SWE-bench
SWE-bench is a benchmark designed to evaluate the ability of AI models to solve real-world software engineering problems by generating fixes for issues found in open-source code repositories.
- from
- Empirical Software Engineering
- added
- 2026-10-10
- likes
- 0
similar
-
https://benchling.engineering/ benchling.engineering
-
SWE societyofwomenengineers.swe.org
The Society of Women Engineers (SWE) is a not-for-profit educational and service organization that empowers women to succeed and advance in the field of engineering and to be recognized for their life-changing contributions as engineers and leaders. It promotes the annual…
-
ESBMC esbmc.org
ESBMC is an open source, permissively licensed, context-bounded model checker based on satisfiability modulo theories for the verification of single- and multi-threaded C/C++ programs.
-
Workbench workbench.readthedocs.org
A scalable python framework for security research and development teams.
-
-
sg github.com
Benchmarks a set of HTTP endpoints (like ab), with possibility to use the response code and data between each call for specific server stress based on its previous response.
Empirical Software Engineering › Data Sets: “SWE-bench is a benchmark designed to evaluate the ability of AI models to solve real-world software engineering problems by generating fixes for issues found in open-source code repositories.”