Center for AI Safety — Provider Intelligence Profile

What this reference supports

The Center for AI Safety (CAIS) is a San Francisco-based non-profit research organization that publishes HarmBench, an open evaluation framework and set of classifier models for red-teaming and safety-testing language models. Center for AI Safety is a non-profit research institute, founded in 2022 and headquartered in San Francisco, CA, USA. ModelRefs currently indexes 1 canonical model from Center for AI Safety. Center for AI Safety's indexed lineup includes at least one open-weight model available for self-hosted deployment.

Use this page to check Center for AI Safety's indexed model coverage, open-source posture, and top-scoring tracked capability, then review the Quick Facts panel and the provider implementation reference below for deployment, governance, and pricing detail before comparing it against other providers.

Catalog presence and these figures reflect ModelRefs' own canonical registry, not an external ranking or endorsement. Model coverage and capability scores change as evidence is added, and provider-published claims — compliance, pricing, regional availability — should be confirmed directly with Center for AI Safety before implementation.