Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dialect Robustness on PT
Loading...
82
Success Rate
mT5
33.12
45.81
58.5
71.19
Nov 2, 2022
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
mT5
Model Scale=XXL, Train...
2022.11
82
mT5
Model Scale=XXL, Train...
2022.11
81
mT5
Model Scale=XL, Traini...
2022.11
65
BLEURT
Metric Category=Learned
2022.11
59
mT5
Model Scale=XL, Traini...
2022.11
57
PRISM
Metric Category=Learned
2022.11
53
mT5
Model Scale=base, Trai...
2022.11
44
mT5
Model Scale=base, Trai...
2022.11
39
YiSi
Metric Category=Lexical
2022.11
36
BLEU
Metric Category=Lexical
2022.11
35
CHRF
Metric Category=Lexical
2022.11
35
Feedback
Search any
task
Search any
task
