Benchmark · general

HealthBench

1 results 1 models

OpenAI's physician-graded health-conversation benchmark.

0 12.5 25 37.5 50 2025-08-07 GPT-5 · 46.2 · 2025-08-07
GPT-5
Timeline
Date Model Score Source
2025-08-07 GPT-5 46.2% OpenAI launches GPT-5 with adaptive reasoning and unified architecture