Rare Disease Diagnosis on RareBench RAMEDIS
73.23Recall@1DeepRare
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DeepRarebackbone=GPT-4o2025.06 | 73.23 | 81.57 | 85.26 | |
| DeepRarebackbone=DeepSeek-V32025.06 | 72.6 | 82.85 | 84.62 | |
| DeepRarebackbone=Claude-3.72025.06 | 70.03 | 81.57 | 84.46 | |
| DeepRarebackbone=DeepSeek-R12025.06 | 62.17 | 76.28 | 79.32 | |
| DeepRarebackbone=Gemini-22025.06 | 49.67 | 69.55 | 75.64 | |
| Claude-3.7-Sonnet2025.06 | 42.47 | 68.59 | 73.88 | |
| Claude 3.7 think2025.06 | 41.83 | 63.78 | 72.92 | |
| Gemini 22025.06 | 40.37 | 52.56 | 60.42 | |
| DeepSeek V32025.06 | 40.06 | 66.51 | 72.11 | |
| DS-R1-search2025.06 | 39.9 | 66.51 | 71.31 | |
| o3mini2025.06 | 39.42 | 64.42 | 67.47 | |
| MDAgentsbackbone=GPT-4o2025.06 | 37.82 | 58.01 | 62.98 | |
| Baichuan-14B2025.06 | 37.66 | 64.26 | 68.75 | |
| MDAgentsbackbone=DeepSeek-V32025.06 | 36.22 | 59.29 | 63.3 | |
| GPT-4o2025.06 | 35.47 | 52.24 | 61.06 | |
| Gemini 2 think2025.06 | 33.97 | 50.8 | 58.65 | |
| DeepSeek R12025.06 | 33.17 | 47.6 | 53.21 | |
| MMedS-Llama 32025.06 | 30.45 | 45.67 | 50 | |
| RAGbackbone=DeepSeek-V32025.06 | 28.57 | 46.1 | 50.16 | |
| PubCaseFinder2025.06 | 25.84 | 32.58 | 39.97 | |
| PhenoBrain2025.06 | 20.67 | 38.3 | 55.77 |