| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Note-table consistency verification | EHRCon Nursing notes | Recall72.53 | 16 | |
| Note-table consistency verification | EHRCon Physician notes | Recall79.58 | 16 | |
| Note-table consistency verification | EHRCon Discharge notes | Recall77.36 | 16 | |
| STRING | EHRCon | LLM Judge Accuracy67.4 | 9 | |
| Agentic Task Solving | EHRCon | Pass@379.1 | 9 | |
| String Extraction | EHRCon | Exact Match67.4 | 9 |