---
title: "Parsimony"
description: "Open benchmark that ranks AI coding models by how much code their SWE-bench patches add, counting net syntax units instead of lines, with an upload-your-own-results chart."
canonical: "https://vibing.inc/library/parsimony-vg-2566"
category: "Dev Utilities & Vibe-Coding Tooling"
subcategory: "Codebase hygiene"
license: "open-source"
author: "@La5u"
source: "https://parsimony.lasu.dev/"
---

# Parsimony
Open benchmark that ranks AI coding models by how much code their SWE-bench patches add, counting net syntax units instead of lines, with an upload-your-own-results chart.
## Facts
- Source: https://parsimony.lasu.dev/
- Category: Dev Utilities & Vibe-Coding Tooling / Codebase hygiene
- Author: @La5u
- Licence: open-source
- Tags: benchmark, ai-models, code-quality, swe-bench, leaderboard
## Why it's a gem
The only leaderboard that punishes models for bloating your codebase.
---
Listed in The Vibeary: https://vibing.inc/library/parsimony-vg-2566 · JSON: https://vibing.inc/api/public/library/gems/parsimony-vg-2566