| ID | Language | Benchmark | Output | bleu |
|---|---|---|---|---|
| 0 | eng-eng | tatoeba-test-v2021-03-30 | show | 7.7 |
| 1 | eng-eng | tatoeba-test-v2021-08-07 | show | 8.1 |
| 2 | eng-eus | flores200-devtest | show | 9.7 |
| 3 | eng-eus | ntrex128 | show | 7.5 |
| 4 | eng-eus | tatoeba-test-v2020-07-28 | show | 28.2 |
| 5 | eng-eus | tatoeba-test-v2021-03-30 | show | 28.2 |
| 6 | eng-eus | tatoeba-test-v2021-08-07 | show | 28.2 |
| 7 | eus-eng | flores200-devtest | show | 15.2 |
| 8 | eus-eng | ntrex128 | show | 13.8 |
| 9 | eus-eng | tatoeba-test-v2020-07-28 | show | 42.5 |
| 10 | eus-eng | tatoeba-test-v2021-03-30 | show | 42.5 |
| 11 | eus-eng | tatoeba-test-v2021-08-07 | show | 42.4 |
| average | 22.833 |