# SWE-bench

SWE-bench is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Tests whether coding systems can resolve real GitHub issues in complete software repositories.

## Details

- Address: Online, Global
- Website: [github.com/SWE-bench/SWE-bench](<https://github.com/SWE-bench/SWE-bench>)
- Tags: Helpful, Viral, Science
- Category: Coding
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: unit-test
- Organization: Princeton NLP
- Released: 2023-10
- Paper: [arxiv.org/abs/2310.06770](<https://arxiv.org/abs/2310.06770>)
- Leaderboard: [www.swebench.com/](<https://www.swebench.com/>)
- Repository: [github.com/SWE-bench/SWE-bench](<https://github.com/SWE-bench/SWE-bench>)
- Task count: 2,294
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is SWE-bench?

SWE-bench is at Online, Global.

### How do I contact SWE-bench?

To contact SWE-bench, visit https://github.com/SWE-bench/SWE-bench.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/swe-bench>)
- [Coding in Online](<https://aibenchmarkindex.com/global/online/category/coding.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.