terminal-bench-science rudycelekli · COMPLETED
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
github.com/rudycelekli/terminal-bench-science · ★ 0 · Forks 0 · Size 798.1 MB
SUMMARY
Technologies 22
Scored 22
Observed 22
Practices 6
Evidence 24
Skips 0
COVERAGE
Analyzed 3774 files · 1613 commits · 0 API calls
TECHNOLOGIES & DEPTH
TypeScript LANGUAGE Depth 70
2 files · PRODUCTION
Dockerfile LANGUAGE Depth 70
244 files · PRODUCTION
C++ LANGUAGE Depth 70
105 files · PRODUCTION
Shell LANGUAGE Depth 70
346 files · PRODUCTION
Rust LANGUAGE Depth 70
2 files · PRODUCTION
C LANGUAGE Depth 70
6 files · PRODUCTION
JavaScript LANGUAGE Depth 70
2 files · PRODUCTION
JSON LANGUAGE Depth 70
443 files · PRODUCTION
Markdown LANGUAGE Depth 70
335 files · PRODUCTION
TOML LANGUAGE Depth 70
167 files · PRODUCTION
YAML LANGUAGE Depth 70
41 files · PRODUCTION
Python LANGUAGE Depth 70
779 files · PRODUCTION
Cargo BUILD_TOOL Depth 80
1 files · CONFIGURATION
uv BUILD_TOOL Depth 80
1 files · CONFIGURATION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 81
484 files · PRODUCTION, TEST
Playwright TESTING Depth 46
1 files · PRODUCTION
Redis CACHE Depth 77
4 files · CONFIGURATION
Requests LIBRARY Depth 40
1 files · PRODUCTION
pandas LIBRARY Depth 74
86 files · PRODUCTION, TEST
pytest TESTING Depth 78
73 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · observedlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-01-23
Last commit 2026-10-03
Active months 10
Commits 1613