OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/sin-eng/opus-2021-02-19
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	sin-eng	flores200-devtest	show	12.3
1	sin-eng	ntrex128	show	10.2
2	sin-eng	wikipedia.devtest	show	10.6
3	sin-eng	wikipedia.devtest.si-en	show	10.5
4	sin-eng	wikipedia.test	show	9.3
5	sin-eng	wikipedia.test.si-en	show	9.2
			average	10.350