Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Attack & Defense Accuracy)
Loading...
100
Accuracy under Attack (GSM8K)
Reporting-and-penalty mechanism
53.2
65.35
77.5
89.65
Apr 26, 2026
Accuracy under Attack (GSM8K)
Accuracy after Defense Recovery (GSM8K)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy under Attack (GSM8K)
Accuracy after Defense Recovery (GSM8K)
Reporting-and-penalty mechanism
Attack Type=All Attack...
2026.04
100
100
SentinelNet
Attack Type=Collaborat...
2026.04
70
97
GroupGuard
Attack Type=False Cons...
2026.04
60
99
GroupGuard
Attack Type=False Cons...
2026.04
57
100
GroupGuard
Attack Type=False Cons...
2026.04
55
81
Feedback
Search any
task
Search any
task