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

OPUS-MT Dashboard

Model Scores (selected model)

IDLanguageBenchmarkOutputbleu
0est-engflores101-devtestshow 25.5
1est-engflores200-devtestshow 25.6
2est-engnewstest2018show 22.1
3est-engntrex128show (logfile)21.3
4est-engtatoeba-test-v2020-07-28show 46.5
5est-engtatoeba-test-v2021-03-30show 46.5
6est-engtatoeba-test-v2021-08-07show 46.6
7fin-engflores101-devtestshow 22.9
8fin-engflores200-devtestshow 22.9
9fin-engnewstest2015show 20.2
10fin-engnewstest2016show 21.9
11fin-engnewstest2017show 24.4
12fin-engnewstest2018show 18.6
13fin-engnewstest2019show 20.6
14fin-engnewstestB2016show 18.3
15fin-engnewstestB2017show 20.6
16fin-engntrex128show (logfile)19.5
17fin-engtatoeba-test-v2020-07-28show 40.9
18fin-engtatoeba-test-v2021-03-30show 40.8
19fin-engtatoeba-test-v2021-08-07show 40.9
20hun-engflores101-devtestshow 23
21hun-engflores200-devtestshow 23
22hun-engnewssyscomb2009show 18.5
23hun-engnewstest2008show (logfile)15.9
24hun-engnewstest2009show 18
25hun-engntrex128show (logfile)15.4
26hun-engtatoeba-test-v2020-07-28show 36.9
27hun-engtatoeba-test-v2021-03-30show 35.8
28hun-engtatoeba-test-v2021-08-07show 35.5
29liv-enggeneraltest2022show (logfile)1.3
average26.330

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