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_2022-03-19
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	16.3
1	bel-fra	flores200-devtest	show	16.3
2	bel-fra	ntrex128	show	19.3
3	bel-fra	tatoeba-test-v2020-07-28	show	45.2
4	bel-fra	tatoeba-test-v2021-03-30	show	45
5	bel-fra	tatoeba-test-v2021-08-07	show	45.2
6	rus-fra	flores101-devtest	show	33
7	rus-fra	flores200-devtest	show	33
8	rus-fra	newstest2012	show	25.3
9	rus-fra	newstest2013	show	29.4
10	rus-fra	ntrex128	show	24.4
11	rus-fra	tatoeba-test-v2020-07-28	show	53
12	rus-fra	tatoeba-test-v2021-03-30	show	52.9
13	rus-fra	tatoeba-test-v2021-08-07	show	52.8
14	rus-fra	tico19-test	show	27
15	ukr-fra	flores101-devtest	show	34
16	ukr-fra	flores200-devtest	show	34
17	ukr-fra	ntrex128	show	22.8
18	ukr-fra	tatoeba-test-v2020-07-28	show	51.7
19	ukr-fra	tatoeba-test-v2021-03-30	show	51.8
20	ukr-fra	tatoeba-test-v2021-08-07	show	51.8
			average	36.390