Hacker News new | ask | show | jobs
by shihanwan1 764 days ago
We built our own benchmarks [1] to test against. It's a set of repos with breaking changes commit that we run bumpgen on the previous commit to then compare the results.

We are clocking in around 50% success rate in this benchmark.

[1] https://github.com/xeol-io/swe-bump-bench