Text · Factuality · Instruction Following
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (High) | 1,528.2186 |
| 2 | Gemini 4 Carbon (High) | 1,520.6073 |
| 3 | Gemini 4 Argon (High) | 1,515.1644 |
| 4 | Claude Fable 5.1 (Max) | 1,509.8582 |
| 5 | Claude Opus 4.6 (High) | 1,507.2964 |
| 6 | Claude Opus 5 (Max) | 1,501.1997 |
| 7 | Claude Opus 4.6 | 1,497.8053 |
| 8 | Muse Wonder (Max) | 1,495.3645 |
| 9 | Claude Opus 5 (High) | 1,495.2477 |
| 10 | Claude Fable 5 (High) | 1,494.5237 |
| 11 | GPT-5.6 Sol (xHigh) | 1,491.9949 |
| 12 | Claude Sonnet 5.5 (xHigh) | 1,491.3609 |
| 13 | GPT-5.5 (High) | 1,491.2244 |
| 14 | GPT-5.5 | 1,488.9536 |
| 15 | Claude Opus 4.7 (High) | 1,487.2944 |
| 16 | MiMo-V2.6-Pro | 1,484.1791 |
| 17 | GPT-5.4 (High) | 1,483.7657 |
| 18 | Claude Opus 4.5 (High, 32K, 20251101) | 1,483.4911 |
| 19 | GPT-6.1 Sol (Max) | 1,482.9323 |
| 20 | Claude Opus 4.7 | 1,482.4817 |
| 21 | Claude Opus 4.8 (High) | 1,482.3364 |
| 22 | Kimi K3 (Max) | 1,482.0951 |
| 23 | Muse Spark 1.3 (Max) | 1,479.8698 |
| 24 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,479.7411 |
| 25 | Gemini 3.7 Flash (High) | 1,479.4841 |
| 26 | Qwen3.5-Max-Preview | 1,478.1552 |
| 27 | Claude Opus 4.5 (20251101) | 1,477.7207 |
| 28 | GLM-5.3 (Max) | 1,477.5219 |
| 29 | Gemini 3.8 Flash (High) | 1,476.0901 |
| 30 | Claude Sonnet 4.6 | 1,476.0419 |
| 31 | Qwen3.7-Max-Preview | 1,474.7309 |
| 32 | Qwen3.8-Max | 1,474.7269 |
| 33 | GLM-5.3-Flash | 1,474.3414 |
| 34 | MiMo-V2.5-Pro | 1,473.8694 |
| 35 | GPT-5.4 | 1,473.822 |
| 36 | GPT-5.6 Terra (xHigh) | 1,470.6523 |
| 37 | Gemini 3.5 Flash (High) | 1,470.4409 |
| 38 | Claude Opus 4.8 | 1,470.3908 |
| 39 | Muse Spark 1.2 (xHigh) | 1,470.3233 |
| 40 | GPT-6 Astra (Max) | 1,469.1964 |
| 41 | Gemini 3 Pro | 1,468.8914 |
| 42 | Gemini 3.6 Flash (High) | 1,468.684 |
| 43 | Claude Sonnet 4.5 (20250929) | 1,468.3581 |
| 44 | GLM-5.2 (Max) | 1,468.0582 |
| 45 | Gemini 3.1 Pro Preview | 1,466.6419 |
| 46 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,465.7241 |
| 47 | GPT-6 Luna (Max) | 1,464.8208 |
| 48 | Grok 4.5 | 1,464.1039 |
| 49 | Gemini 3.5 Flash (Medium) | 1,463.5333 |
| 50 | GPT-5.6 Luna (xHigh) | 1,462.5508 |