OPUS-MT Dashboard

Language pair: [fra-eng] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/fr-es/opus-2020-01-09
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	fra-spa	flores101-devtest	show	23
1	fra-spa	newssyscomb2009	show	34
2	fra-spa	newstest2009	show	31.2
3	fra-spa	newstest2010	show	35.9
4	fra-spa	newstest2011	show	37.5
5	fra-spa	newstest2012	show	37.3
6	fra-spa	newstest2013	show	33.3
7	fra-spa	tatoeba-test-v2020-07-28	show	53.9
8	fra-spa	tatoeba-test-v2021-03-30	show	53.9
9	fra-spa	tatoeba-test-v2021-08-07	show	54
			average	39.400