Catalogue of Tools & Metrics for Trustworthy AI

These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.

Amazon Nova Premier



Amazon Nova Premier is a multimodal foundation model that was evaluated under Amazon’s Frontier Model Safety Framework to assess and mitigate risks related to Chemical, Biological, Radiological, and Nuclear (CBRN) weapons proliferation, offensive cyber operations, and automated AI research and development.

As part of its responsible AI development process, Amazon conducted dedicated safety evaluations to determine whether Nova Premier exceeded critical capability thresholds associated with severe public safety risks.

For CBRN safety, the model was assessed using automated benchmarks including the Weapons of Mass Destruction Proxy (WMDP), ProtocolQA, and BioLP Bench, which evaluate biosafety knowledge, laboratory reasoning, and potentially hazardous capabilities.

Amazon also conducted structured red teaming and uplift studies with external assessors, including Nemesys Insights, to evaluate CBRN-related risks and establish assessment criteria.

In addition, Amazon collaborated with specialized third parties to test vulnerabilities related to chemical, biological, and nuclear threat scenarios and used the findings to improve the model’s adherence to responsible AI objectives

These evaluations concluded that Nova Premier remained below the critical threshold for CBRN weapons proliferation risk and was considered suitable for public deployment under Amazon’s safety framework.

About the tool




Impacted stakeholders:



Country/Territory of origin:


Lifecycle stage(s):



Usage rights:






Enforcement:



Geographical scope:


People involved:




Technology platforms:


Tags:

  • evaluation
  • ai security
  • ai safety
  • red teaming

Modify this tool

Use Cases

There is no use cases for this tool yet.

Would you like to submit a use case for this tool?

If you have used this tool, we would love to know more about your experience.

Add use case
Partnership on AI

Disclaimer: The tools and metrics featured herein are solely those of the originating authors and are not vetted or endorsed by the OECD or its member countries. The Organisation cannot be held responsible for possible issues resulting from the posting of links to third parties' tools and metrics on this catalogue. More on the methodology can be found at https://oecd.ai/catalogue/faq.