OPUS-MT Dashboard

Language pair: eng-kor [all languages]
Models: [all models] [OPUS-MT] [external] [compare]
Benchmark: [all benchmarks] [average score] tatoeba-test-v2021-08-07
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 "tatoeba-test-v2021-08-07" testset)

ID	bleu	Output	Model	Size	Link
7	24.9	show	facebook/m2m100_1.2B	1331.2M	URL
6	22.0	show	facebook/m2m100_418M	418M	URL
5	13.4	show	eng-kor/opus...2021-11-10	61.2M	zip-file
4	13.2	show	eng-kor/opus...2022-07-28	209.2M	zip-file
3	0.1	show	facebook/nllb-200-1.3B	1331.2M	URL
2	0.1	show	facebook/nllb-200-3.3B	3379.2M	URL
1	0.0	show	facebook/nll...illed-1.3B	1331.2M	URL
0	0.0	show	facebook/nll...illed-600M	600M	URL