Text · Style Control · Multi Turn
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,559.4059 |
| 2 | Gemini 4 Argon (High) | 1,539.0135 |
| 3 | Claude Opus 4.6 (High) | 1,516.8307 |
| 4 | Muse Wonder (Max) | 1,516.474 |
| 5 | Claude Fable 5 (High) | 1,516.1481 |
| 6 | Claude Opus 4.7 (High) | 1,515.8221 |
| 7 | Claude Opus 4.7 | 1,513.815 |
| 8 | Claude Opus 4.6 | 1,509.8905 |
| 9 | Muse Spark 1.2 (xHigh) | 1,507.8225 |
| 10 | Gemini 3.8 Flash (High) | 1,504.7958 |
| 11 | Kimi K3 (Max) | 1,502.2465 |
| 12 | Claude Opus 5.5 (High) | 1,499.3161 |
| 13 | Claude Opus 4.8 (High) | 1,496.8521 |
| 14 | Gemini 3.1 Pro Preview | 1,495.9703 |
| 15 | Gemini 3 Pro | 1,495.7432 |
| 16 | Muse Spark 1.1 | 1,495.6497 |
| 17 | Claude Opus 4.8 | 1,494.226 |
| 18 | GPT-5.2 Chat (20260210) | 1,494.1512 |
| 19 | Qwen3.8-Max | 1,493.8178 |
| 20 | Muse Spark 1.3 (Max) | 1,493.0834 |
| 21 | Muse Spark | 1,492.7927 |
| 22 | GPT-5.4 (High) | 1,492.6335 |
| 23 | GPT-5.6 Sol (xHigh) | 1,489.8353 |
| 24 | Claude Fable 5.1 (Max) | 1,488.552 |
| 25 | Gemini 3.7 Flash (High) | 1,487.8763 |
| 26 | Gemini 3.6 Flash (High) | 1,487.8441 |
| 27 | GPT-5.5 (High) | 1,487.2277 |
| 28 | Claude Opus 5 (High) | 1,486.5671 |
| 29 | Claude Opus 5 (Max) | 1,486.2776 |
| 30 | Claude Opus 4.5 (High, 32K, 20251101) | 1,485.321 |
| 31 | Claude Opus 4.5 (20251101) | 1,484.0978 |
| 32 | GPT-6 Astra (Max) | 1,483.9747 |
| 33 | GPT-5.5 | 1,483.9138 |
| 34 | Grok 4.20 Beta 1 | 1,483.2421 |
| 35 | GPT-5.5 Instant | 1,482.555 |
| 36 | Gemini 3 Flash | 1,481.7016 |
| 37 | Qwen3.7-Max-Preview | 1,481.5747 |
| 38 | Claude Sonnet 4.6 | 1,480.7062 |
| 39 | Gemini 3.5 Flash (High) | 1,480.424 |
| 40 | GPT-5.4 | 1,480.1879 |
| 41 | MiMo-V2.5-Pro | 1,479.9297 |
| 42 | GPT-6.1 Sol (Max) | 1,478.6794 |
| 43 | Grok 4.20 Beta (Reasoning, 0309) | 1,478.5592 |
| 44 | GLM-5.1 | 1,478.2538 |
| 45 | GLM-5.3 (Max) | 1,478.1891 |
| 46 | Gemini 3.5 Flash (Medium) | 1,477.9113 |
| 47 | Qwen3.5-Max-Preview | 1,477.2879 |
| 48 | Claude Sonnet 4.5 (20250929) | 1,477.2094 |
| 49 | Claude Sonnet 5.5 (xHigh) | 1,476.6015 |
| 50 | GLM-5.2 (Max) | 1,476.1321 |