OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/zle-fra/opusTCv20210807_transformer-big_2022-03-23
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

ID	Language	Benchmark	Output	bleu
0	bel-fra	flores101-devtest	show	16.7
1	bel-fra	flores200-devtest	show	16.7
2	bel-fra	ntrex128	show (logfile)	20.2
3	bel-fra	tatoeba-test-v2021-03-30	show	47.8
4	bel-fra	tatoeba-test-v2021-08-07	show	47.8
5	rus-fra	flores101-devtest	show	33.7
6	rus-fra	flores200-devtest	show	33.7
7	rus-fra	newstest2012	show	25.3
8	rus-fra	newstest2013	show	29.7
9	rus-fra	ntrex128	show (logfile)	24.6
10	rus-fra	tatoeba-test-v2020-07-28	show	53.2
11	rus-fra	tatoeba-test-v2021-03-30	show	53.2
12	rus-fra	tatoeba-test-v2021-08-07	show	53
13	rus-fra	tico19-test	show (logfile)	27.4
14	ukr-fra	flores101-devtest	show	35.1
15	ukr-fra	flores200-devtest	show	35.1
16	ukr-fra	ntrex128	show (logfile)	23.1
17	ukr-fra	tatoeba-test-v2020-07-28	show	51.9
18	ukr-fra	tatoeba-test-v2021-03-30	show	52
19	ukr-fra	tatoeba-test-v2021-08-07	show	52
			average	36.610