OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/eng-ron/opus-2020-08-27
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-ron	flores101-devtest	show	32.7
1	eng-ron	flores200-devtest	show	32.8
2	eng-ron	newstest2016	show	27.6
3	eng-ron	ntrex128	show	27.1
4	eng-ron	tatoeba-test-v2020-07-28	show	44.9
5	eng-ron	tatoeba-test-v2021-03-30	show	45.2
6	eng-ron	tatoeba-test-v2021-08-07	show	45.3
			average	36.514