| Benchmark | Model | Rank | Results |
|---|---|---|---|
| grammatical-error-correction-on-restricted | CNN Seq2Seq | #1 | F0.5: 70.14 (measured by Ge et al., 2018) |
| grammatical-error-correction-on-conll-2014-shared-task-10-annotations | CNN Seq2Seq | #2 | F0.5: 70.14 |
| grammatical-error-correction-on-jfleg | CNN Seq2Seq | #5 | GLEU: 57.47 |
| grammatical-error-correction-on-conll-2014-shared-task | CNN Seq2Seq | #22 | F0.5: 54.79 |