Text · Factuality · Chinese
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (High) | 1,557.1478 |
| 2 | Claude Opus 5 (Max) | 1,555.1585 |
| 3 | Gemini 4 Argon (High) | 1,551.5966 |
| 4 | Claude Fable 5.1 (Max) | 1,546.5562 |
| 5 | Claude Opus 4.6 (High) | 1,544.9955 |
| 6 | Claude Opus 5 (High) | 1,543.5782 |
| 7 | Claude Opus 4.6 | 1,542.2615 |
| 8 | Claude Fable 5 (High) | 1,540.5769 |
| 9 | GPT-5.6 Sol (xHigh) | 1,539.4928 |
| 10 | GPT-6 Astra (Max) | 1,537.9683 |
| 11 | GPT-5.5 | 1,537.5151 |
| 12 | Gemini 3.7 Flash (High) | 1,535.8101 |
| 13 | GPT-5.5 (High) | 1,534.7049 |
| 14 | GPT-5.4 (High) | 1,532.9832 |
| 15 | Gemini 3 Pro | 1,532.7981 |
| 16 | Gemini 3.8 Flash (High) | 1,532.5916 |
| 17 | Qwen3.8-Max | 1,528.3793 |
| 18 | Claude Opus 4.7 (High) | 1,527.5671 |
| 19 | Claude Opus 4.7 | 1,527.3659 |
| 20 | GPT-5.6 Terra (xHigh) | 1,526.6194 |
| 21 | Gemini 3.5 Flash (High) | 1,525.1529 |
| 22 | GPT-5.4 | 1,525.1399 |
| 23 | Gemini 3.1 Pro Preview | 1,523.9383 |
| 24 | Gemini 3.5 Flash (Medium) | 1,523.7668 |
| 25 | GLM-5 | 1,523.5036 |
| 26 | Kimi K3 (Max) | 1,523.3243 |
| 27 | GLM-5.3 (Max) | 1,523.3015 |
| 28 | Gemini 3.6 Flash (High) | 1,521.0301 |
| 29 | GLM-5.3-Flash | 1,520.9677 |
| 30 | Claude Opus 4.8 | 1,517.9885 |
| 31 | Kimi K2.6 | 1,517.1637 |
| 32 | Gemini 3 Flash | 1,516.9793 |
| 33 | GLM-5.2 (Max) | 1,516.7657 |
| 34 | Muse Spark 1.3 (Max) | 1,515.9357 |
| 35 | GLM-4.6 | 1,515.6297 |
| 36 | GPT-6.1 Sol (Max) | 1,514.67 |
| 37 | GLM-5.1 | 1,514.4192 |
| 38 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,514.2551 |
| 39 | Claude Opus 4.8 (High) | 1,513.9423 |
| 40 | MiMo-V2.5-Pro | 1,511.7637 |
| 41 | Qwen3.7-Plus | 1,511.4774 |
| 42 | GPT-5.1 (High) | 1,509.7144 |
| 43 | MiMo-V2.6-Flash | 1,506.9655 |
| 44 | Grok 4.5 | 1,506.6469 |
| 45 | ERNIE 5.1 | 1,505.9183 |
| 46 | Muse Spark 1.2 (xHigh) | 1,504.6635 |
| 47 | Muse Spark 1.1 | 1,502.54 |
| 48 | Qwen3.8-27B | 1,501.746 |
| 49 | DeepSeek-V4-Pro Preview (High) | 1,501.2721 |
| 50 | Qwen3.5-397B-A17B | 1,500.9931 |