Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Natural Language Understanding on SWAG (dev)
Loading...
92.59
Accuracy
XDELECTRA-l
80.5364
83.6657
86.795
89.9243
Apr 15, 2022
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
XDELECTRA-l
model size=large
2022.04
92.59
ELECTRA-l
model size=large
2022.04
92.46
XDELECTRA-b
model size=base
2022.04
88.73
ELECTRA-b
model size=base
2022.04
88.6
XDBERT-b
model size=base
2022.04
81.35
BERT-b
model size=base
2022.04
81
Feedback
Search any
task
Search any
task