OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/nb+nn+no+nb_NO+nn_NO+no_nb-en/opus-2020-05-22
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	nno-eng	tatoeba-test-v2021-08-07	show	57.7
1	nob-eng	flores101-devtest	show	38.6
2	nob-eng	tatoeba-test-v2021-08-07	show	61.4
3	nor-eng	tatoeba-test-v2021-08-07	show	61.1
			average	54.700