# A Novel Evaluation Benchmark for Medical LLMs: Illuminating Safety and Effectiveness in Clinical Domains

arXiv: https://arxiv.org/abs/2507.23486 · HTML: https://mlsanity.com/paper/2507.23486/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Builds on (most cited first, 17 of 17)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [Towards Accurate Differential Diagnosis with Large Language Models](https://mlsanity.com/paper/2312.00164/) (2023)
- [Towards Conversational Diagnostic AI](https://mlsanity.com/paper/2401.05654/) (2024)
- [SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models](https://mlsanity.com/paper/2410.18927/) (2024)
- [MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks](https://mlsanity.com/paper/2505.23802/) (2025)
- [MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models](https://mlsanity.com/paper/2407.10990/) (2024)
- [LLM-Mini-CEX: Automatic Evaluation of Large Language Model for Diagnostic Conversation](https://mlsanity.com/paper/2308.07635/) (2023)
- [Towards Automatic Evaluation for LLMs' Clinical Capabilities: Metric, Data, and Algorithm](https://mlsanity.com/paper/2403.16446/) (2024)
- [An Automatic Evaluation Framework for Multi-turn Medical Consultations Capabilities of Large Language Models](https://mlsanity.com/paper/2309.02077/) (2023)
- [MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters](https://mlsanity.com/paper/2502.03298/) (2025)
- [aiXamine: Simplified LLM Safety and Security](https://mlsanity.com/paper/2504.14985/) (2025)
- [Clean & Clear: Feasibility of Safe LLM Clinical Guidance](https://mlsanity.com/paper/2503.20953/) (2025)

## Built on by (most cited first, 28 of 28)

- [Health-SCORE: Towards Scalable Rubrics for Improving Health-LLMs](https://mlsanity.com/paper/2601.18706/) (2026)
- [Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction](https://mlsanity.com/paper/2604.04325/) (2026)
- [Measuring Epistemic Resilience of LLMs Under Misleading Medical Context](https://mlsanity.com/paper/2606.12291/) (2026)
- [Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health](https://mlsanity.com/paper/2511.17554/) (2025)
- [MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety](https://mlsanity.com/paper/2606.02630/) (2026)
- [Calibrated Triage, Not Autonomy: Confidence Estimation for Medical Vision-Language Models](https://mlsanity.com/paper/2606.15910/) (2026)
- [AlphaEval: Evaluating Agents in Production](https://mlsanity.com/paper/2604.12162/) (2026)
- [MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills](https://mlsanity.com/paper/2604.20441/) (2026)
- [AI Safety Training Can be Clinically Harmful](https://mlsanity.com/paper/2604.23445/) (2026)
- [Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control](https://mlsanity.com/paper/2604.26577/) (2026)
- [MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters](https://mlsanity.com/paper/2607.08257/) (2026)
- [ClinConsensus: A Physician-Calibrated Benchmark for Evaluating Clinical Rubric Coverage in Chinese Medical LLMs](https://mlsanity.com/paper/2603.02097/) (2026)
- [DepthCharge: A Domain-Agnostic Framework for Measuring Depth-Dependent Knowledge in Large Language Models](https://mlsanity.com/paper/2603.23514/) (2026)
- [IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models](https://mlsanity.com/paper/2604.07709/) (2026)
- [Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment in Clinical LLMs](https://mlsanity.com/paper/2604.20791/) (2026)
- [MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence](https://mlsanity.com/paper/2605.07919/) (2026)
- [GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration](https://mlsanity.com/paper/2605.24636/) (2026)
- [Deployment-Centered Evaluation: Predicting Query-Level Rejection Risk in a Clinical LLM System](https://mlsanity.com/paper/2606.12702/) (2026)
- [Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance](https://mlsanity.com/paper/2606.18613/) (2026)
- [Latent Confidence Alignment for LLM Self-Assessment](https://mlsanity.com/paper/2606.21937/) (2026)
- [When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries](https://mlsanity.com/paper/2606.28332/) (2026)
- [CardioBench: A Real-World Data Benchmark for Evaluating Large Language Models in Clinically Authentic Cardiovascular Care Scenarios](https://mlsanity.com/paper/2607.25186/) (2026)
- [EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses](https://mlsanity.com/paper/2607.28788/) (2026)
- [RESPClinBench: Benchmarking Multimodal Clinical Decision-Making and Longitudinal Disease Management in Respiratory Specialty Care](https://mlsanity.com/paper/2608.04514/) (2026)
- [Coupled Graph--Policy Distillation for Personalized Medication Safety in Older Adults with Multimorbidity](https://mlsanity.com/paper/2608.09443/) (2026)
- [SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support](https://mlsanity.com/paper/2608.22802/) (2026)
- [Beyond Semantic Accuracy: Consequence-Aware Evaluation for Safety-Critical Language Understanding](https://mlsanity.com/paper/2608.24621/) (2026)
- [A collective capability boundary in frontier large language models on guideline-conformant and case-specific oncology decision-making](https://mlsanity.com/paper/2608.28592/) (2026)

## Abstract (arXiv)

Large language models (LLMs) hold promise in clinical decision support but face major challenges in safety evaluation and effectiveness validation. We developed the Clinical Safety-Effectiveness Dual-Track Benchmark (CSEDB), a multidimensional framework built on clinical expert consensus, encompassing 30 criteria covering critical areas like critical illness recognition, guideline adherence, and medication safety, with weighted consequence measures. Thirty-two specialist physicians developed and reviewed 2,069 open-ended Q&A items aligned with these criteria, spanning 26 clinical departments to simulate real-world scenarios. Benchmark testing of six LLMs revealed moderate overall performance (average total score 57.2%, safety 54.7%, effectiveness 62.3%), with a significant 13.3% performance drop in high-risk scenarios (p < 0.0001). Domain-specific medical LLMs showed consistent performance advantages over general-purpose models, with relatively higher top scores in safety (0.912) and effectiveness (0.861). The findings of this study not only provide a standardized metric for evaluating the clinical application of medical LLMs, facilitating comparative analyses, risk exposure identification, and improvement directions across different scenarios, but also hold the potential to promote safer and more effective deployment of large language models in healthcare environments.