Text · Factuality · Medicine & Healthcare
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Argon (High) | 1,536.0971 |
| 2 | Claude Opus 5.5 (High) | 1,533.104 |
| 3 | Claude Opus 5 (Max) | 1,525.8885 |
| 4 | Qwen3.5-Max-Preview | 1,525.4609 |
| 5 | Claude Fable 5.1 (Max) | 1,522.5042 |
| 6 | Gemini 3 Pro | 1,518.8117 |
| 7 | Claude Opus 4.6 (High) | 1,518.0935 |
| 8 | Claude Opus 5 (High) | 1,518.0382 |
| 9 | Kimi K3 (Max) | 1,516.233 |
| 10 | Claude Opus 4.7 | 1,514.9976 |
| 11 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,514.1656 |
| 12 | Qwen3.8-Max | 1,512.8489 |
| 13 | Claude Opus 4.6 | 1,512.8144 |
| 14 | Claude Opus 4.7 (High) | 1,510.7241 |
| 15 | Gemini 3.8 Flash (High) | 1,508.7728 |
| 16 | Gemini 3.5 Flash (High) | 1,506.2873 |
| 17 | Claude Fable 5 (High) | 1,504.7488 |
| 18 | Muse Spark 1.3 (Max) | 1,504.7033 |
| 19 | GPT-5.5 (High) | 1,503.6883 |
| 20 | Gemini 2.5 Pro | 1,502.5007 |
| 21 | ERNIE 5.1 | 1,502.254 |
| 22 | GPT-5.4 (High) | 1,501.5717 |
| 23 | GPT-5.5 | 1,501.2395 |
| 24 | MiMo-V2.5-Pro | 1,500.7569 |
| 25 | Claude Opus 4.8 (High) | 1,500.2995 |
| 26 | Gemini 3.7 Flash (High) | 1,499.8951 |
| 27 | Gemini 3.1 Pro Preview | 1,499.7982 |
| 28 | GLM-5.3 (Max) | 1,498.723 |
| 29 | Gemini 3.5 Flash (Medium) | 1,498.704 |
| 30 | GLM-5.2 (Max) | 1,498.0864 |
| 31 | Muse Spark 1.1 | 1,497.9496 |
| 32 | GLM-5.3-Flash | 1,495.7839 |
| 33 | GLM-5.1 | 1,494.6409 |
| 34 | GLM-4.6 | 1,493.8732 |
| 35 | GPT-5.1 (High) | 1,492.4396 |
| 36 | Claude Opus 4.8 | 1,491.4014 |
| 37 | GPT-5.4 | 1,491.2243 |
| 38 | DeepSeek-V4-Pro | 1,488.2748 |
| 39 | Gemini 3.6 Flash (High) | 1,488.1596 |
| 40 | Qwen3.7-Plus | 1,487.382 |
| 41 | DeepSeek-V4-Pro Preview (High) | 1,487.3482 |
| 42 | Grok 4.20 Beta (Reasoning, 0309) | 1,487.1365 |
| 43 | Gemini 3 Flash | 1,485.7921 |
| 44 | GPT-5.1 | 1,485.6697 |
| 45 | GPT-5.6 Terra (xHigh) | 1,484.9535 |
| 46 | Kimi K2.6 | 1,483.9166 |
| 47 | Qwen3.5-397B-A17B | 1,483.5503 |
| 48 | Grok 4.20 Multi-Agent Beta (0309) | 1,483.3344 |
| 49 | Inkling | 1,483.163 |
| 50 | ChatGPT-4o Latest (20250326) | 1,482.9123 |