SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

By Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Kexin Pei, Ofir Press, Karthik Narasimhan. 2023

3,028 citations recorded by the source corpus.

Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We find real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models. To this end, we introduce SWE-bench, an evaluation framework consisting of $2,294$ software engineering problems drawn from real GitHub issues and corresponding pull requests across $12$ popular Python repositories. Given a codebase along with a description of an issue to be resolved, a language model is tasked with editing the codebase to address the issue. Resolving issues in SWE-bench frequently requires understanding and coordinating changes across multiple functions, classes, and even files simultaneously, calling for models to interact with execution environments, process extremely long contexts and perform complex reasoning that goes far beyond traditional code generation tasks. Our evaluations show that both state-of-the-art proprietary models and our fine-tuned model SWE-Llama can resolve only the simplest issues. The best-performing model, Claude 2, is able to solve a mere $1.96$% of the issues. Advances on SWE-bench represent steps towards LMs that are more practical, intelligent, and autonomous.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems, Evaluation & Benchmarks, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Noah A. Smith
  2. Luke S. Zettlemoyer
  3. Percy Liang
  4. Joseph E. Gonzalez
  5. Mohit Bansal
  6. Graham Neubig
  7. Yejin Choi
  8. Jianfeng Gao

In Computer Networks and Communications

  1. Joseph E. Gonzalez
  2. Ion Stoica
  3. Armando Solar-Lezama
  4. Shin Yoo
  5. Noah A. Smith
  6. Chun Xia
  7. Koushik Sen
  8. Mark Harman

In Information Systems

  1. Koushik Sen
  2. Chun Xia
  3. Lingming Zhang
  4. Yinlin Deng
  5. Mark Harman
  6. Shin Yoo
  7. Ling-Ming Zhang
  8. Soren Dunn

In Evaluation & Benchmarks

  1. Luke S. Zettlemoyer
  2. Chun Xia
  3. Lingming Zhang
  4. Noah A. Smith
  5. Armando Solar-Lezama
  6. Ranjay Krishna
  7. Mark Harman
  8. Naman Jain

In Code Generation & Program Synthesis

  1. Armando Solar-Lezama
  2. Noah A. Smith
  3. Chun Xia
  4. Koushik Sen
  5. Mark Harman
  6. Luke S. Zettlemoyer
  7. Yushi Hu
  8. Jiawei Liu

Citations in the corpus