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

OPUS-MT Dashboard

Model Scores (selected model)

IDLanguageBenchmarkOutputbleu
0fin-cmn_Hansflores101-devtestshow 0.2
1fin-cmn_Hansflores200-devtestshow 0.2
2fin-cmn_Hantflores101-devtestshow 0.1
3fin-cmn_Hantflores200-devtestshow 0.1
4fin-yueflores200-devtestshow (logfile)0
5fin-yuentrex128show (logfile)0
6hun-cmn_Hansflores101-devtestshow 0.2
7hun-cmn_Hansflores200-devtestshow 0.2
8hun-cmn_Hanstatoeba-test-v2020-07-28show 0.7
9hun-cmn_Hanstatoeba-test-v2021-03-30show 0.7
10hun-cmn_Hanstatoeba-test-v2021-08-07show 0.7
11hun-cmn_Hantflores101-devtestshow 0.3
12hun-cmn_Hantflores200-devtestshow 0.3
13hun-yueflores200-devtestshow (logfile)0
14hun-yuentrex128show (logfile)0
average0.247

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