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

OPUS-MT Dashboard

Model Scores (selected model)

IDLanguageBenchmarkOutputbleu
0ind-cmn_Hansflores101-devtestshow 0.2
1ind-cmn_Hansflores200-devtestshow 0.2
2ind-cmn_Hantflores101-devtestshow 0.2
3ind-cmn_Hantflores200-devtestshow 0.2
4ind-yueflores200-devtestshow 0.1
5ind-yuentrex128show 0
6msa-cmn_Hansflores101-devtestshow 0.2
7msa-cmn_Hansflores200-devtestshow 0.1
8msa-cmn_Hantflores101-devtestshow 0.2
9msa-cmn_Hantflores200-devtestshow 0.2
10msa-yueflores200-devtestshow 0.1
11msa-yuentrex128show 0
12msa-zhotatoeba-test-v2020-07-28show 17.4
13msa-zhotatoeba-test-v2021-03-30show 17
14msa-zhotatoeba-test-v2021-08-07show 17.4
15msa-zhotico19-testshow 0.6
16zsm-cmn_Hansflores200-devtestshow 0.1
17zsm-cmn_Hantflores200-devtestshow 0.2
18zsm-yueflores200-devtestshow 0.1
average2.868

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