OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/sla-fiu/opus-2021-02-10
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

	chm	est	fin	hun
bel		7.0	5.9	7.9
bul		13.6	11.6	14.9
ces		14.2	12.1	27.0
mkd		13.9	12.2	14.1
pol		11.4	26.7	28.5
rus	1.4	36.0	27.4	26.7
slk		8.6	6.7	9.4
slv		14.2	12.4	14.9
szl		6.7	5.4	7.5
ukr		13.8	11.6	29.7

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