# OpenAI's Mental-Health Benchmark Scores Its Own Model Above Clinician-Written Replies

GPT-6 Astra reached 57.3 on MentalHealthBench against 38.5 for expert-authored answers, a gap OpenAI attributes partly to clinicians writing short responses that collect fewer scoring points.

- Published: 2026-09-25T06:22:14.083Z
- Canonical: https://polylog.news/ai/2026-09-25/openai-s-mental-health-benchmark-scores-its-own-model-above
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [Anthropic Research](https://www.anthropic.com/research/team/societal-impacts), [Investing.com](https://in.investing.com/news/stock-market-news/openai-launches-mentalhealthbench-to-evaluate-ai-mental-health-responses-93CH-5603648)

OpenAI released MentalHealthBench, an open benchmark for grading model behavior in realistic mental-health conversations, built with input from more than 80 licensed psychologists and psychiatrists working across 22 countries, 19 languages…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-25/openai-s-mental-health-benchmark-scores-its-own-model-above (subscription information: https://polylog.news/pricing).