OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/lav-eng/opus+bt-2021-04-30
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	lav-eng	flores101-devtest	show	35.4
1	lav-eng	newstest2017	show	24
2	lav-eng	ntrex128	show	28.9
3	lav-eng	tatoeba-test-v2020-07-28	show	57.1
4	lav-eng	tatoeba-test-v2021-03-30	show	57.1
5	lav-eng	tatoeba-test-v2021-08-07	show	57.1
6	ltg-eng	flores200-devtest	show	6.3
			average	37.986