Text · Factuality · Expert
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (High) | 1,548.8165 |
| 2 | Claude Opus 5 (Max) | 1,542.646 |
| 3 | Claude Opus 4.6 (High) | 1,542.1202 |
| 4 | Gemini 4 Argon (High) | 1,537.7512 |
| 5 | Claude Fable 5 (High) | 1,535.4016 |
| 6 | Claude Sonnet 5.5 (xHigh) | 1,535.2566 |
| 7 | Claude Opus 5 (High) | 1,534.9429 |
| 8 | Claude Opus 4.6 | 1,534.6111 |
| 9 | GPT-5.5 (High) | 1,531.8867 |
| 10 | GPT-5.6 Sol (xHigh) | 1,531.682 |
| 11 | Claude Fable 5.1 (Max) | 1,529.6839 |
| 12 | GPT-5.4 (High) | 1,529.5103 |
| 13 | GPT-6.1 Sol (Max) | 1,528.1156 |
| 14 | GPT-5.5 | 1,523.7257 |
| 15 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,522.5632 |
| 16 | Kimi K3 (Max) | 1,522.3261 |
| 17 | Claude Opus 4.7 | 1,519.4622 |
| 18 | Claude Opus 4.7 (High) | 1,519.2055 |
| 19 | GPT-5.6 Terra (xHigh) | 1,516.9225 |
| 20 | GLM-5.3 (Max) | 1,516.3845 |
| 21 | GLM-5.3-Flash | 1,515.4527 |
| 22 | Claude Opus 4.8 (High) | 1,515.4325 |
| 23 | Gemini 3.8 Flash (High) | 1,514.2493 |
| 24 | Gemini 3.7 Flash (High) | 1,512.9076 |
| 25 | GPT-6 Astra (Max) | 1,512.2169 |
| 26 | Muse Spark 1.3 (Max) | 1,510.186 |
| 27 | GPT-5.4 | 1,509.6473 |
| 28 | MiMo-V2.5-Pro | 1,509.6327 |
| 29 | MiMo-V2.6-Flash | 1,509.2116 |
| 30 | Claude Sonnet 4.6 | 1,508.5639 |
| 31 | GPT-5.6 Luna (xHigh) | 1,506.2385 |
| 32 | Claude Opus 4.5 (20251101) | 1,506.0169 |
| 33 | Qwen3.5-Max-Preview | 1,505.5272 |
| 34 | Gemini 3.5 Flash (High) | 1,504.1971 |
| 35 | Claude Opus 4.5 (High, 32K, 20251101) | 1,503.1784 |
| 36 | ERNIE 5.1 | 1,503.1687 |
| 37 | Claude Opus 4.8 | 1,502.5729 |
| 38 | Qwen3.8-Max | 1,501.9246 |
| 39 | Claude Sonnet 5 (High) | 1,500.8368 |
| 40 | GPT-6 Luna (Max) | 1,500.181 |
| 41 | Step 5 Preview | 1,499.8473 |
| 42 | Kimi K2.6 | 1,498.9527 |
| 43 | Gemini 3.6 Flash (High) | 1,497.8476 |
| 44 | Gemini 3.5 Flash (Medium) | 1,497.4098 |
| 45 | GLM-5.2 (Max) | 1,495.9453 |
| 46 | Gemini 3 Pro | 1,495.9037 |
| 47 | Muse Spark 1.2 (xHigh) | 1,495.5716 |
| 48 | Grok 4.5 | 1,494.5847 |
| 49 | Gemini 3.1 Pro Preview | 1,493.7702 |
| 50 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,493.7589 |