Home› 🧠 Models ›Introducing MentalHealthBench… OpenAI 🧠 Models 🕐 Sep 23, 2026 👁 37 ⏱ 1 min read Introducing MentalHealthBench Annons Annons MentalHealthBench is an expert-informed benchmark for evaluating helpful and safe AI responses across realistic mental health conversations. Source: OpenAI — Published September 23, 2026 at 10:00 UTC — Category: Models 🔗 Read full article on OpenAI → Share: 𝕏 Twitter in LinkedIn 💬 WhatsApp 🔗 Copy Link More in Models The Decoder15h ago Anthropic pushes ahead with pre-Thanksgiving IPO despite tech selloff, accepts lower valuation The Decoder16h ago AI auditors catch most agent misbehavior but flood reviewers with false alarms, new study finds The Decoder16h ago Thinking Machines' Inkling 2 Small drops 316 F-bombs across benchmark runs The Decoder17h ago The gap between open and closed AI models in cyber capabilities keeps shrinking The Decoder20h ago State propaganda in some Chinese AI models is only "a thin layer" that fine-tuning can strip away The Decoder22h ago Nine AI agents tried autonomous research on open questions from US national labs and none passed the experts' bar Annons Annons