HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench
TL;DR
Evaluating 20 frontier and open models under a cross-vendor panel of three LLM judges, it is found that a statistically tied frontier cluster, measurable refusal behavior in two models, and near-identical rankings across judges are found.
Abstract
General-purpose health benchmarks increasingly anchor claims about LLM medical performance, but they are not always resolved by clinical specialty, making domain-specific performance hard to isolate. Mental health is of acute public-health concern as millions of people turn to LLMs for psychological support, and most existing evaluations are bespoke academic benchmarks that are difficult to integrate into developer workflows. We introduce HealthBench-Psych and HealthBench-Psych-Hard. We screened HealthBench's 5,000 physician-rubric conversations for mental-health relevance with a transparent LLM-applied rubric, then validated the subset through two rounds of blinded clinician review with concealed known-exclude controls, yielding 610 conversations (12.2% of the corpus). Evaluating 20 frontier and open models under a cross-vendor panel of three LLM judges, we find a statistically tied frontier cluster, measurable refusal behavior in two models, and near-identical rankings across judges ($\tau \ge 0.92$). We release the subset, pipeline, model responses, grades, and analysis code as a reusable resource.