# A Controlled Test Finds No Advantage for Vendor-Native Coding Harnesses

Paired runs on 80 private tasks put Anthropic's own agent software within 1.25 percentage points of an open-source alternative on the same model, in both directions.

- Published: 2026-09-14T06:22:55.303Z
- Canonical: https://polylog.news/ai/2026-09-14/a-controlled-test-finds-no-advantage-for-vendor-native-codin
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv](https://arxiv.org/abs/2609.11987)

Practitioners generally assume that a coding agent performs best when the model runs inside the harness its own vendor ships, meaning the tools, prompts, and control flow that turn a chat model into an autonomous software engineer. A prepri…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-14/a-controlled-test-finds-no-advantage-for-vendor-native-codin (subscription information: https://polylog.news/pricing).