[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 (comet)OutputOPUS-MTcometexternalcometDiff
0flores101-devtestcomparefra-eng/opus..2022-03-090.811facebook/nllb-200-3.3B0.79730.014
1flores200-devtestcompareroa-deu+eng+..2024-05-300.8902facebook/nllb-200-3.3B0.79730.093
2multi30k_test_2016_flickrcompareroa-deu+eng+..2024-05-300.8839facebook/nll..illed-1.3B0.81450.069
3multi30k_test_2017_flickrcompareroa-deu+eng+..2024-05-300.8903facebook/nllb-200-1.3B0.79180.099
4multi30k_test_2017_mscococompareroa-deu+eng+..2024-05-300.8764facebook/nll..illed-1.3B0.80570.071
5multi30k_test_2018_flickrcompareroa-deu+eng+..2024-05-300.8666facebook/nll..illed-1.3B0.71850.148
6newsdiscusstest2015compareroa-deu+eng+..2024-05-300.8395facebook/nll..illed-1.3B0.57280.267
7newssyscomb2009compareitc-deu+eng+..2024-05-300.8349facebook/nllb-200-3.3B0.55760.277
8newstest2008showitc-gmw/opus..2022-08-230.82250.823
9newstest2009compareroa-deu+eng+..2024-05-300.8235facebook/nll..illed-1.3B0.5560.267
10newstest2010comparedeu+eng+fra+..2024-05-300.8321facebook/nllb-200-1.3B0.5940.238
11newstest2011compareroa-deu+eng+..2024-05-300.8349facebook/nllb-200-3.3B0.58330.252
12newstest2012compareroa-deu+eng+..2024-05-300.8337facebook/nllb-200-1.3B0.56490.269
13newstest2013compareitc-deu+eng+..2024-05-300.8497facebook/nllb-200-3.3B0.61590.234
14newstest2014compareroa-deu+eng+..2024-05-300.8649facebook/nll..illed-1.3B0.68780.177
15ntrex128showfra-eng/opus..2022-03-090.86860.869
16tatoeba-test-v2020-07-28compareroa-deu+eng+..2024-05-300.9221facebook/nllb-200-3.3B0.9110.011
17tatoeba-test-v2021-03-30comparefra-eng/opus..2022-03-090.923facebook/nllb-200-3.3B0.91370.009
18tatoeba-test-v2021-08-07compareroa-deu+eng+..2024-05-300.9209facebook/nllb-200-3.3B0.89750.023
19tico19-testcompareroa-deu+eng+..2024-05-300.8271facebook/nll..illed-1.3B0.5060.321
average0.8610.7050.156