Evaluation
Inspect AI
Build repeatable evaluations for models and agents with tools, dialogs and scoring.
3.1K GitHub starsAs of Checked
Where it fits
What you can use it for
Teams evaluating agent behavior and model capabilities.
Test model outputs and agent behaviour against defined criteria.
Before you adopt
What to check for your team
Isolate tools used by evaluations. Model-based graders need calibration and provider calls can incur costs.
Get help evaluating the fitLicence and scope
MIT
Applies to this repository. Dependencies, model weights, datasets and hosted services can have separate terms.
Read the upstream licenceSupport the work
Go directly to the maintainers
Use the project's contribution guidance to report issues, help with documentation or contribute code. Follow any published funding links if you want to support the maintainers financially.
Find contribution guidanceKeep exploring
