OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/eng-jpn/opus-2021-02-18
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	eng-jpn	flores101-devtest	show	18.2
1	eng-jpn	flores200-devtest	show	18.1
2	eng-jpn	generaltest2022	show	1.5
3	eng-jpn	newstest2020	show	15.1
4	eng-jpn	newstest2021	show	15.4
5	eng-jpn	ntrex128	show	0.2
6	eng-jpn	tatoeba-test-v2020-07-28	show	16.8
7	eng-jpn	tatoeba-test-v2021-03-30	show	16.7
8	eng-jpn	tatoeba-test-v2021-08-07	show	16.6
			average	13.178