mupt-ai/self-bench
Benchmark coding agents and models on your own repository with private Harbor-formatted evals built from its merged pull requests.
4 best points · 0 comments · 2 Hacker News posts · 34 GitHub stars · View on GitHub
Hacker News discussions
- Show HN: Self-bench – benchmark coding agents on real-world software (4 points, 0 comments, by avyayv, 2026-10-05)
- Show HN: Self-bench – build SWE-bench style evals from private repos (3 points, 0 comments, by byhong03, 2026-08-14)