SWE-bench / SWE-bench Lite

ICLR 2024 (Oral Presentation)

@inproceedings{
    jimenez2024swebench,
    title={{SWE}-bench: Can Language Models Resolve Real-world Github Issues?},
    author={Carlos E Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik R Narasimhan},
    booktitle={The Twelfth International Conference on Learning Representations},
    year={2024},
    url={https://openreview.net/forum?id=VTF8yNQM66}
}
Jimenez, C. E., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., & Narasimhan, K. R. (2024). SWE-bench: Can Language Models Resolve Real-world Github Issues? In The Twelfth International Conference on Learning Representations. https://openreview.net/forum?id=VTF8yNQM66
Jimenez, Carlos E., et al. "SWE-bench: Can Language Models Resolve Real-world Github Issues?" The Twelfth International Conference on Learning Representations, 2024.

SWE-bench Multimodal

ICLR 2025

@inproceedings{
    yang2025swebench,
    title={{SWE}-bench Multimodal: Do {AI} Systems Generalize to Visual Software Domains?},
    author={John Yang and Carlos E Jimenez and Alex L Zhang and Kilian Lieret and Joyce Yang and Xindi Wu and Ori Press and Niklas Muennighoff and Gabriel Synnaeve and Karthik R Narasimhan and Diyi Yang and Sida Wang and Ofir Press},
    booktitle={The Thirteenth International Conference on Learning Representations},
    year={2025},
    url={https://openreview.net/forum?id=riTiq3i21b}
}
Yang, J., Jimenez, C. E., Zhang, A. L., Lieret, K., Yang, J., Wu, X., Press, O., Muennighoff, N., Synnaeve, G., Narasimhan, K. R., Yang, D., Wang, S., & Press, O. (2025). SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? In The Thirteenth International Conference on Learning Representations. https://openreview.net/forum?id=riTiq3i21b
Yang, John, et al. "SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?" The Thirteenth International Conference on Learning Representations, 2025.

SWE-bench Verified

Original SWE-bench Paper

@inproceedings{
    jimenez2024swebench,
    title={{SWE}-bench: Can Language Models Resolve Real-world Github Issues?},
    author={Carlos E Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik R Narasimhan},
    booktitle={The Twelfth International Conference on Learning Representations},
    year={2024},
    url={https://openreview.net/forum?id=VTF8yNQM66}
}

SWE-bench Verified Blog Post

@misc{chowdhury2024swebenchverified,
  title={Introducing {SWE}-bench Verified},
  author={Chowdhury, Neil and Aung, James and Shern, Chan Jun and Jaffe, Oliver and Sherburn, Dane and Starace, Giulio and Mays, Evan and Dias, Rachel and Aljubeh, Marwan and Glaese, Mia and Jimenez, Carlos E. and Yang, John and Ho, Leyton and Patwardhan, Tejal and Liu, Kevin and Madry, Aleksander},
  year={2024},
  url={https://openai.com/index/introducing-swe-bench-verified/},
}