OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: wmt22/Online-W
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	ces-eng	generaltest2022	show	68.7
1	deu-eng	generaltest2022	show	48.8
2	deu-fra	generaltest2022	show	43.6
3	eng-ces	generaltest2022	show	53.1
4	eng-deu	generaltest2022	show	48.9
5	eng-rus	generaltest2022	show	32.4
6	eng-zho	generaltest2022	show	16.4
7	fra-deu	generaltest2022	show	64.8
8	jpn-eng	generaltest2022	show	27.8
9	rus-eng	generaltest2022	show	42.6
			average	44.710