OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/ita-zle/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	ita-bel	flores101-devtest	show	8.5
1	ita-bel	flores200-devtest	show	8.6
2	ita-bel	ntrex128	show	17.8
3	ita-bel	tatoeba-test-v2020-07-28	show	33.3
4	ita-bel	tatoeba-test-v2021-03-30	show	33.6
5	ita-bel	tatoeba-test-v2021-08-07	show	33.3
6	ita-rus	flores101-devtest	show	21.3
7	ita-rus	flores200-devtest	show	21.3
8	ita-rus	ntrex128	show	24.2
9	ita-rus	tatoeba-test-v2020-07-28	show	46.6
10	ita-rus	tatoeba-test-v2021-03-30	show	46.6
11	ita-rus	tatoeba-test-v2021-08-07	show	46.6
12	ita-ukr	flores101-devtest	show	18.3
13	ita-ukr	flores200-devtest	show	18.3
14	ita-ukr	ntrex128	show	19.3
15	ita-ukr	tatoeba-test-v2020-07-28	show	48.3
16	ita-ukr	tatoeba-test-v2021-03-30	show	48.3
17	ita-ukr	tatoeba-test-v2021-08-07	show	48.3
			average	30.139