---
title: "Study: fancier coding-agent harnesses cost more, don't score better"
url: https://www.parallelquant.com/posts/study-fancier-coding-agent-harnesses-cost-more-don-t-score-better-1035e7
source_name: "The Decoder"
source_url: https://the-decoder.com/fancy-harnesses-make-coding-agents-more-expensive-but-not-better-study-finds/
published: 2026-10-24T09:21:39.000Z
topics: ["research", "agents", "llms"]
publisher: "Parallel Quant"
---

# Study: fancier coding-agent harnesses cost more, don't score better

*2026-10-24 · Source: [The Decoder](https://the-decoder.com/fancy-harnesses-make-coding-agents-more-expensive-but-not-better-study-finds/)*

A controlled study compared coding-agent harnesses such as Claude Code, OpenCode and mini-SWE-agent. Switching harnesses moved pass rates barely more than simply rerunning the same setup. Cost per task could triple, driven mainly by the system prompt being resent at every step.

**Why it matters:** It suggests much of the recent harness engineering race buys little measurable accuracy, so model quality and run-to-run variance matter more than scaffolding. For teams deploying agents, trimming prompt overhead is likely a cheaper lever than adopting a heavier harness. It also warns that single-run harness comparisons are noisy and should be repeated before drawing conclusions.

**Topics:** research, agents, llms

---
Read the original: https://the-decoder.com/fancy-harnesses-make-coding-agents-more-expensive-but-not-better-study-finds/
Canonical: https://www.parallelquant.com/posts/study-fancier-coding-agent-harnesses-cost-more-don-t-score-better-1035e7
Published by Parallel Quant — https://www.parallelquant.com