5arXiv cs.CL (Computation and Language)·
MedRealMM: Real-world multimodal benchmark for Chinese online medical consultation
Researchers introduce MedRealMM, a benchmark of 5,620 real-world multimodal patient-doctor interaction cases drawn from a nationwide Chinese internet hospital, spanning 64 clinical departments. The benchmark uses a Multimodal Clinical Challenge Point (MCCP) framework to identify clinically demanding moments and evaluates 19 general-purpose and medical-specialized LLMs. Key findings show that frontier models still fall below online physician performance, particularly on safety-sensitive error avoidance, and that image information is critical for reliable clinical performance. The dataset will be publicly released on Hugging Face.
Related guides (4)
Related events (8)
The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare
Hugging Face has launched the Open Medical-LLM Leaderboard, a public benchmark for evaluating large language models on healthcare and medical tasks. The leaderboard aggregates performance across multiple medical question-answering datasets to enable standardized comparison of open-weight models in clinical and biomedical domains. This initiative aims to accelerate progress in medical AI by providing transparent, reproducible evaluation infrastructure.
OpenMedReason: Large-scale multimodal medical reasoning corpus with 450K instances for clinical VLM training
Researchers introduce OpenMedReason, a 450K-instance open multimodal medical reasoning corpus with reasoning traces derived from human-authored biomedical literature rather than synthetic chains of thought. The dataset covers diverse medical imaging modalities and is paired with OpenMedReason-Bench, a held-out benchmark evaluating LVLMs on perception, medical knowledge, and rationale axes. Training with OpenMedReason yields a 20% average VQA accuracy improvement over base models and achieves performance within 4.2% of leading comparable-scale medical VLMs. Both the dataset and code are publicly released.
ClinEnv: Interactive Multi-Stage Long-Horizon EHR Benchmark for Clinical Agent Evaluation
ClinEnv is a new interactive benchmark that evaluates LLMs as attending physicians over real inpatient admissions using a Longitudinal Inpatient Simulation paradigm. Each case is decomposed into sequential decision stages where models must query four specialized agents before committing to medications, procedures, and diagnoses. Across seven evaluated models, the best achieves only 0.31 decision F1, with a sharp gap between diagnosis recovery (0.51 F1) and management actions (0.17 F1). The benchmark uniquely measures information-acquisition process quality alongside outcome quality, exposing a gap invisible to static or outcome-only evaluations.
MedRLM: Recursive multimodal agent framework for long-context clinical decision support
MedRLM is a proposed framework for clinical decision support that uses recursive multi-agent reasoning over heterogeneous patient data including EHRs, medical images, physiological sensor streams, and clinical guidelines. Rather than single-step prompting, it decomposes patient cases into an inspectable external environment coordinated by specialized agents, with a Clinical Evidence Graph Memory and sensor-triggered deeper reasoning. The paper outlines an evaluation design using public and credentialed clinical datasets spanning radiology, ECG, ICU time series, and referral outcomes. The work targets a gap between static medical QA benchmarks and real-world longitudinal clinical workflows.
MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings
The paper introduces a pipeline for converting unstructured clinical text into HL7 FHIR R4 bundles, enabling evaluation of LLMs in realistic electronic health record settings. Applied to the MedCaseReasoning dataset, it produces MedCase-Structured, a synthetic benchmark achieving valid FHIR generation for 82.5% of cases. Key finding: LLMs show consistently lower diagnostic accuracy on structured FHIR inputs compared to plain text, underscoring the gap between standard benchmarks and real-world clinical deployment conditions.
M³Exam: Benchmark for Multimodal Memory in Realistic User-Agent Interactions
Researchers introduce M³Exam, a query-centric multimodal conversational memory benchmark designed to evaluate language agents on realistic user-agent interactions, including cross-modal grounding and implicit information inference. Existing benchmarks are critiqued for assuming sparse visuals and human-human interaction formats. The paper also proposes M³Proctor, a companion memory method that detects query modality bias and retrieves raw visual sources on demand, achieving 13% accuracy improvement while reducing index-construction time and retrieved tokens by over 70%.
Clinically grounded privacy evaluation framework reveals high memorization risk in medical LMs
Researchers introduce a tiered adversarial framework for evaluating privacy leakage in medical language models, moving beyond simple training-text recovery to realistic clinical threat models. Applied to an LM pretrained on 378k clinical notes, the framework finds that routine encounter metadata (name, DOB, provider, visit date) elicits high verbatim memorization and sensitive-diagnosis recovery (AUROC 0.91 for abortion, 0.81 for HIV). The study also finds that exact-match memorization overstates disclosure risk because 36% of memorized tokens reflect templated documentation. The work provides a practical contextual privacy evaluation methodology for medical LMs trained on longitudinal patient data.
MedMisBench: LLMs show fragile epistemic resilience under misleading medical context
Researchers introduce MedMisBench, a benchmark of 10,932 medical questions paired with 48,889 misleading context injections, to measure whether LLMs maintain correct medical judgment under adversarial pressure. Across 11 model configurations, mean accuracy drops from 71.1% to 38.0% when misleading context is injected, with authority-framed falsehoods achieving 69.5% attack success. A 14-member international clinical panel flagged serious potential harm in 38.2% of reviewed cases. The work argues that existing medical benchmarks measure knowledge but not robustness to manipulation, exposing a structural gap in LLM safety evaluation for healthcare.