HealthBench-Psych

What is HealthBench-Psych?

Evaluates LLMs on 610 mental-health conversations from HealthBench using a three-judge panel and physician rubrics, with a harder 119-conversation subset.

Released

2026-08-25

Evaluates

Biology & Drug Discovery, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.25071

HealthBench-Psych paper, code and dataset

• Paper https://arxiv.org/abs/2608.25071
• Code https://github.com/mindbench-ai/healthbench-psych
• Dataset https://huggingface.co/datasets/mindbench-ai/healthbench-psych

Which sources cite HealthBench-Psych?

• HealthBench-Psych

Related Biology & Drug Discovery, Language & Knowledge, cs.CL benchmarks

• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• ActiveSciBench
• AdaMem-Bench
• AdaPlanBench
• AdvancedMathBench