ID | Benchmark (bleu) | Output | OPUS-MT | bleu | external | bleu | Diff |
---|---|---|---|---|---|---|---|
0 | flores200-devtest | compare | deu+eng+fra+...2024-05-30 | 11.6 | facebook/nll...illed-1.3B | 17.9 | -6.3 |
1 | tatoeba-test-v2020-07-28 | compare | deu+eng+fra+...2024-05-30 | 22.3 | facebook/nll...illed-1.3B | 29.4 | -7.1 |
2 | tatoeba-test-v2021-03-30 | compare | deu+eng+fra+...2024-05-30 | 22.4 | facebook/nll...illed-1.3B | 29.8 | -7.4 |
3 | tatoeba-test-v2021-08-07 | compare | deu+eng+fra+...2024-05-30 | 22.5 | facebook/nll...illed-1.3B | 29.8 | -7.3 |
average | 19.7 | 26.7 | -7.0 |