Unverified50% confidenceFactExact time
MentalHealthBench emphasizes a dual standard of "helpful and safe," measuring both helpfulness and safety simultaneously.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIf widely adopted, MentalHealthBench has the potential to provide quantitative reference criteria for minimum safety thresholds before AI mental health products go live.74% similarUnverifiedMentalHealthBench is an evaluation benchmark designed with expert involvement to measure whether AI systems' responses in real mental health conversation scenarios are both helpful and sufficiently safe.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945034API
curl https://kongchang.com/api/v1/knowledge/claims/945034MCP
get_claim(id=945034)