OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/iir-eng/opus-2020-07-04
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

Selected Benchmark: [avg] [flores101-devtest] [flores200-devtest] [tatoeba-test-v2021-03-30] [tatoeba-test-v2020-07-28] [tatoeba-test-v2021-08-07] [ntrex128] [tico19-test]
Scores shown in percentage points

	eng
asm	9.4
awa	5.4
ben	22.6
bho	5.0
guj	6.6
hin	20.4
kur	2.4
kur_Latn	2.8
mai	7.8
mar	14.2
npi	2.8
pan	11.3
pes	4.3
pus	1.9
rom	2.2
san	2.4
sin	7.1
snd	4.5
tgk	6.1
urd	14.4
zza	0.6

color:
score:	0	10	20	30	40	50	60	70	80	90	100