OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/ara-fra/opus-2020-06-18
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-fra	flores200-devtest	show	21.1
1	ara-fra	flores101-devtest	show	27.5
2	ara-fra	flores200-devtest	show	27.5
3	ara-fra	tatoeba-test-v2020-07-28	show	39.3
4	ara-fra	tatoeba-test-v2021-03-30	show	39.3
5	ara-fra	tatoeba-test-v2021-08-07	show	39.3
6	ara-fra	tico19-test	show	22.1
7	ary-fra	flores200-devtest	show	14.2
8	arz-fra	flores200-devtest	show	19.1
			average	27.711