Clinical Benchmarks

ZJU4HealthCare

ZJU4HealthCare models with results here, each placed on its own board.

Models
2
Results
2
Boards
1 of 13

github.com/ZJU4HealthCare

Models

ModelKindReleasedBoards
HealthGPT-Pro-4BModelNot stated1
HealthGPT-Pro-8BModelNot stated1

Results

One line per result. Dark tick: the board leader.

Safety

  1. MedPIC
    HealthGPT-Pro-8B
    zero-shot; independent questions; exact option-set match
    42.6
    Rank 22 of 28Leader Gemini-3.1-Pro 80.7
    Independent run
    Measured Aug 2026
  2. MedPIC
    HealthGPT-Pro-4B
    zero-shot; independent questions; exact option-set match
    36.0
    Rank 28 of 28Leader Gemini-3.1-Pro 80.7
    Independent run
    Measured Aug 2026