OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/it-de/opus-2020-01-20
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	ita-deu	flores101-devtest	show	22.2
1	ita-deu	newssyscomb2009	show	22.4
2	ita-deu	newstest2009	show	21.3
3	ita-deu	tatoeba-test-v2020-07-28	show	48.3
4	ita-deu	tatoeba-test-v2021-03-30	show	48.3
5	ita-deu	tatoeba-test-v2021-08-07	show	48.5
			average	35.167