OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: huggingface/staka/fugumt-en-ja
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	eng-jpn	flores101-devtest	show	31
1	eng-jpn	flores200-devtest	show	31
2	eng-jpn	newstest2020	show	21.3
3	eng-jpn	newstest2021	show	23.1
4	eng-jpn	tatoeba-test-v2020-07-28	show	34.3
5	eng-jpn	tatoeba-test-v2021-03-30	show	32.6
6	eng-jpn	tatoeba-test-v2021-08-07	show	31.4
			average	29.243