OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/sem-fin/opus4m+btTCv20210807-2022-01-19
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	ara-fin	flores101-devtest	show	13.9
1	ara-fin	flores200-devtest	show	14
2	arz-fin	flores200-devtest	show	8.7
3	heb-fin	flores101-devtest	show	14.9
4	heb-fin	flores200-devtest	show	14.6
5	heb-fin	ntrex128	show	12.3
6	heb-fin	tatoeba-test-v2020-07-28	show	39.3
7	heb-fin	tatoeba-test-v2021-03-30	show	39.6
8	heb-fin	tatoeba-test-v2021-08-07	show	39.3
			average	21.844