2 sources
Co-authored SWE-bench: a key benchmark for whether models can resolve real GitHub issues.
Researcher Profile
Alexander Wettig
Measuring real-world coding ability (SWE-bench)
Researcher at Princeton University
Co-authored SWE-bench: a key benchmark for whether models can resolve real GitHub issues.
Organizations
Princeton University
About This Page
This profile is meant to help you get oriented quickly: why this researcher matters, what to read first, and where to explore next.
Last updated
March 20, 2026
Official And External Links
Known For
The ideas, systems, and research directions that make this person worth knowing.
01
Measuring real-world coding ability (SWE-bench)
02
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
03
SWE-bench (GitHub)
04
Evaluation
05
SWE-bench
06
Code
Start Here
Canonical papers, project pages, or repositories that anchor this profile.
Signature Works
Additional papers, projects, or repositories that help flesh out the profile.
Related Researchers
People worth exploring next because they share topics, labs, or source material with this profile.
2 sources
Co-authored SWE-bench: a key benchmark for whether models can resolve real GitHub issues.
2 sources
Co-authored SWE-bench: a key benchmark for whether models can resolve real GitHub issues.
3 sources
Co-authored SWE-bench and ALiBi: high-leverage evaluation + long-context work.
1 source
Co-authored ARC: an influential reasoning benchmark for question answering.
1 source
Co-authored ARC: an influential reasoning benchmark for question answering.