| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| HealthBench treatment-related conversations | TheraAgent | Overall Score48.94 | 15 | 26d ago | |
| External Cohort | Brain-WM | Accuracy83.5 | 12 | 2mo ago | |
| Internal Cohort | Brain-WM | Accuracy91.5 | 12 | 2mo ago | |
| LDR-PB (test) | Number of Nodes (#N)304 | 6 | 3mo ago | ||
| WSI-Bench | WSI-LLaVA | WSI Precision (Open Set)81 | 5 | 2mo ago |
