OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/sla-sla/opus-2021-02-16
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

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

	bel	bul	ces	dsb	hbs	hsb	mkd	orv	pol	rus	slk	slv	szl	ukr
bel	bel	13.4	8.8				11.3		31.2	40.1	1.0	9.1	1.2	37.7
bul	6.5	bul	16.4				23.6		12.1	33.2	1.6	15.8	2.1	36.0
ces	6.0	20.9	ces				19.2		32.4	30.8	2.0	10.3	2.6	36.3
dsb				dsb		3.7						2.1
hbs					hbs				43.2	52.2				51.2
hsb				0.3		hsb						7.1
mkd	6.7	25.4	17.2				mkd		11.9	16.5	1.6	17.3	2.2	15.6
orv								orv						3.1
pol	21.2	17.9	31.0		44.6		15.6		pol	33.8	1.8	14.1	2.6	32.1
rus	25.4	35.2	28.8		44.3		18.8		31.4	rus	1.5	21.4	2.0	41.7
slk	4.1	13.8	14.3				12.5		8.9	9.6	slk	12.0	2.6	8.4
slv	6.0	19.4	29.6	0.7		8.5	18.1		11.4	31.0	2.0	slv	2.5	25.9
szl	3.9	10.5	8.8				9.9		8.9	8.6	1.7	8.6	szl	8.2
ukr	27.4	42.7	37.1		47.1		19.9	0.2	33.7	45.8	1.5	15.0	1.9	ukr

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