Pathological Multimodal Understanding on PathMMU ALL (test)
72.9PubMed Accuracy
Expert Performance
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2025.12 | 72.9 | 71.8 | 71.5 | 69 | 68.3 | 78.9 | |
2025.12 | 71.8 | 68 | 68.9 | 69.8 | 69.5 | 58.1 | |
2025.12 | 69.9 | - | - | 70.6 | 70.6 | 79 | |
2025.12 | 66.4 | 65.7 | 68.4 | 73.9 | 77.7 | 46.6 | |
2025.12 | 59.9 | 58.4 | 58.7 | 60.5 | 65.1 | 49.7 | |
2025.12 | 57.2 | 54.5 | 65.8 | 56.1 | 58.3 | 35.7 | |
2025.12 | 56.2 | 52.3 | 59.6 | 54.1 | 61.3 | 31.9 | |
2025.12 | 54.9 | 50.6 | 56.7 | 56 | 59.4 | 26.9 | |
2025.12 | 54.4 | 51.5 | 56.3 | 53.7 | 55.1 | 37.9 | |
2025.12 | 53.9 | 49.9 | 53.4 | 53.9 | 52.6 | 33.9 | |
2025.12 | 48.8 | 40.4 | 40.4 | 41.9 | 40.4 | 24.4 | |
2025.12 | 41.9 | 41.2 | 45.9 | 45 | 43.7 | 30.1 | |
2025.12 | 41.4 | 37.7 | 40.1 | 39.9 | 43.4 | 23.7 | |
2025.12 | 40.6 | 37.6 | 39.2 | 42.3 | 38.7 | 25.3 | |
2025.12 | 36.9 | 34 | 37.7 | 37.4 | 38.8 | 19.5 | |
2025.12 | 28.5 | 26.8 | 28.2 | 27.4 | 30.4 | 20.1 |