| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Error Detection | Mintaka (val) | Precision100 | 36 | |
| Error Detection | Mintaka | F1 Score88 | 36 | |
| Hallucination prediction | Mintaka refined by question type and domain | AUROC75.51 | 20 | |
| Hallucination prediction | Mintaka refined by question type | AUROC77.89 | 20 | |
| Hallucination prediction | Mintaka (original) | AUROC79.41 | 10 | |
| Hallucination prediction | Mintaka unrefined (original) | AUROC79.41 | 10 | |
| Retrieval | Mintaka | Recall82.7 | 7 |