| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Short-form generation ID | HBO | PRR67 | 38 | 3mo ago | |
| TriviaQA | SeSE | AUROC0.87 | 32 | 1mo ago | |
| SVAMP | P(True) | AUROC90 | 32 | 1mo ago | |
| SQuAD | SeSE | AUROC83 | 32 | 1mo ago | |
| NQ-Open | AUROC83 | 32 | 1mo ago | ||
| BioASQ | SeSE | AUROC84 | 32 | 1mo ago | |
| Short-form generation datasets 1D-DiffTask most OOD | MSP | PRR0.64 | 24 | 3mo ago | |
| DiffTask OOD | MSP | PRR0.64 | 24 | 3mo ago | |
| Short-form generation datasets 1D-SameTask - OOD | MSP | PRR0.64 | 24 | 3mo ago | |
| Short-form generation datasets LOO - near OOD | MSP | PRR0.64 | 24 | 3mo ago | |
| 1D-DiffTask Short-form generation | MSP | PRR64 | 14 | 3mo ago | |
| DiffTask Short-form generation | MSP | PRR0.64 | 14 | 3mo ago | |
| Short-form generation 1D-SameTask | MSP | PRR0.64 | 14 | 3mo ago | |
| Short-form generation LOO | MSP | PRR64 | 14 | 3mo ago |