Text · Style Control · Exclude Ties
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,554.1923 |
| 2 | Gemini 4 Argon (High) | 1,546.9323 |
| 3 | Muse Wonder (Max) | 1,530.0533 |
| 4 | Claude Opus 5.5 (High) | 1,529.5844 |
| 5 | Claude Fable 5.1 (Max) | 1,524.0517 |
| 6 | Claude Fable 5 (High) | 1,523.2149 |
| 7 | Claude Opus 4.6 (High) | 1,522.0804 |
| 8 | Claude Opus 4.7 (High) | 1,518.7229 |
| 9 | Claude Opus 4.6 | 1,514.6451 |
| 10 | Gemini 3.8 Flash (High) | 1,513.8537 |
| 11 | Muse Spark 1.3 (Max) | 1,512.7802 |
| 12 | Muse Spark 1.2 (xHigh) | 1,508.3685 |
| 13 | Claude Opus 4.7 | 1,508.153 |
| 14 | Claude Opus 5 (High) | 1,506.7054 |
| 15 | Muse Spark 1.1 | 1,505.7441 |
| 16 | Claude Opus 5 (Max) | 1,505.22 |
| 17 | Gemini 3.7 Flash (High) | 1,504.885 |
| 18 | Kimi K3 (Max) | 1,502.4451 |
| 19 | Muse Spark | 1,502.137 |
| 20 | Gemini 3.1 Pro Preview | 1,501.5862 |
| 21 | Gemini 3 Pro | 1,501.1142 |
| 22 | GPT-5.6 Sol (xHigh) | 1,500.4856 |
| 23 | Gemini 3.6 Flash (High) | 1,495.5574 |
| 24 | Qwen3.8-Max | 1,495.4152 |
| 25 | GPT-6.1 Sol (Max) | 1,494.9149 |
| 26 | Claude Opus 4.8 (High) | 1,494.0363 |
| 27 | GPT-5.5 (High) | 1,492.3097 |
| 28 | GLM-5.3 (Max) | 1,489.8429 |
| 29 | MiMo-V2.6-Pro | 1,489.5365 |
| 30 | GPT-6 Astra (Max) | 1,487.8347 |
| 31 | Gemini 3.5 Flash (High) | 1,487.618 |
| 32 | Gemini 3.5 Flash (Medium) | 1,487.3314 |
| 33 | Claude Sonnet 5.5 (xHigh) | 1,486.9424 |
| 34 | GPT-5.2 Chat (20260210) | 1,486.3337 |
| 35 | GPT-5.5 | 1,486.0441 |
| 36 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,485.6463 |
| 37 | GLM-5.3-Flash | 1,485.1155 |
| 38 | Claude Opus 4.5 (High, 32K, 20251101) | 1,484.9856 |
| 39 | Gemini 3 Flash | 1,484.9847 |
| 40 | GLM-5.2 (Max) | 1,484.9679 |
| 41 | GPT-5.4 (High) | 1,484.445 |
| 42 | Claude Opus 4.8 | 1,484.4331 |
| 43 | GPT-5.5 Instant | 1,484.3961 |
| 44 | Grok 4.20 Beta 1 | 1,484.029 |
| 45 | Claude Sonnet 4.6 | 1,481.558 |
| 46 | Qwen3.7-Max-Preview | 1,481.3138 |
| 47 | Grok 4.20 Beta (Reasoning, 0309) | 1,479.8037 |
| 48 | Claude Opus 4.5 (20251101) | 1,478.6481 |
| 49 | Grok 4.20 Multi-Agent Beta (0309) | 1,477.7454 |
| 50 | GPT-5.6 Terra (xHigh) | 1,475.1275 |