Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Malicious Code Detection on NPM (test)
Loading...
98.07
Accuracy
PYGUARD
52.0292
63.9821
75.935
87.8879
Jan 23, 2026
Accuracy
Precision
Recall
F1-Score
False Positives
False Negatives
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Precision
Recall
F1-Score
False Positives
False Negatives
PYGUARD
Technique=RAG, Backbon...
2026.01
98.07
98.26
97.53
97.89
14
20
GPT-4.1
2026.01
96.71
98.08
94.68
96.35
15
43
GuardDog
2026.01
94.1
97.44
89.49
93.3
19
85
Cerebro
2026.01
87.32
99.66
72.11
83.68
2
226
OSSGadget
2026.01
53.8
49.83
90.11
64.17
734
80
Feedback
Search any
task
Search any
task