SWE-bench/SWE-bench

SWE-bench: Can Language Models Resolve Real-world Github Issues?

6.0k

Stars

1.0k

Forks

64.8

Radar Score

Rising

Momentum

Scoring Breakdown

Impact87.3

Velocity45.2

Health56.2

Growth Metrics

7-Day Stars

+36

30-Day Stars

+184

Acceleration

0.84x

Language

Python

Why it ranks

Steady growth — consistently collecting stars and contributors.

Top 89% globallyLast push 24d ago+36 stars / 7d+184 stars / 30d