Open Source52d ago
Detected, not submitted
DFAH-Bench
Own DFAH-Bench?
Verify your site to claim this listing and get emailed the moment a buyer's looking for something like it.
A PyPI library that evaluates AI agents not just on whether they reach the right decision, but whether they follow the same tool paths and arguments consistently across repeated runs.
Spotted on Hacker News on August 2, 2026.
RA
raffisk
Maker