| ID | Language | Benchmark | Output | bleu |
|---|---|---|---|---|
| 0 | fin-eng | flores101-devtest | show (logfile) | 29.2 |
| 1 | fin-eng | flores200-devtest | show (logfile) | 29.2 |
| 2 | fin-eng | newstest2015 | show (logfile) | 25.4 |
| 3 | fin-eng | newstest2016 | show (logfile) | 28 |
| 4 | fin-eng | newstest2017 | show (logfile) | 30.8 |
| 5 | fin-eng | newstest2018 | show (logfile) | 22.5 |
| 6 | fin-eng | newstest2019 | show (logfile) | 30.2 |
| 7 | fin-eng | newstestB2017 | show (logfile) | 27 |
| 8 | fin-eng | ntrex128 | show (logfile) | 22.7 |
| 9 | fin-eng | tatoeba-test-v2020-07-28 | show (logfile) | 46.6 |
| 10 | fin-eng | tatoeba-test-v2021-03-30 | show (logfile) | 46.6 |
| 11 | fin-eng | tatoeba-test-v2021-08-07 | show (logfile) | 46.4 |
| average | 32.050 |