Share your thoughts, 1 month free Claude Pro on usSee more

Healthcare QA on HealthBench 500

41.16Rubric Score

POP

Updated 1mo ago

Evaluation Results

Method	Links
POP 2026.04		41.16
Qwen-2.5-7B-Inst 2026.04		40.83
POP 2026.04		29.97
Qwen-2.5-7B 2026.04		26.36
Train on D 2026.04		26.14
Train on D 2026.04		23.89