OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/es-fr/opus-2020-01-08
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-fra	flores101-devtest	show	24.7
1	spa-fra	newssyscomb2009	show	33.6
2	spa-fra	newstest2009	show	32.2
3	spa-fra	newstest2010	show	33.7
4	spa-fra	newstest2011	show	33.7
5	spa-fra	newstest2012	show	32.5
6	spa-fra	newstest2013	show	32.1
7	spa-fra	tatoeba-test-v2020-07-28	show	58.2
8	spa-fra	tatoeba-test-v2021-03-30	show	58.2
9	spa-fra	tatoeba-test-v2021-08-07	show	58.2
			average	39.710