#swe-bench
2 briefs tagged #swe-bench.
Research
Researchers introduce SWE-Bench ProMax
The benchmark tests AI coding agents on 170 multilingual code refactoring tasks.
HF Daily Papers+1 outlet·5d ago
Research
SWE-Touch tests coding agents in shared workspaces
The benchmark finds user counter-edits reduce coding-agent resolve rates on SWE-bench Verified.
arXiv cs.AI+1 outlet·Aug 4