OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/ukr-slv/opus-2021-02-19
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	ukr-slv	flores101-devtest	show	16.2
1	ukr-slv	flores200-devtest	show	16.1
2	ukr-slv	ntrex128	show	14.4
3	ukr-slv	tatoeba-test-v2020-07-28	show	12.1
4	ukr-slv	tatoeba-test-v2021-03-30	show	11.5
5	ukr-slv	tatoeba-test-v2021-08-07	show	12
			average	13.717