Parsimony – an open-source benchmark for how much code AI models add
Existing benchmarks measure solve rate and token output/cost, but don't punish excess code, which makes a codebase harder to work with in the long term. I wanted to measure this since it matters most for long-term projects.Method:
公开 Show HN / Launch HN 条目达到发现阈值。
Who it is for: 公开资料未明确
Pricing
未公开
Updated 2026-10-14
Visit Parsimony – an open-source benchmark for how much code AI models add