OpenAI Evals
/All repositories
Overview
HEALTH SCORE
Fair
60out of 100
Security posture drags the score down. Maintainer coverage and development cadence help keep it from falling further.
LIFECYCLE
Active
Consistent commits, responsive maintainers, regular releases, and healthy issue triage.
Health breakdown
Fair(60/100)
Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.
Maintainer responsiveness
Median response time is 9 days.
Bus factor
6 active maintainers currently have merge rights.
Organization Diversity
Contributors span 443 organizations.
Project Achievements
Leaderboards
About
OpenAI Evals is a framework for evaluating AI models through automated testing. It provides tools to create, run and analyze behavioral tests that assess model capabilities, weaknesses and risks across various tasks and metrics.
First commit
Software value
$1.9M
License(s)
Other
Links
Data sources
Git
GitHub