Rare Disease Diagnosis on RareBench MME
77.5R@1DeepRare
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DeepRarebackbone=Gemini-22025.06 | 77.5 | 85 | 90 | |
| DeepRarebackbone=GPT-4o2025.06 | 72.5 | 77.5 | 82.5 | |
| DeepRarebackbone=Claude-3.72025.06 | 72.5 | 85 | 87.5 | |
| DeepRarebackbone=DeepSeek-V32025.06 | 70 | 77.5 | 77.5 | |
| DeepRarebackbone=DeepSeek-R12025.06 | 67.57 | 81.08 | 83.78 | |
| RAGbackbone=DeepSeek-V32025.06 | 42.5 | 45 | 47.5 | |
| PubCaseFinder2025.06 | 40 | 57.5 | 57.5 | |
| DeepSeek R12025.06 | 35 | 60 | 65 | |
| Claude 3.7 think2025.06 | 27.5 | 50 | 57.5 | |
| PhenoBrain2025.06 | 25 | 45 | 80 | |
| MMedS-Llama 32025.06 | 12.5 | 20 | 20 | |
| DS-R1-search2025.06 | 12.5 | 17.5 | 22.5 | |
| Claude-3.7-Sonnet2025.06 | 7.5 | 27.5 | 32.5 | |
| DeepSeek V32025.06 | 5 | 20 | 27.5 | |
| Gemini 22025.06 | 5 | 7.5 | 10 | |
| Baichuan-14B2025.06 | 5 | 10 | 10 | |
| GPT-4o2025.06 | 2.5 | 5 | 10 | |
| o3mini2025.06 | 2.5 | 7.5 | 7.5 | |
| MDAgentsbackbone=GPT-4o2025.06 | 2.25 | 2.25 | 5 | |
| Gemini 2 think2025.06 | 0 | 5 | 12.5 | |
| MDAgentsbackbone=DeepSeek-V32025.06 | 0 | 0 | 0.025 |