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

OPUS-MT Dashboard

Model Scores (selected model)

IDLanguageBenchmarkOutputbleu
0deu-engflores101-devtestshow 43.6
1deu-engflores200-devtestshow 43.5
2deu-enggeneraltest2022show (logfile)40.6
3deu-engmulti30k_task2_test_2016show 4.8
4deu-engmulti30k_test_2016_flickrshow 43.6
5deu-engmulti30k_test_2017_flickrshow 42.9
6deu-engmulti30k_test_2017_mscocoshow 37
7deu-engmulti30k_test_2018_flickrshow 39.3
8deu-engnewssyscomb2009show 27.9
9deu-engnewstest2008show (logfile)27.5
10deu-engnewstest2009show 26.5
11deu-engnewstest2010show 31.8
12deu-engnewstest2011show 27.3
13deu-engnewstest2012show 29.8
14deu-engnewstest2013show 32.9
15deu-engnewstest2014show 34.8
16deu-engnewstest2015show 36.2
17deu-engnewstest2016show 41.9
18deu-engnewstest2017show 37
19deu-engnewstest2018show 43.8
20deu-engnewstest2019show 34.6
21deu-engnewstest2020show 30.7
22deu-engnewstest2021show (logfile)43.7
23deu-engnewstestALL2020show (logfile)42.3
24deu-engnewstestB2020show 30.6
25deu-engntrex128show (logfile)40.2
26deu-engtatoeba-test-v2020-07-28show 57.6
27deu-engtatoeba-test-v2021-03-30show 56.5
28deu-engtatoeba-test-v2021-08-07show 54.9
show allaverage37.372

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