Start with an
open eval suite
Free to discover and run with any Yearly plan. Publish, discover, and run evaluation suites for LLMs securely.
How does it work?
We've built a decentralized marketplace for AI evaluation. You can browse certified packages or community contributions and run them directly against your own models using your own API keys.
EvalKit is free during early access — no credit card, no run limits. All evaluations are performed locally or in your private environment to ensure data privacy.
Featured Packages
View all packages →No featured packages yet.