Inspect Evals

by UK AI Security Institute & community

Editor note

A large, actively maintained collection of ready-to-run evals implemented in the Inspect framework.

What it tests: Many benchmarks under one runner: coding, agents, safety, knowledge.
Original source: github.com/UKGovernmentBEIS/inspect_evals
Last updated: Repo last commit 2026-10-15
License: MIT

Facts come only from the linked source (checked 15 Oct 2026). Credit belongs to the creators.

No reviews yet.

Reviews from practitioners who sign in with GitHub open soon.