HealthBench HardBODHI
…rk through controlled evaluation on 200 clinical vignettes from HealthBench Hard, assessing GPT-4o-mini and GPT-4.1-mini across 5 random seeds (…
1articles mentioning institutions
2institution mentions
1distinct institutions extracted
0%of mentions human-reviewed
Active filtersEntity: HealthBench Hard ×
HealthBench Hard
This institution is selected. Its supporting articles are shown below.