OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/itc-heb/opus1m-2021-05-16
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	cat-heb	flores101-devtest	show	11.6
1	cat-heb	flores200-devtest	show	11.7
2	cat-heb	ntrex128	show	8.9
3	fra-heb	flores101-devtest	show	11.1
4	fra-heb	flores200-devtest	show	11.2
5	fra-heb	ntrex128	show	8.9
6	fra-heb	tatoeba-test-v2020-07-28	show	33.1
7	fra-heb	tatoeba-test-v2021-03-30	show	33.1
8	fra-heb	tatoeba-test-v2021-08-07	show	33.1
			average	18.078