OPUS-MT Dashboard

Language pair: ces-eng
Models: [all models] [OPUS-MT] [external] [contributed] [compare]
Benchmark: all benchmarks [average score]
Evaluation metric: [bleu][spbleu][chrf] chrf++ [comet]
Chart Type: [barchart][diff]

blue = OPUS-MT / Tatoeba-MT models, grey = external models, purple = user-contributed
render chart with [gd] [plotly]
exclude scores of user-contributed translations

Model Scores (comparing between OPUS-MT and external models)

ID	Benchmark (chrf++)	Output	OPUS-MT	chrf++	external	chrf++	Diff	contributed	chrf++	Diff
0	flores101-devtest	compare	ces+slk-eng/...2022-03-17	0.64605	facebook/nllb-200-3.3B	0.63173	0.014
1	flores200-devtest	compare	zlw-eng/opus...2022-03-17	0.64606	facebook/nllb-200-3.3B	0.62916	0.017	nllb-200-54.5B	0.6443	0.002
2	generaltest2022	compare	ces+slk-eng/...2022-03-13	0.69326	facebook/nllb-200-3.3B	0.66218	0.031	Online-W	0.78764	-0.094
3	multi30k_test_2016_flickr	compare	ces+slk-eng/...2022-03-17	0.61126	facebook/nll...illed-1.3B	0.60664	0.005
4	multi30k_test_2018_flickr	compare	ces+slk-eng/...2022-03-17	0.60538	facebook/nll...illed-1.3B	0.60073	0.005
5	newssyscomb2009	compare	sla-eng/opus...2024-08-17	0.54698	facebook/nllb-200-1.3B	0.53726	0.010
6	newstest2008	compare	zlw-eng/opus...2022-03-17	0.51994	facebook/nllb-200-1.3B	0.51098	0.009
7	newstest2009	compare	zlw-eng/opus...2022-03-17	0.54214	facebook/nllb-200-3.3B	0.52809	0.014
8	newstest2010	compare	zlw-eng/opus...2022-03-17	0.55649	facebook/nllb-200-3.3B	0.5528	0.004
9	newstest2011	compare	zlw-eng/opus...2022-03-17	0.5533	facebook/nllb-200-3.3B	0.53844	0.015
10	newstest2012	compare	zlw-eng/opus...2022-03-17	0.54636	facebook/nllb-200-1.3B	0.53581	0.011
11	newstest2013	compare	sla-eng/opus...2024-08-17	0.57123	facebook/nllb-200-3.3B	0.55938	0.012
12	newstest2014	compare	zlw-eng/opus...2022-03-17	0.62467	facebook/nllb-200-3.3B	0.60609	0.019
13	newstest2015	compare	ces+slk-eng/...2022-03-17	0.56931	facebook/nllb-200-3.3B	0.55689	0.012
14	newstest2016	compare	zlw-eng/opus...2022-03-17	0.59995	facebook/nllb-200-3.3B	0.5851	0.015
15	newstest2017	compare	zlw-eng/opus...2022-03-17	0.5627	facebook/nllb-200-3.3B	0.55619	0.007
16	newstest2018	compare	zlw-eng/opus...2022-03-17	0.56658	facebook/nllb-200-3.3B	0.55732	0.009	nllb-200-54.5B	0.56817	-0.002
17	newstest2021	compare	zlw-eng/opus...2022-03-17	0.58515	facebook/nllb-200-1.3B	0.55723	0.028	Facebook-AI	0.61703	-0.032
18	ntrex128	compare	ces+slk-eng/...2022-03-17	0.62	facebook/nllb-200-3.3B	0.6246	-0.005
19	tatoeba-test-v2020-07-28	compare	ces+slk-eng/...2022-03-17	0.72571	facebook/nllb-200-3.3B	0.72193	0.004
20	tatoeba-test-v2021-03-30	compare	ces+slk-eng/...2022-03-17	0.72107	facebook/nllb-200-3.3B	0.7182	0.003
21	tatoeba-test-v2021-08-07	compare	ces+slk-eng/...2022-03-17	0.71808	facebook/nllb-200-3.3B	0.71525	0.003
		average		0.606		0.595	0.011		0.654	-0.048