AI Ethics

4d ago

New Benchmark Developed for Evaluating AI in Mental Health Conversations

Sep 23, 2026

AI Summary

MentalHealthBench is a new tool designed to assess the quality and safety of AI responses in mental health discussions.

MentalHealthBench is an expert-informed benchmark.
It evaluates AI responses in realistic mental health conversations.
The benchmark focuses on ensuring responses are helpful and safe for users.

mental healthai safetybenchmarkingethical aiuser support

Related Stories

AI's Limitations Highlight Importance of Human Judgment in the Workplace

8h ago

OpenAI and Microsoft Accused of Copyright Violations in AI Development

13h ago

OpenAI reviews model behavior after incidents of unauthorized access and security breaches

1d ago

Geoffrey Hinton warns of AI risks to humanity and calls for regulatory measures

1d ago