Text · Factuality · Coding
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,569.6789 |
| 2 | Claude Opus 5.5 (High) | 1,566.0705 |
| 3 | Claude Opus 4.6 (High) | 1,550.1901 |
| 4 | MiMo-V2.6-Pro | 1,547.4577 |
| 5 | Claude Fable 5.1 (Max) | 1,547.1971 |
| 6 | Claude Opus 4.6 | 1,547.024 |
| 7 | Muse Wonder (Max) | 1,546.0361 |
| 8 | Claude Opus 5 (Max) | 1,545.8079 |
| 9 | Gemini 4 Argon (High) | 1,545.1329 |
| 10 | Claude Opus 5 (High) | 1,537.1051 |
| 11 | Claude Fable 5 (High) | 1,536.2794 |
| 12 | Claude Sonnet 5.5 (xHigh) | 1,536.1572 |
| 13 | Claude Opus 4.7 (High) | 1,534.2859 |
| 14 | GPT-5.4 (High) | 1,533.9834 |
| 15 | Claude Opus 4.5 (High, 32K, 20251101) | 1,533.1758 |
| 16 | Muse Spark 1.3 (Max) | 1,532.8928 |
| 17 | GPT-5.5 (High) | 1,532.5488 |
| 18 | Muse Spark 1.2 (xHigh) | 1,532.4502 |
| 19 | GPT-5.6 Sol (xHigh) | 1,532.3065 |
| 20 | Claude Opus 4.7 | 1,532.1848 |
| 21 | Kimi K3 (Max) | 1,531.9682 |
| 22 | Claude Opus 4.5 (20251101) | 1,531.3824 |
| 23 | GPT-6 Astra (Max) | 1,529.3718 |
| 24 | Claude Sonnet 4.6 | 1,528.9733 |
| 25 | GLM-5.3-Flash | 1,528.5202 |
| 26 | MiMo-V2.5-Pro | 1,528.4867 |
| 27 | GPT-6.1 Sol (Max) | 1,527.6675 |
| 28 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,526.256 |
| 29 | GPT-5.5 | 1,525.1462 |
| 30 | Gemini 3.7 Flash (High) | 1,524.3464 |
| 31 | GPT-5.4 | 1,524.3375 |
| 32 | Qwen3.5-Max-Preview | 1,523.7056 |
| 33 | Qwen3.8-Max | 1,523.5025 |
| 34 | Claude Opus 4.8 (High) | 1,523.5004 |
| 35 | GPT-5.6 Terra (xHigh) | 1,522.0605 |
| 36 | Claude Sonnet 4.5 (20250929) | 1,521.5481 |
| 37 | MiMo-V2.6-Flash | 1,520.6119 |
| 38 | GLM-5.3 (Max) | 1,520.5725 |
| 39 | Gemini 3.8 Flash (High) | 1,520.4514 |
| 40 | Gemini 3.5 Flash (High) | 1,520.3346 |
| 41 | Beam 1.0 501B A23B | 1,520.1203 |
| 42 | Claude Opus 4.8 | 1,519.7668 |
| 43 | Gemini 3.6 Flash (High) | 1,519.6986 |
| 44 | Gemini 3 Pro | 1,519.0056 |
| 45 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,518.2645 |
| 46 | Grok 4.5 | 1,516.872 |
| 47 | GPT-6 Luna (Max) | 1,516.6316 |
| 48 | Muse Spark 1.1 | 1,516.5809 |
| 49 | Kimi K2.5 (Instant) | 1,515.7446 |
| 50 | Kimi K2.6 | 1,515.081 |