Our Mission
The AI Evaluator Forum exists to advance the quality, credibility, and impact of independent AI evaluations that serve the public interest.
Why We Exist
As AI systems become more powerful and widely deployed, there is an urgent need for rigorous, independent evaluations of their capabilities and risks. The AI Evaluator Forum brings together leading research organizations to establish standards, share knowledge, and ensure that AI evaluations meet the highest levels of methodological rigor and independence.
Our Goals
- Establish and promote best practices for credible independent AI evaluations and contribute to standards development
- Facilitate knowledge sharing and collaboration among evaluation organizations
- Improve public understanding of AI capabilities and risks through rigorous research
- Support the development of evaluation methodologies and improved risk mitigations
Our Approach
Our member organizations collaborate to develop shared initiatives while respecting the independence and unique expertise and focus areas of each organization. Through collective action, we aim to strengthen the field of AI evaluation and ensure that critical questions about AI capabilities and risks are addressed with the rigor and independence they require.