OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/ara-spa/opus-2021-02-23
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	apc-spa	flores200-devtest	show	15.8
1	ara-spa	flores101-devtest	show	18.8
2	ara-spa	flores200-devtest	show	18.7
3	ara-spa	tatoeba-test-v2020-07-28	show	47.2
4	ara-spa	tatoeba-test-v2021-03-30	show	47.2
5	ara-spa	tatoeba-test-v2021-08-07	show	47.2
6	ara-spa	tico19-test	show (logfile)	30.6
7	arz-spa	flores200-devtest	show	14.8
			average	30.037