← Wednesday, October 14, 2026AgentsBenchmark

Parsimony measures how much code AI models add in benchmark patches

parsimony.lasu.dev Editor score 7/10

The benchmark counts net syntax units in patches from DeepSWE, SWE-bench Verified and SWE-bench Live, subtracting deleted code rather than relying on lines. It adds a maintainability dimension to coding-agent evaluation, though some newer-model results use only 3–10 tasks.

What

Parsimony benchmarks excess code in AI-generated patches, addressing a dimension not captured by solve rate or token cost.

How

It counts syntax-level coding units, subtracts deleted code, and uses patches from DeepSWE, SWE-bench Verified, and SWE-bench Live.

Why it matters

Measuring net code growth gives engineers a signal about maintainability costs in AI-generated changes.

Read on parsimony.lasu.dev → Hacker News · 12 comments

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.