agent-ecosystem / agent-reading-testView on GitHub
A benchmark website that tests how well AI coding agents read web content. 10 task pages, each targeting a failure mode from the Agent-Friendly Documentation Spec. Agents report the canary tokens they encountered; the scoring form turns that into a 20-point breakdown.
☆16Sep 27, 2026Updated last week

Alternatives and similar repositories for agent-reading-test

Users that are interested in agent-reading-test are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?