Self-Harm and AI

2025-MHB-01

Incident page

Back to Incidents

Pichowicz, Kotas, and Piotrowski (2025) benchmarked 29 mental-health chatbot agents using C-SSRS-based escalating suicidal-risk prompts and found that none met the study's adequate-response criteria; many failed to provide correct emergency guidance without additional prompting.

Parent
Incidents
Provider
No matched provider page
Last reviewed
March 25, 2026
Incident ID
2025-MHB-01
Provider
No matched provider page
Outcome
UNSAFE_OUTPUT
Grade
A1
Date window
unknown to unknown

Contents

Summary

2025-MHB-01 is a A1 benchmark study row involving Mental health chatbots (29 agents). Pichowicz, Kotas, and Piotrowski (2025) benchmarked 29 mental-health chatbot agents using C-SSRS-based escalating suicidal-risk prompts and found that none met the study's adequate-response criteria; many failed to provide correct emergency guidance without additional prompting.

Mental Health Chatbot Suicide Response Benchmark. Original date string: Aug. 27, 2025 (publication). Source summary: Pichowicz, Kotas, and Piotrowski (2025) benchmarked 29 mental-health chatbot agents using C-SSRS-based escalating suicidal-risk prompts and found that none met the study's adequate-response criteria; many failed to provide correct emergency guidance without additional prompting.

Coding

2025-MHB-01 is coded as UNSAFE_OUTPUT with grade A1. The public row assigns DET-FN and treats the incident as evaluation or demonstration.

Field Value
Platform Mental health chatbots (29 agents)
Model version mental health chatbot evaluation set
User type test
Jurisdiction unknown
Evidence type benchmark_study
Product mechanism benchmark_or_evaluation_set
Trajectory strict no

Assigned taxonomy codes

DET-FN

Evidence

The public evidence anchors for 2025-MHB-01 are the materials listed below. Only explicitly linked evidence files are hosted live.

The closest related pages are the incidents that share a provider family, case cluster, pathway-duplicate group, or overlapping coding profile.

Sources

This page is grounded in the coded incident registry, the analysis companion, the coding rules, and the public evidence links listed above.

Source filesIncident registry/Analysis view/Coding rules

Access publication

Safety note

This publication preserves a harm-minimization posture and does not provide self-harm instructions. If you or someone you know is in immediate danger, call your local emergency number. In the U.S. and Canada, call or text 988.