OPUS-MT Dashboard

Language pair: ces-eng
Models: [all models] [OPUS-MT] [external] [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]

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

ID	Benchmark (bleu)	Output	OPUS-MT	bleu	external	bleu	Diff
0	flores101-devtest	compare	zlw-eng/opus...2022-03-17	41.2	facebook/nllb-200-3.3B	39.2	2.0
1	flores200-devtest	compare	zlw-eng/opus...2022-03-17	41.2	facebook/nllb-200-3.3B	39.1	2.1
2	generaltest2022	compare	ces+slk-eng/...2022-03-17	55.4	facebook/nllb-200-3.3B	51	4.4
3	multi30k_test_2016_flickr	compare	ces+slk-eng/...2022-03-17	38.6	facebook/nll...illed-1.3B	38.1	0.5
4	multi30k_test_2018_flickr	compare	ces+slk-eng/...2022-03-17	37.9	facebook/nll...illed-1.3B	37.7	0.2
5	newssyscomb2009	compare	zlw-eng/opus...2022-03-17	30.2	facebook/nllb-200-1.3B	28.6	1.6
6	newstest2008	compare	zlw-eng/opus...2022-03-17	26.3	facebook/nllb-200-1.3B	25.3	1.0
7	newstest2009	compare	zlw-eng/opus...2022-03-17	29.5	facebook/nllb-200-3.3B	27.9	1.6
8	newstest2010	compare	zlw-eng/opus...2022-03-17	30.7	facebook/nllb-200-1.3B	30.3	0.4
9	newstest2011	compare	zlw-eng/opus...2022-03-17	30.9	facebook/nllb-200-3.3B	28.9	2.0
10	newstest2012	compare	zlw-eng/opus...2022-03-17	29.4	facebook/nllb-200-3.3B	28.7	0.7
11	newstest2013	compare	ces+slk-eng/...2022-03-17	33.1	facebook/nllb-200-3.3B	32.1	1.0
12	newstest2014	compare	zlw-eng/opus...2022-03-17	38.7	facebook/nllb-200-3.3B	36.5	2.2
13	newstest2015	compare	ces+slk-eng/...2022-03-17	33.6	facebook/nll...illed-1.3B	32.2	1.4
14	newstest2016	compare	zlw-eng/opus...2022-03-17	37.1	facebook/nllb-200-3.3B	35.6	1.5
15	newstest2017	compare	zlw-eng/opus...2022-03-17	32.5	facebook/nllb-200-3.3B	31.8	0.7
16	newstest2018	compare	zlw-eng/opus...2022-03-17	33.1	facebook/nllb-200-3.3B	31.9	1.2
17	newstest2021	compare	zlw-eng/opus...2022-03-17	41.1	facebook/nllb-200-3.3B	36.5	4.6
18	ntrex128	compare	ces+slk-eng/...2022-03-17	38.4	facebook/nllb-200-3.3B	39	-0.6
19	tatoeba-test-v2020-07-28	compare	ces+slk-eng/...2022-03-17	58.7	facebook/nllb-200-3.3B	58.6	0.1
20	tatoeba-test-v2021-03-30	compare	ces+slk-eng/...2022-03-17	58.1	facebook/nllb-200-3.3B	58.1	0.0
21	tatoeba-test-v2021-08-07	compare	ces+slk-eng/...2022-03-17	57.7	facebook/nllb-200-3.3B	57.7	0.0
		average		38.8		37.5	1.3