[restart] [share link] select language: [swap] [compare scores] [compare models] [map] [release history] [uploads]

OPUS-MT Dashboard

Model Scores (comparing between OPUS-MT and external models)

IDBenchmark (bleu)OutputOPUS-MTbleuexternalbleuDiff
0flores101-devtestcomparefra-eng/opus..2022-03-0946facebook/nllb-200-3.3B45.4 0.6
1flores200-devtestcomparefra-eng/opus..2022-03-0946facebook/nllb-200-3.3B45.7 0.3
2multi30k_test_2016_flickrcomparefra-eng/opus..2022-03-0949.7facebook/nll..illed-1.3B49.5 0.2
3multi30k_test_2017_flickrcomparefra-eng/opus..2022-03-0952facebook/nllb-200-1.3B50.7 1.3
4multi30k_test_2017_mscococomparefra-eng/opus..2022-03-0950.6facebook/nll..illed-1.3B50.9-0.3
5multi30k_test_2018_flickrcomparefra-eng/opus..2022-03-0944.9facebook/nllb-200-1.3B44.9 0.0
6newsdiscusstest2015comparefra-eng/opus..2022-03-0940.2facebook/nllb-200-3.3B36.6 3.6
7newssyscomb2009comparefra-eng/opus..2022-03-0931.1facebook/nllb-200-1.3B30.7 0.4
8newstest2008comparefra-eng/opus..2022-03-0926.5facebook/nllb-200-1.3B26.7-0.2
9newstest2009comparefra-eng/opus-2021-02-1930.5facebook/nllb-200-1.3B30.1 0.4
10newstest2010comparefra-eng/opus..2022-03-0933.4facebook/nllb-200-1.3B34.1-0.7
11newstest2011comparefra-eng/opus..2022-03-0933.8facebook/nllb-200-3.3B33.8 0.0
12newstest2012comparefra-eng/opus..2022-03-0933.6facebook/nllb-200-3.3B33.5 0.1
13newstest2013comparefra-eng/opus..2022-03-0934.8facebook/nllb-200-1.3B34.7 0.1
14newstest2014comparefra-eng/opus..2022-03-0939.4facebook/nllb-200-3.3B40.3-0.9
15tatoeba-test-v2020-07-28comparefra-eng/opus..2022-03-0959.2facebook/nllb-200-3.3B60.2-1.0
16tatoeba-test-v2021-03-30comparefra-eng/opus..2022-03-0959.5facebook/nllb-200-3.3B60.6-1.1
17tatoeba-test-v2021-08-07comparefra-eng/opus..2022-03-0959.8facebook/nllb-200-3.3B60-0.2
18tico19-testcomparefra-eng/opus..2022-03-0941.3facebook/nllb-200-3.3B43.4-2.1
average42.842.7 0.0

GitHub: [OPUS] [OPUS-MT] [benchmarks] [leaderboards] [dashboard]