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

• URL: http://arxiv.org/abs/2609.15855v2
• Date: Tue, 15 Sep 2026 07:30:50 GMT
• Title: K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
• Abstract summary: We developed K-Bench, a protected benchmark evaluating 125 model configurations representing 33 base models from 14 providers.<n>A frozen GPT-4o judge achieved 94.2% exact agreement with clinician consensus across 6,751 eligible item comparisons.<n>Leading models combined strong supportive conversation with combined-risk scores above 95, whereas risk exploration exposed substantial variation among lower-performing configurations.
• Score: 1.6247217262916298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 www.k-bench.ai.

Related papers

• Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting [59.709162055944915]
  ThyroidXAgent is an agentic AI system that coordinates specialized diagnostic tools and stores their outputs as an auditable case-level evidence record.<n>It was evaluated on 28,458 non-overlapping test cases, including 8,721 cases from 35 centres in the private NHC-MISD-TUS cohort.<n>It achieved a mean Dice score of 87.21 percent for segmentation and a mean AUROC of 0.9466 for benign-malignant classification.
  arXiv  Detail & Related papers  (2026-08-12T21:02:59Z)
• PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents [5.247635961504091]
  PatientAgentBench benchmarks patient-facing agentic healthcare.<n>It evaluates a foundation model wrapped in an agent with a sandbox of healthcare tools, conversing with a simulated patient.<n>We benchmarked 10 models across four families on the same 1,200 scenarios and found clinical gaps.
  arXiv  Detail & Related papers  (2026-07-28T09:24:04Z)
• Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases [71.12461204050985]
  MedSP1000 is an SP-derived interactive benchmark for clinical-agent evaluation.<n>It converts peer-reviewed SP teaching cases into executable scenarios with defined SP case scripts, clinical environment contexts, and human-validated structured rubrics.<n>Applying MedSP1000 to a range of general-purpose and medically specialized LLMs, we find that performance on static benchmarks does not reliably translate to such educational scenarios.
  arXiv  Detail & Related papers  (2026-06-03T17:17:16Z)
• AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment [3.1849948640573245]
  AcuityBench is a benchmark for evaluating whether language models identify the appropriate urgency of care from user medical presentations.<n>It consists of five public datasets spanning user conversations, online forum posts, clinical vignettes, and patient portal messages.<n>It supports two complementary task formats: explicit four-way classification in a QA setting, and free-form conversational responses evaluated with a rubric-based judge.
  arXiv  Detail & Related papers  (2026-05-12T01:39:46Z)
• Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment [56.62016795093786]
  Cerebra is an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis.<n>It supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete.<n>Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation.
  arXiv  Detail & Related papers  (2026-03-23T05:46:45Z)
• Clinician input steers frontier AI models toward both accurate and harmful decisions [10.599240857217811]
  We evaluated 21 large language models (LLMs) across 8 frontier models on differential diagnosis generation and next step recommendations.<n>Expert context significantly improved correct final diagnosis inclusion across all 21 models.<n>In GPT-4o experiments, explicit clinician uncertainty signals improved diagnostic performance after adversarial context.
  arXiv  Detail & Related papers  (2026-03-14T23:47:53Z)
• LiveClin: A Live Clinical Benchmark without Leakage [50.45415584327275]
  LiveClin is a live benchmark designed for approximating real-world clinical practice.<n>We transform authentic patient cases into complex, multimodal evaluation scenarios that span the entire clinical pathway.<n>Our evaluation of 26 models on LiveClin reveals the profound difficulty of these real-world scenarios, with the top-performing model achieving a Case Accuracy of just 35.7%.
  arXiv  Detail & Related papers  (2026-02-18T03:59:46Z)
• Automated Rubrics for Reliable Evaluation of Medical Dialogue Systems [19.880569341968023]
  Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety.<n>We propose a retrieval-augmented multi-agent framework designed to automate the generation of instance-specific evaluation rubrics.
  arXiv  Detail & Related papers  (2026-01-21T16:40:41Z)
• A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice [83.11942224668127]
  Janus-Pro-CXR (1B) is a chest X-ray interpretation system based on DeepSeek Janus-Pro model.<n>Our system outperforms state-of-the-art X-ray report generation models in automated report generation.
  arXiv  Detail & Related papers  (2025-12-23T13:26:13Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine [69.08855631283829]
  We introduce Med Omni-45 Degrees, a benchmark designed to quantify safety-performance trade-offs under manipulative hint conditions.<n>It contains 1,804 reasoning-focused medical questions across six specialties and three task types, including 500 from MedMCQA.<n>Results show a consistent safety-performance trade-off, with no model surpassing the diagonal.
  arXiv  Detail & Related papers  (2025-08-22T08:38:16Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.