Confirmed Success
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (Max) | 0.1978 |
| 2 | Claude Sonnet 5.5 (Max) | 0.1976 |
| 3 | Gemini 4 Carbon (High) | 0.1783 |
| 4 | GPT-6 Astra (Max) | 0.1369 |
| 5 | Gemini 4 Argon (High) | 0.127 |
| 6 | Claude Fable 5.1 (Max) | 0.1239 |
| 7 | Muse Wonder Full (Max) | 0.1188 |
| 8 | GPT-6.1 Sol (Max) | 0.1149 |
| 9 | Claude Opus 5 (Max) | 0.1142 |
| 10 | GPT-6.1 Terra (Max) | 0.0972 |
| 11 | Muse Wonder (Max) | 0.0679 |
| 12 | MiMo-V2.6-Flash | 0.0554 |
| 13 | Claude Fable 5 (High) | 0.0518 |
| 14 | MiMo-V2.6-Pro | 0.0513 |
| 15 | Grok 4.7 (xHigh) | 0.0508 |
| 16 | Hy4 preview | 0.0439 |
| 17 | Qwen3.8-Max | 0.0405 |
| 18 | DeepSeek-V4.1-Flash-20261017 (Max) | 0.0385 |
| 19 | GPT-6 Sol (Max) | 0.0385 |
| 20 | Muse Spark 1.3 (Max) | 0.0382 |
| 21 | Kimi K3 (Max) | 0.0377 |
| 22 | Kimi K3.1 Pro (Max) | 0.0365 |
| 23 | GLM-5.3 (Max) | 0.0362 |
| 24 | GLM-5.2 (Max) | 0.0279 |
| 25 | GLM-5.3-Flash | 0.0238 |
| 26 | Claude Haiku 5.5 (High) | 0.019 |
| 27 | MiniMax-M3.1-Flash | 0.0177 |
| 28 | GPT-5.6 Sol (xHigh) | 0.0173 |
| 29 | Gemini 3.8 Flash (High) | 0.0123 |
| 30 | Qwen3.8-Flash-Next | 0.0099 |
| 31 | Claude Sonnet 5 (High) | 0.0024 |
| 32 | Step 5 Preview | -0.0036 |
| 33 | GPT-6 Luna (Max) | -0.004 |
| 34 | Mistral Large 4 | -0.0114 |
| 35 | Grok 4.6 (xHigh) | -0.0157 |
| 36 | Qwen3.8-27B | -0.0255 |
| 37 | DeepSeek-V4-Pro (High, 20260813) | -0.0281 |
| 38 | Gemini 3.7 Flash (High) | -0.0303 |
| 39 | Muse Spark 1.1 | -0.0659 |
| 40 | GPT-6 Luna (Medium) | -0.0667 |
| 41 | GPT-5.6 Terra (xHigh) | -0.0706 |
| 42 | Spark-X2.6 | -0.0788 |
| 43 | Qwen3.7-Plus | -0.0889 |
| 44 | Muse Spark 1.2 (xHigh) | -0.0929 |
| 45 | Qwen3.7-Max | -0.1017 |
| 46 | Beam 1.0 501B A23B | -0.1044 |
| 47 | MiMo-V2.5-Pro | -0.1084 |
| 48 | Hy3 | -0.1143 |
| 49 | Gemini 3.1 Pro Preview | -0.1184 |
| 50 | GPT-6 Luna (Low) | -0.1573 |