Five surprising facts about GPT-5 and health AI

gpt-5-thinking achieved a score of 46.2% on HealthBench Hard.

gpt-5-thinking outperforms previous models in health-related settings.

The model shows an 8x reduction in failures in urgent health situations.

gpt-5-thinking never provided harmful assistance in health evaluations.

The health performance improvement follows extensive model safety training.

Space: Let’s explore the GPT-5 Model Card