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

PyPI

Benchmarks

Task NameDataset NameSOTA ResultTrend
SBOM GenerationPyPI dataset (51 Python applications)
Success Rate100
54
Malicious Package DetectionPyPI (test)
Precision96.1
17
Malicious Package DetectionPyPI (Extremely Large ≥700KB)
Accuracy96.33
12
Malicious Package DetectionPyPI (Extremely Small ≤1.57KB)
Accuracy95.96
12
Malicious Package DetectionPyPI Extensive Imports (test)
Accuracy95
12
Malicious Package DetectionPyPI Minimal Imports (test)
Accuracy96.6
12
Malicious Package DetectionPyPI
Accuracy99.5
8
Malicious Package DetectionPyPI NPM-trained (test)
Precision75.1
6
Vulnerability DetectionPyPI Top100
Accuracy93.5
2
Package Size EvaluationPyPI Linux x86_64 2025
Metric-
0
Showing 10 of 10 rows