Rare Disease Diagnosis on RareBench HMS
56.97Recall@1DeepRare
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DeepRarebackbone=DeepSeek-V32025.06 | 56.97 | 65.12 | 70.93 | |
| DeepRarebackbone=Claude-3.72025.06 | 56.82 | 63.64 | 64.77 | |
| DeepRarebackbone=GPT-4o2025.06 | 54.54 | 65.9 | 69.31 | |
| DeepRarebackbone=DeepSeek-R12025.06 | 51.76 | 60 | 67.06 | |
| GPT-4o2025.06 | 47.73 | 60.23 | 65.91 | |
| Claude 3.7 think2025.06 | 44.32 | 57.95 | 62.5 | |
| Claude-3.7-Sonnet2025.06 | 43.18 | 60.23 | 63.64 | |
| DeepSeek V32025.06 | 42.05 | 56.82 | 62.5 | |
| DeepRarebackbone=Gemini-22025.06 | 40.91 | 54.25 | 57.95 | |
| DeepSeek R12025.06 | 38.64 | 53.41 | 60.23 | |
| Gemini 2 think2025.06 | 38.64 | 48.86 | 56.82 | |
| Baichuan-14B2025.06 | 38.64 | 53.41 | 60.23 | |
| DS-R1-search2025.06 | 38.64 | 55.68 | 62.5 | |
| RAGbackbone=DeepSeek-V32025.06 | 36.36 | 46.59 | 46.59 | |
| Gemini 22025.06 | 31.82 | 47.73 | 54.55 | |
| o3mini2025.06 | 30.68 | 44.32 | 54.55 | |
| MDAgentsbackbone=DeepSeek-V32025.06 | 29.55 | 43.18 | 45.45 | |
| MDAgentsbackbone=GPT-4o2025.06 | 27.27 | 40.91 | 46.59 | |
| PhenoBrain2025.06 | 22.35 | 32.94 | 42.35 | |
| MMedS-Llama 32025.06 | 17.04 | 29.55 | 31.82 | |
| PubCaseFinder2025.06 | 7.32 | 13.41 | 15.85 |