inspect_evals

UK AISI/Arcadia/Vector: GAIA and other evals in Inspect AI; level 1–3, sandboxed, tool-calling solvers.

evalssandbox

Stars: 730
Adoption surface: slightly complex
Autonomy: headless
Recovery: resumable
License: ✅ open-source
Category: Evaluation and benchmarking harnesses

Repository ↗ Example: inspect SWE-bench eval ↗

Related in Evaluation and benchmarking harnesses

Agent Lightning
SWE-bench
AgentBench
inspect_ai
WebArena
ClawBench

Maintain inspect_evals? Add the badge

Paste this into your README so readers can find the list and see how inspect_evals compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)