Rare Disease Diagnosis on RareArena In-Distribution (test)
60.29Top-1 AccuracyRareDxR1-Qwen + CRR
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RareDxR1-Qwen + CRRParams=14B, Domain=Medical, RLM=Yes2026.06 | 60.29 | 71.71 | 78.73 | |
| RareDxR1-DeepSeek + CRRParams=14B, Domain=Medical, RLM=Yes2026.06 | 56.98 | 69.56 | 75.41 | |
| RareDxR1-QwenParams=14B, Domain=Medical, RLM=Yes2026.06 | 55.46 | 66.34 | 75.32 | |
| RareDxR1-DeepSeekParams=14B, Domain=Medical, RLM=Yes2026.06 | 52.29 | 63.61 | 69.27 | |
| Gemini-2.5-FlashParams=-, Domain=General, RLM=Yes2026.06 | 44.88 | 53.76 | 57.37 | |
| DeepSeek-R1Params=671B, Domain=General, RLM=Yes2026.06 | 44.2 | 54.73 | 59.02 | |
| Doubao-1.5-Thinking-ProParams=-, Domain=General, RLM=Yes2026.06 | 43.71 | 52.88 | 56.78 | |
| GPT-4oParams=-, Domain=General, RLM=No2026.06 | 41.66 | 50.54 | 56.88 | |
| HuatuoGPT-o1Params=70B, Domain=Medical, RLM=Yes2026.06 | 36.29 | 41.27 | 41.76 | |
| Qwen3Params=14B, Domain=General, RLM=Yes2026.06 | 32.68 | 40.59 | 45.95 | |
| Baichuan-M1Params=14B, Domain=Medical, RLM=Yes2026.06 | 31.9 | 40.98 | 48 | |
| DeepSeek-DistillParams=14B, Domain=General, RLM=Yes2026.06 | 25.76 | 35.12 | 42.15 |