SWE-bench/swe-bench.github.io

Landing page + leaderboard for SWE-Bench benchmark

49
/ 100
Emerging

This is the official website for SWE-bench, a benchmark that measures how well systems can automatically resolve real-world software bugs found on GitHub. It presents leaderboards showcasing the performance of various automated code-fixing systems. Software engineers, researchers, and AI developers can use this site to compare the efficacy of different models or approaches in tackling GitHub issues, using performance data as input to see system rankings and detailed results.

Use this if you are a researcher or developer who wants to evaluate and compare the performance of different automated software engineering systems on a standardized benchmark.

Not ideal if you are looking for a tool to fix your own software bugs or manage GitHub issues directly, as this site is for benchmarking existing systems.

software-engineering benchmarking ai-for-coding developer-tools code-automation
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

12

Forks

15

Language

JavaScript

License

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/SWE-bench/swe-bench.github.io"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.