| ID | Language | Benchmark | Output | bleu |
|---|---|---|---|---|
| 0 | fin-eng | flores101-devtest | show | 31.6 |
| 1 | fin-eng | flores200-devtest | show | 31.5 |
| 2 | fin-eng | newstest2015 | show | 26.7 |
| 3 | fin-eng | newstest2016 | show | 29.7 |
| 4 | fin-eng | newstest2017 | show | 32.9 |
| 5 | fin-eng | newstest2018 | show | 24.1 |
| 6 | fin-eng | newstest2019 | show | 29.2 |
| 7 | fin-eng | newstestB2016 | show | 24.5 |
| 8 | fin-eng | newstestB2017 | show | 27.5 |
| 9 | fin-eng | ntrex128 | show | 25.9 |
| 10 | fin-eng | tatoeba-test-v2020-07-28 | show | 53.5 |
| 11 | fin-eng | tatoeba-test-v2021-03-30 | show | 53.5 |
| 12 | fin-eng | tatoeba-test-v2021-08-07 | show | 53.3 |
| average | 34.146 |