SWE-bench

Repository facts

Stars

6,046

Forks

1,022

Open issues and pull requests

40

Primary language

Python

License

MIT License (MIT)

Owner

SWE-bench · Organization

Created

Oct 4, 2023

Last push

Sep 18, 2026

Topics

• benchmark
• language-model
• software-engineering

Rank #1,342 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 1,625

  Rank 1,625: Kodezi/Chronos

  Kodezi Chronos is a debugging-first language model that achieves state-of-the-art results on SWE-bench Lite (80.33%) and 67% real-world fix accuracy, over six times better than GP…

  4,963 starsJavaOther licenseLast push Nov 12, 2025

• 7,064

  Rank 7,064: SWE-bench/SWE-smith

  [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

  804 starsPythonMITLast push Oct 12, 2026

• 1,866

  Rank 1,866: CLUEbenchmark/CLUE

  中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

  4,287 starsPythonNo license file detectedLast push Feb 6, 2026

• 2,441

  Rank 2,441: xlang-ai/OSWorld

  [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

  3,217 starsPythonApache-2.0Last push Sep 14, 2026

• 664

  Rank 664: bytedance/trae-agent

  Trae Agent is an LLM-based agent for general purpose software engineering tasks.

  12,145 starsPythonMITLast push Feb 5, 2026

• 2,171

  Rank 2,171: mgsalem/Tensorflow-Project-Template

  A best practice for tensorflow project template architecture.

  3,616 starsPythonApache-2.0Last push Apr 21, 2022