OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/sal-sal/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] [ntrex128] [tatoeba-test-v2020-07-28] [tico19-test]
Scores shown in percentage points

	eng	ind	msa	zsm	zsm_Latn
eng	52.2	30.1	22.9	22.1	27.9
ind	29.3	ind	2.6	2.0	3.2
msa	26.0	14.1	8.5	3.2
zsm	22.9	14.2	3.2	zsm
zsm_Latn	36.8	20.5			zsm_Latn

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