Reproduce “InclusionMed: Benchmarking AI for Inclusive Healthcare” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

InclusionMed Collaboration

InclusionMed organizes healthcare benchmark evaluation by the roles represented and capabilities tested, then reports an equally weighted Index and category-specific scores. Its first release covers five benchmarks across only three of nine role–capability cells, with none focused on patient and public assistance. Across 22 model releases, scores ranged from 17.5 to 49.1, showing portfolio-specific results, not clinical suitability.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.