
| 22 | Muse Spark 1.2 (xHigh) | 1,490.5674 |
| 23 | MiMo-V2.6-Flash | 1,490.1227 |
| 24 | GLM-5.3-Flash | 1,489.1802 |
| 25 | Gemini 3.7 Flash (High) | 1,488.6832 |
| 26 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,488.2532 |
| 27 | Claude Opus 4.8 (High) | 1,486.9336 |
| 28 | ERNIE 5.1 | 1,484.7729 |
| 29 | Gemini 3.6 Flash (High) | 1,484.7428 |
| 30 | GPT-5.5 | 1,483.2678 |
| 31 | GPT-5.5 (High) | 1,482.5979 |
| 32 | GLM-5.1 | 1,482.5085 |
| 33 | Gemini 3.5 Flash (High) | 1,482.3493 |
| 34 | Qwen3.5-Max-Preview | 1,481.9233 |
| 35 | Claude Opus 4.5 (20251101) | 1,481.5947 |
| 36 | GLM-5.2 (Max) | 1,481.4524 |
| 37 | Muse Spark 1.1 | 1,480.9219 |
| 38 | Gemini 3.1 Pro Preview | 1,480.0108 |
| 39 | Gemini 3.5 Flash (Medium) | 1,479.1262 |
| 40 | GPT-5.4 (High) | 1,478.736 |
| 41 | Muse Spark | 1,477.2369 |
| 42 | GPT-5.6 Sol (xHigh) | 1,477.1135 |
| 43 | Claude Opus 4.5 (High, 32K, 20251101) | 1,476.9975 |
| 44 | Claude Opus 4.8 | 1,475.4104 |
| 45 | Gemini 3 Pro | 1,474.7072 |
| 46 | MiMo-V2-Pro | 1,472.8567 |
| 47 | Qwen3.7-Max-Preview | 1,472.304 |
| 48 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,471.5417 |
| 49 | Kimi K2.6 | 1,471.3313 |
| 50 | Claude Sonnet 4.5 (20250929) | 1,470.0963 |