OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/tut-eng/opus4m-2020-08-12
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

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

	eng
aze	14.5
bak	1.2
chv	1.2
crh	2.1
kaz	6.5
kaz_Cyrl	12.4
kir	3.3
mon	6.0
ota	2.0
ota_Arab	0.2
ota_Latn	3.4
tat	4.5
tuk	4.9
tuk_Latn	6.7
tur	12.1
uig	0.2
uig_Arab	0.1
uzb	3.7
uzb_Latn	7.1
xal	1.0

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