@wrongstack/bench
MITModel-independent agentic benchmark harness for WrongStack (bundled smoke suite, Aider polyglot, SWE-bench Verified) with deterministic graders, harness fingerprinting, and run-to-run comparison reports.
100
Security score
0 known advisories in v1.0.24
Weekly downloads
948
Unpacked size
173.3 kB
Dependencies
1
Last publish
1 day ago
Security advisories
No known vulnerabilities affect v1.0.24.
Downloads — last 30 days
6.3K total▼ 58.7% vs prior week
Aug 23Sep 21