OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Benchmark: [all benchmarks] [average score] newstest2019
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Highlighting colors: [model score] [model type] [model size]

Table of bleu score differences between the best OPUS-MT model and the best external modelfor language pairs with an existing external model (other cells are left blank):

	ces	deu	eng	fin	fra	guj	kaz	lit	rus	zho
ces	ces	1.4
deu	2.4	deu	0.1		5.1
eng	1.8	0.3	eng	2.5		1.9	-0.8	1.5	-1.6	-6.1
fin			5.5	fin
fra		5.7			fra
guj			-1.8			guj
kaz			-11.0				kaz
lit			2.4					lit
rus			2.6						rus
zho			-3.0							zho