OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/cus-cus/opus-2020-10-04
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	eng-eng	tatoeba-test-v2021-03-30	show	0
1	eng-eng	tatoeba-test-v2021-08-07	show	0
2	eng-som	flores101-devtest	show	0.9
3	eng-som	flores200-devtest	show	0.9
4	eng-som	ntrex128	show	0.9
5	eng-som	tico19-test	show	0.6
6	som-eng	flores101-devtest	show	2.7
7	som-eng	flores200-devtest	show	2.7
8	som-eng	ntrex128	show	2.3
9	som-eng	tico19-test	show	1.2
			average	1.220