SWE-Gym

Training and evaluation for SWE agents and verifiers (ICML 2025).

evalstrainingpython

Stars: 754
Adoption surface: slightly complex
Autonomy: headless
Recovery: none
License: ✅ open-source
Category: Evaluation and benchmarking harnesses

Repository ↗ Example: SWE-Gym ICML 2025 paper ↗

Related in Evaluation and benchmarking harnesses

Agent Lightning
SWE-bench
AgentBench
inspect_ai
WebArena
ClawBench

Maintain SWE-Gym? Add the badge

Paste this into your README so readers can find the list and see how SWE-Gym compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)