OPUS-MT Dashboard

Language pair: ara-ell [all languages]
Models: [all models] [OPUS-MT] [external] [compare]
Benchmark: [all benchmarks] [average score] flores101-devtest
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart][scatterplot] [size] [type]

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 (bleu scores on the "flores101-devtest" testset)

ID	bleu	Output	Model	Size	Link
7	19.1	show	facebook/nll...illed-1.3B	1331.2M	URL
6	18.0	show	facebook/nllb-200-3.3B	3379.2M	URL
5	17.6	show	facebook/nllb-200-1.3B	1331.2M	URL
4	16.4	show	facebook/m2m100_1.2B	1331.2M	URL
3	16.1	show	ara-ell/opus-2021-02-24	76.6M	zip-file
2	15.9	show	facebook/m2m100_418M	418M	URL
1	15.8	show	ara-ell/opus-2020-07-03	76.6M	zip-file
0	15.7	show	facebook/nll...illed-600M	600M	URL