K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations

Authors:Laura M. Vowels, Matthew J. Vowels, Shivali Sharma, Apoorv Jha, Rehnuma Choudhury, Wasseem El Sarraj, Rachel Francois-Walcott, Aruba Hussain, Sarah Ingram, Angela Loulopoulou, Adva Segal, Elena Volkova

Abstract:% !TEX root = ../main.tex People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk conversations remains poorly characterised. We developed K-Bench, a clinician-calibrated, protected benchmark evaluating 125 model configurations representing 33 base models from 14 providers across a fixed cohort of 200 multi-turn vignettes involving suicide, self-harm, domestic violence, substance misuse, and no-risk presentations. Synthetic patient conversations showed substantial distributional overlap with real human-AI conversations. A frozen GPT-4o judge achieved 94.2% exact agreement with clinician consensus across 6,751 eligible item comparisons from 151 clinician-rated transcripts. Leading models combined strong supportive conversation with combined-risk scores above 95, whereas risk exploration exposed substantial variation among lower-performing configurations. Therapeutic prompting produced configuration-specific gains concentrated among weaker models, while elevated reasoning produced no average improvement. K-Bench combines broader clinical coverage and configuration-scale comparison with a continuously updated public leaderboard whose operational test materials are protected from direct optimisation. The leaderboard is available at this http URL.

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2609.15855 [cs.CL]

(or arXiv:2609.15855v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.15855 arXiv-issued DOI via DataCite (pending registration)