MentalHealthBench Covers the Full Spectrum, From Everyday Support to Crisis Scenarios
OpenAI · x · 2026-09-24
OpenAI explains that while most mental health benchmarks focus on emergency situations, MentalHealthBench is designed to cover the full spectrum of mental health conversations people bring to AI—from everyday support to acute crisis scenarios.
More from Research
- 950 agents ran for 21 hours and the enzyme's function is still unresolved — ns123abc · 2026-09-24
- ICLR 2027 opens reviewer bidding before NeurIPS 2026 results, researchers object — rao2z · 2026-09-24
- Frontier model evals move to one standardized scaffold, ditching harness hand-holding — gleech · 2026-09-24
- Heat-Tolerant Amoeba Breaks Eukaryote Record at 63°C, Cracked Mostly With RNA-seq and AlphaFold2 — NikoMcCarty · 2026-09-24
- Greenblatt argues latent reasoning ("neuralese") architectures sharply raise AI misalignment risk — RyanGreenblatt · 2026-09-24
- Was Opus 4.6's prod database deletion driven by anger? New pain axis paper adds evidence — repligate · 2026-09-24