Rare Disease Diagnosis on RareBench
46.79Pass@1MedXIAOHE
Evaluation Results
| Method | Links | |
|---|---|---|
| MedXIAOHEMode=Thinking mode, Decoding=Greedy2026.02 | 46.79 | |
| GPT-5.2 ThinkingMode=Thinking mode, Decoding=Greedy2026.02 | 42.19 | |
| Gemini 3.0 ProDecoding=Greedy2026.02 | 41 | |
| Gemini 2.5 ProDecoding=Greedy2026.02 | 36.01 |