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_2022-03-14
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	14.5
1	bel-fra	flores200-devtest	show	14.5
2	bel-fra	ntrex128	show (logfile)	17.4
3	bel-fra	tatoeba-test-v2020-07-28	show	41.7
4	bel-fra	tatoeba-test-v2021-03-30	show	41.5
5	bel-fra	tatoeba-test-v2021-08-07	show	41.7
6	rus-fra	flores101-devtest	show	31.7
7	rus-fra	flores200-devtest	show	31.7
8	rus-fra	newstest2012	show	24.5
9	rus-fra	newstest2013	show	28.7
10	rus-fra	ntrex128	show (logfile)	23.7
11	rus-fra	tatoeba-test-v2020-07-28	show	51.8
12	rus-fra	tatoeba-test-v2021-03-30	show	51.7
13	rus-fra	tatoeba-test-v2021-08-07	show	51.5
14	rus-fra	tico19-test	show (logfile)	26
15	ukr-fra	flores101-devtest	show	33
16	ukr-fra	flores200-devtest	show	33
17	ukr-fra	ntrex128	show (logfile)	22
18	ukr-fra	tatoeba-test-v2020-07-28	show	50.4
19	ukr-fra	tatoeba-test-v2021-03-30	show	50.4
20	ukr-fra	tatoeba-test-v2021-08-07	show	50.4
			average	34.848