| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| DDxBench n = 150 | PathChat+ | Top-1 Accuracy (Primary Diagnosis)80 | 9 | 2mo ago | |
| Eurorad (test) | Qwen3-VL-30B | Diagnostic Accuracy (Baseline)74.9 | 7 | 9d ago | |
| HISTAI | ANTONI-α | Accuracy (%)0.6845 | 7 | 3mo ago | |
| Intra-operative Differential Diagnosis (Intra-Diagnosis) | BRAVE | Macro-AUC96.4 | 5 | 22d ago | |
| Pre-operative Differential Diagnosis (Pre-Diagnosis) | BRAVE | Macro-AUC98 | 5 | 22d ago | |
| Ours SymptomAI | SymptomAI | Top-5 Accuracy75.2 | 1 | 28d ago | |
| Ours Auxiliary | SymptomAI | Top-5 Accuracy80 | 1 | 28d ago | |
| Symptom Checker Vignettes | SymptomAI | Top-5 Accuracy91.5 | 1 | 28d ago | |
| NEJM Case Reports | SymptomAI | Top-5 Accuracy81.6 | 1 | 28d ago |