OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/urj-urj/opus-2020-10-04
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

Selected Benchmark: [avg] [tatoeba-test-v2021-03-30] [tatoeba-test-v2021-08-07] [flores101-devtest] [flores200-devtest] [newstest2018] [ntrex128] [tatoeba-test-v2020-07-28]
Scores shown in percentage points

	eng	est	fin	fkv	hun	liv
eng	64.3	31.8	20.7		20.5	3.6
est	37.0	est	14.2		12.6
fin	27.9	14.9	22.2	0.5	28.2
fkv			20.3	fkv
hun	27.3	12.0	28.9		19.5
liv	4.5					liv

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