OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/deu-fin/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	deu-fin	flores101-devtest	show	18.7
1	deu-fin	flores200-devtest	show	18.6
2	deu-fin	goethe-institute-test1	show	18.1
3	deu-fin	goethe-institute-test2	show	17.7
4	deu-fin	ntrex128	show	14.7
5	deu-fin	tatoeba-test-v2020-07-28	show	40.2
6	deu-fin	tatoeba-test-v2021-03-30	show	40.1
7	deu-fin	tatoeba-test-v2021-08-07	show	40.3
			average	26.050