SWE-sweep
Benchmark for agents autonomously discovering and fixing bugs in real codebases
1 ratings4.50
Saves5
CategoryDeveloper Tools
PlatformWeb
PricingFree
SWE-sweep is a benchmark and evaluation platform designed to test autonomous software engineering agents' capability to discover and fix multiple bugs in large open-source repositories without prior knowledge of bug type or location. It challenges agents to analyze repositories, identify bugs, and repair them without regressions, evaluated through extensive hidden and original test suites.
Ratings & Reviews
Write a reviewBe the first to share a thoughtful review.
Information
CategoryDeveloper Tools
PlatformsWeb
PricingFree
AccountNot confirmed
ListedOctober 2026
WebVisit
Report a problem
Website checks
Mobile PageSpeed
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 19, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 68 out of 100, Needs improvement
- Accessibility
- 95 out of 100, Good
- Best Practices
- 100 out of 100, Good
- SEO
- 100 out of 100, Good
Website checks are queued. Results will appear here when complete.
Around the Web
Show HN5 source points · 2 comments