AI brief
A controlled study found that switching between coding-agent harnesses such as Claude Code, OpenCode and mini-SWE-agent barely changed pass rates more than rerunning the same setup, while cost per task could triple.
Why it matters: It suggests teams may pay significantly more for harness changes without gaining measurable accuracy.
Written by AI from The Decoder's published text.
Source
“A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup.”
Reporting from a publisher outside the organisation being covered.
Read original story ↗