mle-bench AnuarRazii · PARTIAL
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
github.com/AnuarRazii/mle-bench · ★ 1 · Forks 0 · Size 713 KB
SUMMARY
Technologies 21
Scored 18
Observed 18
Practices 6
Evidence 22
Skips 3
COVERAGE
Analyzed 984 files · 42 commits · 0 API calls
TECHNOLOGIES & DEPTH
Dockerfile LANGUAGE Depth 70
5 files · PRODUCTION
Shell LANGUAGE Depth 70
9 files · PRODUCTION
JavaScript LANGUAGE Depth 70
1 files · PRODUCTION
JSON LANGUAGE Depth 70
211 files · PRODUCTION
TOML LANGUAGE Depth 70
1 files · PRODUCTION
Markdown LANGUAGE Depth 70
175 files · PRODUCTION
YAML LANGUAGE Depth 70
169 files · PRODUCTION
Python LANGUAGE Depth 70
221 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
npm BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
Black QUALITY Depth —
0 files · config only
Flask FRAMEWORK Depth 49
1 files · PRODUCTION
MongoDB DATABASE Depth 59
1 files · CONFIGURATION
NumPy LIBRARY Depth 81
53 files · PRODUCTION, TEST
Playwright LIBRARY Depth 51
1 files · PRODUCTION
Requests LIBRARY Depth 58
1 files · PRODUCTION
mypy QUALITY Depth —
0 files · config only
pandas LIBRARY Depth 85
132 files · PRODUCTION
pytest TESTING Depth 66
3 files · PRODUCTION, TEST
python-dotenv LIBRARY Depth —
0 files · config only
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · absentcontainerization · observedlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2024-10-08
Last commit 2025-12-19
Active months 11
Commits 42