Get up and running on the Portex Datalab.
This page gives a short overview of the two main workflows on Portex. For detailed guides, follow the links in each section.
You create evals and sell (or open-source) them.
Create an account with seller access enabled
Design your eval: decide between Q&A (single-turn) and Agentic (multi-turn) and follow the best practices guide
Build your eval using the Eval Builder (or import files for Q&A evals if you prefer working in an editor)
Publish a listing commercially, or open-source itarrow-up-right for community use
Review results as model builders submit runs and annotate responses to improve your eval
You run models against expert evals and receive scored reports.
Create an account
Browse evals on the Datalab
Run an eval: download tasks, generate model responses, upload and pay
Optionally purchase the Core Dataset for model improvement
Last updated 18 days ago