Rare Disease Diagnosis on RareBench LIRICAL
55.95R@1DeepRare
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DeepRarebackbone=DeepSeek-V32025.06 | 55.95 | 65.16 | 67.57 | |
| DeepRarebackbone=DeepSeek-R12025.06 | 52.43 | 63.51 | 67.84 | |
| DeepRarebackbone=GPT-4o2025.06 | 51.62 | 62.7 | 65.4 | |
| DeepRarebackbone=Gemini-22025.06 | 48.91 | 63.24 | 68.91 | |
| DeepRarebackbone=Claude-3.72025.06 | 40 | 51.08 | 54.86 | |
| Claude 3.7 think2025.06 | 38.11 | 50.27 | 52.43 | |
| PubCaseFinder2025.06 | 37.77 | 47.01 | 48.91 | |
| DeepSeek R12025.06 | 36.76 | 45.14 | 47.57 | |
| DS-R1-search2025.06 | 33.51 | 45.41 | 49.46 | |
| DeepSeek V32025.06 | 33.24 | 42.97 | 45.68 | |
| Claude-3.7-Sonnet2025.06 | 33.24 | 46.49 | 50 | |
| GPT-4o2025.06 | 31.08 | 42.16 | 48.92 | |
| Gemini 22025.06 | 30.81 | 39.73 | 43.51 | |
| Gemini 2 think2025.06 | 30.81 | 41.35 | 44.05 | |
| RAGbackbone=DeepSeek-V32025.06 | 29.46 | 36.76 | 39.46 | |
| PhenoBrain2025.06 | 27.1 | 44.72 | 57.72 | |
| Baichuan-14B2025.06 | 26.77 | 37.03 | 40.27 | |
| o3mini2025.06 | 25.68 | 35.41 | 40 | |
| MDAgentsbackbone=DeepSeek-V32025.06 | 23.24 | 28.11 | 31.08 | |
| MDAgentsbackbone=GPT-4o2025.06 | 21.89 | 28.92 | 31.08 | |
| MMedS-Llama 32025.06 | 21.08 | 29.73 | 33.51 |