Health Optimization BenchLeaderboard16 models · 257 tasks
16 frontier models on 257 rubric-graded tasks, across eight subject areas of preventive and optimization medicine.
Work
From the lab
Benchmarks and studies we have published or are building.
Recent work
Clinical Reasoning BenchIn development
Our second benchmark, now in development.
Multilingual clinical speechEast Africa
An overview of multilingual clinical speech from East Africa.