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

OPUS-MT Dashboard

Model Scores (selected model)

IDLanguageBenchmarkOutputbleu
0dan-estflores101-devtestshow 18
1dan-finflores101-devtestshow 17
2dan-fintatoeba-test-v2021-08-07show 35.3
3dan-hunflores101-devtestshow 17.3
4isl-estflores101-devtestshow 9
5isl-finflores101-devtestshow 8.3
6isl-hunflores101-devtestshow 9
7nno-fintatoeba-test-v2020-07-28show 26.5
8nno-fintatoeba-test-v2021-03-30show 26.5
9nno-fintatoeba-test-v2021-08-07show 26.4
10nob-estflores101-devtestshow 14.6
11nob-finflores101-devtestshow 13.6
12nob-fintatoeba-test-v2021-08-07show 34.5
13nob-hunflores101-devtestshow 14.7
14nor-fintatoeba-test-v2020-07-28show 32
15nor-fintatoeba-test-v2021-03-30show 32
16nor-fintatoeba-test-v2021-08-07show 32
17swe-estflores101-devtestshow 17.4
18swe-finfiskmo_testsetshow 22.4
19swe-finflores101-devtestshow 17.9
20swe-fintatoeba-test-v2020-07-28show 41.3
21swe-fintatoeba-test-v2021-03-30show 41.2
22swe-fintatoeba-test-v2021-08-07show 40.9
23swe-hunflores101-devtestshow 17
24swe-huntatoeba-test-v2021-08-07show 39.8
average24.184

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