About
MAST
The Medical AI Superintelligence Test (MAST) is an active collaborative effort run by the ARISE AI Research Network to curate a centralized resource of the most robust and realistic clinical benchmarks to measure the performance of medical AI.
MAST exists to ensure that AI entering healthcare is rigorously tested, independently validated, and held to the highest clinical standards before it reaches patients.
Our Mission
To establish an open, evidence-based evaluation framework that holds medical AI to the highest clinical standards — ensuring that deployed systems help rather than harm patients. We believe rigorous, independent benchmarking is the foundation of safe AI adoption in healthcare.
Who We Are
MAST is developed by a multidisciplinary team of clinicians, AI researchers, biostatisticians, and medical educators from the ARISE Network — an independent academic collaborative spanning Stanford Medicine, Harvard Medical School, and partner institutions committed to advancing safe and reliable clinical AI through open science.
Our Approach
We evaluate AI systems the way medicine evaluates treatments: with blinded assessments, expert panels, standardized rubrics, and transparent methodology. Every benchmark in the MAST suite is designed by board-certified physicians, validated against clinical consensus, and resistant to data contamination or shortcut learning.