| ID | Language | Benchmark | Output | bleu |
|---|---|---|---|---|
| 0 | fin-eng | flores101-devtest | show | 30.4 |
| 1 | fin-eng | flores200-devtest | show | 30.5 |
| 2 | fin-eng | newstest2015 | show | 26.5 |
| 3 | fin-eng | newstest2016 | show | 28.8 |
| 4 | fin-eng | newstest2017 | show | 31.9 |
| 5 | fin-eng | newstest2018 | show | 23.8 |
| 6 | fin-eng | newstest2019 | show | 28.6 |
| 7 | fin-eng | newstestB2016 | show | 24.3 |
| 8 | fin-eng | newstestB2017 | show | 27 |
| 9 | fin-eng | ntrex128 | show | 25.1 |
| 10 | fin-eng | tatoeba-test-v2020-07-28 | show | 53.7 |
| 11 | fin-eng | tatoeba-test-v2021-03-30 | show | 53.7 |
| 12 | fin-eng | tatoeba-test-v2021-08-07 | show | 53.5 |
| average | 33.677 |