| ID | Language | Benchmark | Output | bleu |
|---|---|---|---|---|
| 0 | fin-eng | flores101-devtest | show (logfile) | 31.7 |
| 1 | fin-eng | flores200-devtest | show (logfile) | 31.7 |
| 2 | fin-eng | newstest2015 | show (logfile) | 26.7 |
| 3 | fin-eng | newstest2016 | show (logfile) | 30 |
| 4 | fin-eng | newstest2017 | show (logfile) | 33 |
| 5 | fin-eng | newstest2018 | show (logfile) | 24.2 |
| 6 | fin-eng | newstest2019 | show (logfile) | 30.7 |
| 7 | fin-eng | newstestB2017 | show (logfile) | 28.6 |
| 8 | fin-eng | ntrex128 | show (logfile) | 25.2 |
| 9 | fin-eng | tatoeba-test-v2020-07-28 | show (logfile) | 51.6 |
| 10 | fin-eng | tatoeba-test-v2021-03-30 | show (logfile) | 51.5 |
| 11 | fin-eng | tatoeba-test-v2021-08-07 | show (logfile) | 51.3 |
| average | 34.683 |