| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Natural Language Processing | decaNLP Tasks (unseen) | AN'34.69 | 14 | |
| Natural Language Processing | decaNLP Tasks seen (test) | AN Score77.97 | 14 | |
| Multitask Natural Language Processing | DecaNLP SQuAD 2.0, WikiSQL, SST, QA-SRL, WOZ (test) | Average Score78.2 | 11 | |
| Continual Learning | decaNLP WOZ, QA-SRL, SST, WikiSQL, SQuAD reversed order (test) | Average Score78.2 | 9 |