| ID | Benchmark (bleu) | Output | OPUS-MT | bleu | external | bleu | Diff |
|---|---|---|---|---|---|---|---|
| 0 | flores200-devtest | compare | mul-deu+eng+...2024-05-30 | 12.3 | facebook/nll...illed-1.3B | 22.4 | -10.1 |
| 1 | tatoeba-test-v2020-07-28 | compare | mul-deu+eng+...2024-05-30 | 23.9 | facebook/nll...illed-1.3B | 33.2 | -9.3 |
| 2 | tatoeba-test-v2021-03-30 | compare | mul-deu+eng+...2024-05-30 | 23.7 | facebook/nll...illed-1.3B | 33.1 | -9.4 |
| 3 | tatoeba-test-v2021-08-07 | compare | mul-deu+eng+...2024-05-30 | 23.8 | facebook/nll...illed-1.3B | 33.1 | -9.3 |
| average | 20.9 | 30.5 | -9.5 |