MentalHealthBench
AssessTools
An expert-informed benchmark for evaluating AI responses in mental health conversations.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 5OpenAI Blog·9/23/2026researchOpenAI Introduces MentalHealthBench
OpenAI introduced MentalHealthBench, an expert-informed benchmark designed to evaluate how well AI systems respond in realistic mental health conversations. The benchmark focuses on both helpfulness and safety in these sensitive interactions.