OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/gmq-gmq/opus-2021-02-18
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

Selected Benchmark: [avg] [tatoeba-test-v2021-08-07] [flores101-devtest] [flores200-devtest] [tatoeba-test-v2020-07-28] [tatoeba-test-v2021-03-30] [ntrex128] [europeana2021]
Scores shown in percentage points

	dan	eng	fao	isl	nno	nob	swe
dan	51.9	51.9	6.7	15.3	22.0	50.4	51.1
eng	49.9	eng	8.1	20.4	29.7	43.2	49.8
fao	14.9	22.3	fao	9.5	10.3	12.0	13.2
isl	21.0	37.9	5.7	isl	15.2	17.4	19.9
nno	30.5	44.6	6.3	16.4	nno	56.4	30.4
nob	49.7	47.1	6.4	16.3	35.6	nob	49.7
swe	51.6	52.9	6.2	17.2	23.0	49.2	45.8

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