Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

AdvGLUE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Natural Language UnderstandingAdvGLUE
RTE Accuracy81.96
24
HelpfulnessAdvGLUE
Accuracy75.15
20
Binary classificationAdvGLUE (test)
QNLI Accuracy0.701
17
Natural Language UnderstandingAdvGLUE
Performance Score68.29
8
Adversarial RobustnessAdvGLUE (test)
AdvGLUE Score76.73
6
Showing 5 of 5 rows