InclusionMed launches open medical AI benchmark atlas after auditing 388 candidates

The InclusionMed Collaboration · hf · 2026-11-17

InclusionMed is an open evaluation initiative auditing and reproducing medical AI benchmarks across healthcare roles and AI capabilities. From 388 candidates, structured audits and independent reproduction selected four public benchmarks, plus the private diagnostic-reasoning benchmark InclusionMed-DxFiles, forming a five-benchmark Atlas. Findings show model rankings and inference costs vary by context, motivating broader context-specific evaluation.

Original post →

More from Research

Research channel →