Parsimony

Parsimony is an open-source benchmark for how much code AI models add. Existing benchmarks track solve rate and token output or cost, but they do not penalize excess code, which can make a codebase harder to work with over the long term.

It analyzes patches published by DeepSWE, SWE-bench Verified, and SWE-bench Live, counting "coding units" such as statements, calls, names, and literals rather than lines of code. The goal is to measure added code in long-term projects, where it matters most.