Text · Factuality · Polish
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 1,487.9749 |
| 2 | Claude Opus 5 (Max) | 1,484.2527 |
| 3 | Claude Opus 4.6 (High) | 1,481.913 |
| 4 | GPT-5.5 (High) | 1,477.6909 |
| 5 | GPT-5.4 (High) | 1,476.2388 |
| 6 | Gemini 3 Flash | 1,476.2086 |
| 7 | Gemini 3.1 Pro Preview | 1,475.2182 |
| 8 | Claude Opus 5 (High) | 1,470.8018 |
| 9 | Gemini 3.5 Flash (Medium) | 1,468.1076 |
| 10 | GPT-5.6 Sol (xHigh) | 1,467.6778 |
| 11 | GPT-5.5 | 1,467.1958 |
| 12 | Claude Opus 4.7 | 1,465.4845 |
| 13 | Claude Opus 4.6 | 1,465.0807 |
| 14 | Claude Opus 4.7 (High) | 1,463.639 |
| 15 | Gemini 3.8 Flash (High) | 1,458.4708 |
| 16 | Claude Opus 4.8 (High) | 1,458.0061 |
| 17 | Claude Opus 4.8 | 1,456.8375 |
| 18 | GPT-5.4 | 1,456.5456 |
| 19 | Gemini 2.5 Pro | 1,455.5588 |
| 20 | Gemini 3 Flash (Minimal) | 1,454.1403 |
| 21 | MiMo-V2.5-Pro | 1,451.3257 |
| 22 | GPT-5.6 Terra (xHigh) | 1,448.8407 |
| 23 | Grok 4.5 | 1,448.5991 |
| 24 | GPT-5.1 | 1,445.5435 |
| 25 | ChatGPT-4o Latest (20250326) | 1,444.5582 |
| 26 | GPT-5.2 | 1,441.226 |
| 27 | Dola Seed 2.0 Pro | 1,440.695 |
| 28 | GLM-5.1 | 1,440.4333 |
| 29 | Qwen3.5-397B-A17B | 1,439.4208 |
| 30 | Grok 4.20 Multi-Agent Beta (0309) | 1,439.3757 |
| 31 | GPT-5.1 (High) | 1,437.9658 |
| 32 | DeepSeek-V4-Pro Preview (High) | 1,437.6445 |
| 33 | Claude Opus 4.5 (20251101) | 1,437.4251 |
| 34 | Qwen3.7-Plus | 1,437.1314 |
| 35 | GPT-5.4 mini (High) | 1,435.225 |
| 36 | Gemini 3.1 Flash-Lite Preview | 1,432.55 |
| 37 | Claude Opus 4.5 (High, 32K, 20251101) | 1,431.4987 |
| 38 | Grok 4.20 Beta (Reasoning, 0309) | 1,428.8455 |
| 39 | ERNIE 5.0 (0110) | 1,427.9019 |
| 40 | Claude Sonnet 4.6 | 1,426.7642 |
| 41 | MiniMax-M3 | 1,426.0033 |
| 42 | Grok 4.1 (Thinking) | 1,425.7662 |
| 43 | GPT-5.2 (High) | 1,425.6735 |
| 44 | GLM-5.3-Flash | 1,425.3849 |
| 45 | Kimi K2.5 (Thinking) | 1,425.3667 |
| 46 | GLM-5.2 (Max) | 1,422.6795 |
| 47 | Grok 4.1 | 1,420.6306 |
| 48 | Mistral Large 3 | 1,416.7685 |
| 49 | GLM-4.6 | 1,414.4021 |
| 50 | Gemini 2.5 Flash | 1,409.6292 |