OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/en-fi/opus+bt-news-2020-03-21
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	25.4
1	eng-fin	newstest2015	show	27.8
2	eng-fin	newstest2016	show	30.1
3	eng-fin	newstest2017	show	32.7
4	eng-fin	newstest2018	show	21
5	eng-fin	newstest2019	show	25.5
6	eng-fin	newstestB2016	show	25.5
7	eng-fin	newstestB2017	show	28.7
8	eng-fin	tatoeba-test-v2020-07-28	show	40.7
9	eng-fin	tatoeba-test-v2021-03-30	show	40.6
10	eng-fin	tatoeba-test-v2021-08-07	show	40.5
			average	30.773