Sign in Sign up
npm

@wrongstack/bench

Model-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.

npm View on Npm

Activity

Latest release
3h ago
Total releases
105
Cadence
~daily
Last 12 months
105

Reach

Downloads (recent)
1.1k

Details

License
MIT
First release
Jun 14, 2026
Releases
Version Released
1.0.16 patch
1.0.15 patch
1.0.14 patch
1.0.13 patch
1.0.12 patch
1.0.11 patch
1.0.10 patch
1.0.9 patch
1.0.8 patch
1.0.7 patch
1.0.6 patch
1.0.5 patch
1.0.4 patch
1.0.3 patch
1.0.2 patch
1.0.1 patch
1.0.0 major
0.320.1 minor
0.319.1 patch
0.319.0 minor
0.318.0 minor
0.317.2 patch
0.317.0 minor
0.316.2 patch
0.316.1 minor
0.313.1 patch
0.313.0 minor
0.310.1 patch
0.310.0 minor
0.309.1 patch
0.309.0 minor
0.308.7 patch
0.308.6 patch
0.308.5 patch
0.308.4 patch
0.308.2 patch
0.308.1 patch
0.308.0 minor
0.307.1 patch
0.307.0 minor
0.306.4 patch
0.306.3 patch
0.306.2 patch
0.306.0 minor
0.305.1 patch
0.305.0 minor
0.303.0 minor
0.302.2 patch
0.302.0 minor
0.301.0 minor
1–50 of 105