OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/grk-eng/opus2m-2020-08-01
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	ell-eng	flores101-devtest	show	27.4
1	ell-eng	flores200-devtest	show	27.4
2	ell-eng	ntrex128	show	30.4
3	ell-eng	tatoeba-test-v2020-07-28	show	65.9
4	ell-eng	tatoeba-test-v2021-03-30	show	64.5
5	ell-eng	tatoeba-test-v2021-08-07	show	63.5
6	grc-eng	tatoeba-test-v2020-07-28	show	4.2
7	grc-eng	tatoeba-test-v2021-03-30	show	4.1
8	grc-eng	tatoeba-test-v2021-08-07	show	4
			average	32.378