OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/fi-en/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	fin-eng	flores101-devtest	show	30.5
1	fin-eng	newstest2015	show	26.1
2	fin-eng	newstest2016	show	28.8
3	fin-eng	newstest2017	show	31.6
4	fin-eng	newstest2018	show	23.9
5	fin-eng	newstest2019	show	28.2
6	fin-eng	newstestB2016	show	24
7	fin-eng	newstestB2017	show	26.7
8	fin-eng	tatoeba-test-v2020-07-28	show	56.2
9	fin-eng	tatoeba-test-v2021-03-30	show	56.1
10	fin-eng	tatoeba-test-v2021-08-07	show	55.9
			average	35.273