OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/de-es/opus-2020-01-15
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-spa	flores101-devtest	show	21.6
1	deu-spa	newssyscomb2009	show	27
2	deu-spa	newstest2009	show	24.2
3	deu-spa	newstest2010	show	30.2
4	deu-spa	newstest2011	show	28.7
5	deu-spa	newstest2012	show	29.4
6	deu-spa	newstest2013	show	29.5
7	deu-spa	tatoeba-test-v2020-07-28	show	48.7
8	deu-spa	tatoeba-test-v2021-03-30	show	48.8
9	deu-spa	tatoeba-test-v2021-08-07	show	48.8
			average	33.690