| ID | Language | Benchmark | Output | bleu |
|---|---|---|---|---|
| 0 | est-afr | flores101-devtest | show | 10.9 |
| 1 | est-deu | flores101-devtest | show | 19.5 |
| 2 | est-deu | tatoeba-test-v2020-07-28 | show | 47.5 |
| 3 | est-deu | tatoeba-test-v2021-03-30 | show | 47.2 |
| 4 | est-deu | tatoeba-test-v2021-08-07 | show | 47.2 |
| 5 | est-nld | flores101-devtest | show | 16.3 |
| 6 | fin-afr | flores101-devtest | show | 9.8 |
| 7 | fin-deu | flores101-devtest | show | 17.9 |
| 8 | fin-deu | tatoeba-test-v2020-07-28 | show | 43.9 |
| 9 | fin-deu | tatoeba-test-v2021-03-30 | show | 43.9 |
| 10 | fin-deu | tatoeba-test-v2021-08-07 | show | 44 |
| 11 | fin-nld | flores101-devtest | show | 15.7 |
| 12 | fin-nld | tatoeba-test-v2020-07-28 | show | 58.5 |
| 13 | fin-nld | tatoeba-test-v2021-03-30 | show | 58.2 |
| 14 | fin-nld | tatoeba-test-v2021-08-07 | show | 58.3 |
| average | 35.920 |