OPUS-MT Dashboard

Language pair: [fra-eng] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/en-fi/opus-2019-12-18
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	22.3
1	eng-fin	newstest2015	show	21.4
2	eng-fin	newstest2016	show	23.4
3	eng-fin	newstest2017	show	25.6
4	eng-fin	newstest2018	show	16.5
5	eng-fin	newstest2019	show	21.8
6	eng-fin	newstestB2016	show	18.9
7	eng-fin	newstestB2017	show	21.8
8	eng-fin	tatoeba-test-v2020-07-28	show	39.7
9	eng-fin	tatoeba-test-v2021-03-30	show	39.6
10	eng-fin	tatoeba-test-v2021-08-07	show	39.5
			average	26.409