Text · Factuality · Mathematical
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (High) | 1,522.6023 |
| 2 | Gemini 4 Argon (High) | 1,508.9667 |
| 3 | Claude Fable 5.1 (Max) | 1,506.2895 |
| 4 | Claude Opus 5 (Max) | 1,505.5768 |
| 5 | Claude Opus 4.6 (High) | 1,505.5625 |
| 6 | Claude Opus 4.6 | 1,499.3199 |
| 7 | GPT-5.4 (High) | 1,497.9394 |
| 8 | Claude Fable 5 (High) | 1,494.008 |
| 9 | GPT-5.5 (High) | 1,493.0376 |
| 10 | GPT-5.6 Sol (xHigh) | 1,489.7238 |
| 11 | Gemini 3.8 Flash (High) | 1,489.633 |
| 12 | Claude Opus 4.7 (High) | 1,487.2554 |
| 13 | Kimi K3 (Max) | 1,487.2299 |
| 14 | GPT-6 Astra (Max) | 1,485.9091 |
| 15 | GPT-5.5 | 1,485.7749 |
| 16 | Claude Opus 4.8 (High) | 1,485.5759 |
| 17 | ERNIE 5.1 | 1,483.4457 |
| 18 | Grok 4.5 | 1,482.894 |
| 19 | GPT-5.6 Terra (xHigh) | 1,482.7073 |
| 20 | Gemini 3.7 Flash (High) | 1,482.6953 |
| 21 | Gemini 3.5 Flash (Medium) | 1,482.3988 |
| 22 | Claude Opus 4.7 | 1,482.2747 |
| 23 | MiMo-V2.5-Pro | 1,481.0023 |
| 24 | GLM-5.3 (Max) | 1,480.8975 |
| 25 | Claude Sonnet 5 (High) | 1,480.5284 |
| 26 | Claude Opus 4.8 | 1,480.4778 |
| 27 | Gemini 3.6 Flash (High) | 1,479.8321 |
| 28 | Muse Spark 1.3 (Max) | 1,478.4195 |
| 29 | GLM-5.3-Flash | 1,477.687 |
| 30 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,475.5645 |
| 31 | Kimi K2.6 | 1,475.1142 |
| 32 | GPT-5.4 | 1,474.6455 |
| 33 | GLM-5.2 (Max) | 1,472.4651 |
| 34 | Claude Sonnet 4.6 | 1,471.9821 |
| 35 | Inkling | 1,471.5068 |
| 36 | Gemini 3 Pro | 1,471.4225 |
| 37 | GPT-5.6 Luna (xHigh) | 1,470.9056 |
| 38 | Qwen3.8-Max | 1,470.4032 |
| 39 | Gemini 3.5 Flash (High) | 1,468.7412 |
| 40 | Claude Opus 4.5 (20251101) | 1,468.1489 |
| 41 | Gemini 3.1 Pro Preview | 1,467.9582 |
| 42 | Qwen3.7-Plus | 1,467.5817 |
| 43 | Hy3 | 1,464.0608 |
| 44 | Muse Spark 1.1 | 1,463.7761 |
| 45 | Grok 4.6 (High) | 1,462.5248 |
| 46 | GLM-5 | 1,461.1148 |
| 47 | Claude Opus 4.5 (High, 32K, 20251101) | 1,460.6757 |
| 48 | Kimi K2.5 (Thinking) | 1,460.4149 |
| 49 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,459.4708 |
| 50 | MiMo-V2.6-Flash | 1,459.3336 |