OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/deu+eng+fra+por+spa-cau/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30
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	deu-kat	flores200-devtest	show (logfile)	5.7
1	deu-kat	ntrex128	show (logfile)	6.2
2	eng-kat	flores200-devtest	show (logfile)	8.8
3	eng-kat	ntrex128	show (logfile)	10.6
4	eng-kat	tatoeba-test-v2020-07-28	show (logfile)	18.6
5	eng-kat	tatoeba-test-v2021-03-30	show (logfile)	18.6
6	eng-kat	tatoeba-test-v2021-08-07	show (logfile)	18.6
7	fra-kat	flores200-devtest	show (logfile)	6
8	fra-kat	ntrex128	show (logfile)	7.1
9	por-kat	flores200-devtest	show (logfile)	6.1
10	por-kat	ntrex128	show (logfile)	6.7
11	spa-kat	flores200-devtest	show (logfile)	4.9
12	spa-kat	ntrex128	show (logfile)	6.9
			average	9.600