OPUS-MT Dashboard

Language pair: cmn_Hans-heb [all languages]
Models: [all models] [OPUS-MT] [external] [compare]
Benchmark: [all benchmarks] [average score] tatoeba-test-v2020-07-28
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-v2020-07-28" testset)

ID	bleu	Output	Model	Size	Link
4	25.0	show	facebook/nll...illed-600M	600M	URL
3	24.8	show	facebook/nllb-200-1.3B	1331.2M	URL
2	24.1	show	facebook/nll...illed-1.3B	1331.2M	URL
1	23.9	show	facebook/nllb-200-3.3B	3379.2M	URL
0	6.8	show	mul-mul/opus...2024-08-17	247.8M	zip-file