OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/deu-isl/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	deu-isl	flores101-devtest	show	13.8
1	deu-isl	flores200-devtest	show	13.8
2	deu-isl	ntrex128	show	12.9
3	deu-isl	tatoeba-test-v2020-07-28	show	26.9
4	deu-isl	tatoeba-test-v2021-03-30	show	27.5
5	deu-isl	tatoeba-test-v2021-08-07	show	26.9
			average	20.300