InclusionMed AI Evaluation Benchmark Released
The story so far
Hugging Face has released the AI evaluation benchmark InclusionMed for inclusive healthcare, aiming to ensure that global diverse healthcare needs guide the development direction and metrics of medical AI. InclusionMed consists of two parts: Atlas and Index. Atlas organizes the evaluation benchmark by medical role and AI capability. Index summarizes the benchmark model results contained in Atlas; in the initial version, the Index score for each model is the equal-weighted average of its five benchmark scores. Index also reports scores by medical role and AI capability, revealing differences in model rankings and score levels.
AI-written from the reports · Updated 20 minutes ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersInclusionMed: Benchmarking AI for Inclusive Healthcare
InclusionMed is an open and inclusive medical AI evaluation initiative, gradually released through Atlas and Index, aiming to guide the development direction and metrics of medical AI based on the diverse healthcare needs of people worldwide.
Heat over time
Not enough data yet to draw a trend.