| Benchmark | Model | Rank | Results |
|---|---|---|---|
| semantic-parsing-on-wikisql | TAPEX-Large (weak supervision) | #2 | Denotation accuracy (test): 89.5 |
| semantic-parsing-on-wikitablequestions | TAPEX-Large | #18 | Accuracy (Test): 57.5Accuracy (Dev): 57.0 |
| table-based-fact-verification-on-tabfact | TAPEX-Large | #6 | Test: 84.2Val: 84.6 |