Text · Factuality · Russian
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Argon (High) | 1,523.6362 |
| 2 | Claude Opus 5.5 (High) | 1,517.5446 |
| 3 | Muse Wonder (Max) | 1,516.5871 |
| 4 | Claude Fable 5.1 (Max) | 1,512.939 |
| 5 | Gemini 3.8 Flash (High) | 1,510.4633 |
| 6 | Claude Fable 5 (High) | 1,507.1841 |
| 7 | Gemini 3.7 Flash (High) | 1,504.5026 |
| 8 | Claude Opus 5 (Max) | 1,503.6818 |
| 9 | Claude Opus 5 (High) | 1,501.0758 |
| 10 | Gemini 3.5 Flash (High) | 1,497.6939 |
| 11 | GPT-5.4 (High) | 1,497.6327 |
| 12 | Claude Opus 4.6 | 1,497.1931 |
| 13 | Gemini 3.1 Pro Preview | 1,496.3917 |
| 14 | Claude Opus 4.6 (High) | 1,495.8207 |
| 15 | Claude Opus 4.7 (High) | 1,493.491 |
| 16 | Muse Spark 1.3 (Max) | 1,493.2127 |
| 17 | GPT-5.5 | 1,492.3461 |
| 18 | Gemini 3 Pro | 1,491.5875 |
| 19 | Claude Opus 4.7 | 1,488.8485 |
| 20 | Qwen3.5-Max-Preview | 1,488.5877 |
| 21 | GPT-5.6 Sol (xHigh) | 1,488.4116 |
| 22 | Gemini 3.5 Flash (Medium) | 1,488.0733 |
| 23 | Kimi K3 (Max) | 1,487.4982 |
| 24 | Gemini 3.6 Flash (High) | 1,487.4494 |
| 25 | GPT-5.5 (High) | 1,486.3916 |
| 26 | Claude Opus 4.8 (High) | 1,484.3223 |
| 27 | Qwen3.8-Max | 1,483.8809 |
| 28 | GPT-6.1 Sol (Max) | 1,483.8682 |
| 29 | MiMo-V2.6-Pro | 1,483.6363 |
| 30 | Gemini 3 Flash | 1,479.4665 |
| 31 | Muse Spark 1.2 (xHigh) | 1,479.4404 |
| 32 | Muse Spark 1.1 | 1,479.367 |
| 33 | GPT-5.6 Terra (xHigh) | 1,478.5641 |
| 34 | Claude Sonnet 5.5 (xHigh) | 1,478.4195 |
| 35 | GLM-5.3 (Max) | 1,477.5378 |
| 36 | Grok 4.5 | 1,476.9601 |
| 37 | GPT-5.4 | 1,475.7136 |
| 38 | GPT-6 Astra (Max) | 1,474.2947 |
| 39 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,474.0506 |
| 40 | Claude Opus 4.8 | 1,473.4921 |
| 41 | GLM-5.3-Flash | 1,472.5193 |
| 42 | GLM-5.2 (Max) | 1,471.2587 |
| 43 | Grok 4.20 Beta (Reasoning, 0309) | 1,468.225 |
| 44 | Gemini 2.5 Pro | 1,467.6713 |
| 45 | Qwen3.7-Plus | 1,467.2313 |
| 46 | Gemini 3 Flash (Minimal) | 1,465.7997 |
| 47 | GPT-5.2 Chat (20260210) | 1,464.628 |
| 48 | GLM-5V-Turbo | 1,463.8861 |
| 49 | ERNIE 5.1 | 1,463.7436 |
| 50 | Grok 4.20 Multi-Agent Beta (0309) | 1,462.8851 |