| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Question Answering | NaturalQA | Accuracy38 | 66 | |
| Question Answering | NaturalQA (test) | Accuracy67.4 | 39 | |
| Uncertainty Estimation | NaturalQA | AUROC77 | 39 | |
| Question Answering | NaturalQA | EM38.92 | 26 | |
| Abstention Classification | NaturalQA (test) | Accuracy (Abs=0)100 | 9 |