OPUS-MT Dashboard

blue = OPUS-MT / Tatoeba-MT models, grey = external models, purple = user-contributed
render chart with [gd] [plotly]

ID	Benchmark (bleu)	Output	OPUS-MT	bleu	external	bleu	Diff
0	flores101-devtest	compare	bul-jpn/opus-2021-02-18	12.2	facebook/m2m100_1.2B	24.2	-12.0
1	flores200-devtest	compare	bul-jpn/opus-2021-02-18	12.2	facebook/m2m100_1.2B	24.2	-12.0
2	ntrex128	compare	bul-jpn/opus-2021-02-18	0.1	facebook/nllb-200-1.3B	0.5	-0.4
3	tatoeba-test-v2020-07-28	compare	bul-jpn/opus-2021-02-18	18.1	facebook/m2m100_418M	19.6	-1.5
4	tatoeba-test-v2021-03-30	compare	bul-jpn/opus-2021-02-18	18.3	facebook/m2m100_418M	19.7	-1.4
5	tatoeba-test-v2021-08-07	compare	bul-jpn/opus-2021-02-18	18.3	facebook/m2m100_418M	19.5	-1.2
		average		13.2		17.9	-4.7