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

OPUS-MT Dashboard

Model Scores (selected model)

IDLanguageBenchmarkOutputbleu
0ces-engflores101-devtestshow 31.2
1ces-engflores200-devtestshow 31.1
2ces-enggeneraltest2022show (logfile)42.9
3ces-engmulti30k_test_2016_flickrshow 32.2
4ces-engmulti30k_test_2018_flickrshow 31
5ces-engnewssyscomb2009show 25.5
6ces-engnewstest2008show (logfile)22.2
7ces-engnewstest2009show 24.4
8ces-engnewstest2010show 24.8
9ces-engnewstest2011show 25.8
10ces-engnewstest2012show 24.7
11ces-engnewstest2013show 27.9
12ces-engnewstest2014show 29.7
13ces-engnewstest2015show 27.3
14ces-engnewstest2016show 28.9
15ces-engnewstest2017show 25.8
16ces-engnewstest2018show 27.1
17ces-engnewstest2021show (logfile)33.4
18ces-engntrex128show (logfile)28.2
19ces-engtatoeba-test-v2020-07-28show 53.2
20ces-engtatoeba-test-v2021-03-30show 52.7
21ces-engtatoeba-test-v2021-08-07show 52.2
22pol-engflores101-devtestshow 22.7
23pol-engflores200-devtestshow 22.8
24pol-engnewstest2020show 27.1
25pol-engntrex128show (logfile)22.6
26pol-engtatoeba-test-v2020-07-28show 50.4
27pol-engtatoeba-test-v2021-03-30show 50.4
28pol-engtatoeba-test-v2021-08-07show 50.4
average32.710

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