Leading AI chatbots avoid harm but fall short in high-risk conversations, startup’s new benchmark finds

https://cdn.geekwire.com/wp-content/uploads/2026/05/mpathic-1.png" width="900" />
Seattle-based mpathic released mPACT, a clinician-led benchmark that evaluates how leading AI models handle conversations involving suicide risk, eating disorders, and misinformation. https://www.geekwire.com/2026/leading-ai-chatbots-avoid-harm-but-fall-short-in-high-risk-conversations-startups-new-benchmark-finds/">Read More