OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/fin-zle/opus4m+btTCv20210807-2022-01-19
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

orange = OPUS-MT, blue = Tatoeba-MT models, red = HPLT-MT models
green = student models, grey = external models, purple = user-contributed
render chart with [gd] [plotly]

Model Scores (selected model)

ID	Language	Benchmark	Output	bleu
0	fin-rus	flores101-devtest	show	19.8
1	fin-rus	flores200-devtest	show	19.7
2	fin-rus	ntrex128	show	16.2
3	fin-rus	tatoeba-test-v2020-07-28	show	45.8
4	fin-rus	tatoeba-test-v2021-03-30	show	45.8
5	fin-rus	tatoeba-test-v2021-08-07	show	45.8
6	fin-ukr	flores101-devtest	show	17.7
7	fin-ukr	flores200-devtest	show	17.7
8	fin-ukr	ntrex128	show	15
			average	27.056