Show HN: Self-bench – benchmark coding agents on real-world software
By avyayv · 2026-10-05 · 4 points · 0 comments
https://github.com/mupt-ai/self-bench
Hey HN, Today, we're launching selfbench.dev, an open-source tool that lets you create and run evals automatically from your PRs. Every benchmark with sufficient trust eventually gets benchmaxxed (Goodhart's law) - the labs are incentivized to maximize their scores on that bench…
Open the full discussion on BetterNews