OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/en-fi/opus-2019-12-04
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-fin	flores101-devtest	show	22.1
1	eng-fin	newstest2015	show	22.1
2	eng-fin	newstest2016	show	23.3
3	eng-fin	newstest2017	show	25.8
4	eng-fin	newstest2018	show	16.9
5	eng-fin	newstest2019	show	21.7
6	eng-fin	newstestB2016	show	19.3
7	eng-fin	newstestB2017	show	22
8	eng-fin	tatoeba-test-v2020-07-28	show	37.9
9	eng-fin	tatoeba-test-v2021-03-30	show	37.8
10	eng-fin	tatoeba-test-v2021-08-07	show	37.8
			average	26.064