OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/fin-swe/opusTCv20210807+bt-2021-11-09
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-swe	fiskmo_testset	show	32.3
1	fin-swe	flores101-devtest	show	27.5
2	fin-swe	flores200-devtest	show	27.6
3	fin-swe	ntrex128	show	24
4	fin-swe	tatoeba-test-v2020-07-28	show	55.6
5	fin-swe	tatoeba-test-v2021-03-30	show	55.6
6	fin-swe	tatoeba-test-v2021-08-07	show	55.6
			average	39.743