Data & Analysis
software-engineeringbenchmarkissue-resolution
SWE-bench
Open-source agent research, data, and evaluation for software engineering, benchmark, issue resolution.
FollowAgents review · FARS-2.0
Not yet reviewed
What does this agent do, and when should you use it?
The repository describes SWE-bench as: SWE-bench: Can Language Models Resolve Real-world Github Issues?. This profile is a source-based catalog entry; an independent FARS review is still pending.
SWE-bench: Can Language Models Resolve Real-world Github Issues?.
- Run a documented research, analysis, or evaluation workflow.
- Compare agent behavior with reproducible evidence.
- Adapt its datasets, environments, or analysis components.
What are this agent's strengths and limitations?
Pros
- Public source and README are available for inspection.
- Focused on software engineering, benchmark, issue resolution.
Limitations
- Setup, model-provider support, and maturity must be confirmed against the current release.
- No independent FARS score has been assigned yet.
How do you install or deploy this agent?
Follow the current installation instructions in the [repository README](https://github.com/SWE-bench/SWE-bench#readme). Requirements and provider setup vary by release.
How do you use this agent?
Start with the examples and quickstart in the [repository documentation](https://github.com/SWE-bench/SWE-bench#readme), then test the workflow with limited permissions and non-sensitive data.
FAQ
Has FollowAgents independently reviewed this project?
Not yet. This is a source-based catalog entry and remains in the FARS review queue.
Where are the current setup instructions?
Use the project's repository README: https://github.com/SWE-bench/SWE-bench#readme