OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/hun-eng/opus+bt-2021-04-30
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

orange = OPUS-MT, blue = Tatoeba-MT models, red = HPLT-MT models
green = student models, grey = external models, purple = user-contributed
render chart with [gd] [plotly]

Model Scores (selected model)

ID	Language	Benchmark	Output	bleu
0	hun-eng	flores101-devtest	show	32.7
1	hun-eng	flores200-devtest	show	32.7
2	hun-eng	newssyscomb2009	show	23.4
3	hun-eng	newstest2008	show (logfile)	20.3
4	hun-eng	newstest2009	show	22.3
5	hun-eng	ntrex128	show (logfile)	22.6
6	hun-eng	tatoeba-test-v2020-07-28	show	51.5
7	hun-eng	tatoeba-test-v2021-03-30	show	49.5
8	hun-eng	tatoeba-test-v2021-08-07	show	48.9
			average	33.767