| Benchmark | Model | Rank | Results |
|---|---|---|---|
| grammatical-error-correction-on-bea-2019-test | Majority-voting ensemble on best 7 models | #1 | F0.5: 81.4 |
| grammatical-error-correction-on-conll-2014-shared-task | Ensembles of best 7 models + GRECO + GTP-rerank | #1 | F0.5: 72.8Precision: 83.9Recall: 47.5 |
| grammatical-error-correction-on-conll-2014-shared-task | Majority-voting ensemble on best 7 models | #2 | F0.5: 71.8Precision: 83.7Recall: 45.7 |