OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/zle-ita/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-ita	flores101-devtest	show	13.5
1	bel-ita	flores200-devtest	show	13.5
2	bel-ita	ntrex128	show (logfile)	20.5
3	bel-ita	tatoeba-test-v2020-07-28	show	49.3
4	bel-ita	tatoeba-test-v2021-03-30	show	49.5
5	bel-ita	tatoeba-test-v2021-08-07	show	49.3
6	rus-ita	flores101-devtest	show	23.7
7	rus-ita	flores200-devtest	show	23.7
8	rus-ita	ntrex128	show (logfile)	21.9
9	rus-ita	tatoeba-test-v2020-07-28	show	43.4
10	rus-ita	tatoeba-test-v2021-03-30	show	43.5
11	rus-ita	tatoeba-test-v2021-08-07	show	43.5
12	ukr-ita	flores101-devtest	show	23.2
13	ukr-ita	flores200-devtest	show	23.2
14	ukr-ita	ntrex128	show (logfile)	22.1
15	ukr-ita	tatoeba-test-v2020-07-28	show	50
16	ukr-ita	tatoeba-test-v2021-03-30	show	50
17	ukr-ita	tatoeba-test-v2021-08-07	show	50
			average	34.100