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 (spbleu)	Output	OPUS-MT	spbleu	external	spbleu	Diff
0	flores101-devtest	compare	zlw-eng/opus...2022-03-17	45.1	facebook/nllb-200-3.3B	43	2.100
1	flores200-devtest	compare	zlw-eng/opus...2022-03-17	45.2	facebook/nllb-200-3.3B	42.8	2.400
2	generaltest2022	compare	ces+slk-eng/...2022-03-13	58.9	facebook/nllb-200-3.3B	54	4.900
3	multi30k_test_2016_flickr	compare	ces+slk-eng/...2022-03-13	41.5	facebook/nll...illed-1.3B	40.4	1.100
4	multi30k_test_2018_flickr	compare	ces+slk-eng/...2022-03-17	40.9	facebook/nll...illed-1.3B	40.4	0.500
5	newssyscomb2009	compare	sla-eng/opus...2024-08-17	33.4	facebook/nllb-200-1.3B	31.9	1.500
6	newstest2008	compare	zlw-eng/opus...2022-03-17	29.4	facebook/nllb-200-1.3B	28.3	1.100
7	newstest2009	compare	zlw-eng/opus...2022-03-17	32.7	facebook/nllb-200-3.3B	31.4	1.300
8	newstest2010	compare	zlw-eng/opus...2022-03-17	34.4	facebook/nllb-200-3.3B	34.2	0.200
9	newstest2011	compare	zlw-eng/opus...2022-03-17	34.4	facebook/nllb-200-3.3B	32.3	2.100
10	newstest2012	compare	zlw-eng/opus...2022-03-17	32.8	facebook/nllb-200-3.3B	31.9	0.900
11	newstest2013	compare	ces+slk-eng/...2022-03-13	35.9	facebook/nllb-200-1.3B	34.8	1.100
12	newstest2014	compare	zlw-eng/opus...2022-03-17	42.2	facebook/nllb-200-3.3B	39.8	2.400
13	newstest2015	compare	ces+slk-eng/...2022-03-17	36.8	facebook/nll...illed-1.3B	35.3	1.500
14	newstest2016	compare	zlw-eng/opus...2022-03-17	40.5	facebook/nllb-200-3.3B	39.1	1.400
15	newstest2017	compare	zlw-eng/opus...2022-03-17	35.9	facebook/nllb-200-3.3B	35.2	0.700
16	newstest2018	compare	zlw-eng/opus...2022-03-17	36.8	facebook/nllb-200-3.3B	35.6	1.200
17	newstest2021	compare	zlw-eng/opus...2022-03-17	45.8	facebook/nllb-200-3.3B	41.2	4.600
18	ntrex128	compare	ces+slk-eng/...2022-03-17	42.3	facebook/nllb-200-3.3B	42.9	-0.600
19	tatoeba-test-v2020-07-28	compare	ces+slk-eng/...2022-03-13	60.9	facebook/nllb-200-3.3B	60.7	0.200
20	tatoeba-test-v2021-03-30	compare	ces+slk-eng/...2022-03-17	60.3	facebook/nllb-200-3.3B	60.1	0.200
21	tatoeba-test-v2021-08-07	compare	ces+slk-eng/...2022-03-13	59.9	facebook/nllb-200-3.3B	59.7	0.200
		average		42.091		40.682	1.409