OpenAI Evals

Framework / harness (not an eval — tooling/reference entry)

OpenAI's original eval framework and registry, incl. MakeMeSay, MakeMePay persuasion evals.

Category: Eval frameworks & harnesses
Insurance exposure: Unmapped
Publisher: OpenAI
Publisher type: Frontier lab
License: MIT
Status: Maintained (<12mo)
Last commit: 2026-04-14
Stars: 19609
Notes: OpenAI now pushes dashboard evals.

View source on GitHub →

Wanich Risk Lab, 2026.