SWE-bench
ActiveDescription
SWE-bench is a benchmark for evaluating language models on real-world GitHub issue resolution, featuring genuine problems from popular Python repositories, now a core standard for measuring AI coding agent capabilities.
Related Projects
Augment SWE-bench Agent
867 · Python
Augment SWE-bench Agent is the number one open-source SWE-bench Verified implementation, demonstrating how to build high-performance software engineering agents to automatically resolve GitHub issues.
codingpythonagent +2
AutoCodeRover
3.1k · Python
AutoCodeRover is a project structure-aware autonomous software engineer agent that achieves automated program repair and issue resolution by understanding the overall codebase architecture.
codingpythonagent +2
DeepCode
15.2k · Python
DeepCode is an open agentic coding platform supporting Paper2Code, Text2Web, and Text2Backend, leveraging agent technology for automated software development workflows.
codingpythonllm +2
Kodezi Chronos
5.0k · Java
Kodezi Chronos is a debugging-first language model achieving state-of-the-art performance on SWE-bench, capable of autonomously handling software debugging and code repair tasks.
codingjavallm +2