OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/es-ru/opus-2020-01-20
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	spa-rus	flores101-devtest	show	15.7
1	spa-rus	newstest2012	show	20
2	spa-rus	newstest2013	show	22.5
3	spa-rus	tatoeba-test-v2020-07-28	show	46.8
4	spa-rus	tatoeba-test-v2021-03-30	show	46.6
5	spa-rus	tatoeba-test-v2021-08-07	show	46.5
			average	33.017