METR Blog company blog

Many SWE-bench-Passing PRs would not be merged

We find that roughly half of test-passing SWE-bench Verified PRs written by recent AI agents would not be merged into main by repo maintainers. A naive interpretation of benchmark scores may lead one to overestimate how useful agents are without more elicitation or human feedback.
Points
278
HN comments
153
Submissions
1
Cited by
0 commenters

Software EngineeringAI & Machine Learning2026

On Hacker News

SubmittedTitle on HNPointsComments
Mar 11, 2026Many SWE-bench-Passing PRs would not be merged by mustaphah278153

More from METR Blog

All 6 posts →

Related posts from the same era