MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning

• URL: http://arxiv.org/abs/2503.07459v2
• Date: Thu, 20 Mar 2025 01:30:56 GMT
• Title: MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
• Authors: Xiangru Tang, Daniel Shao, Jiwoong Sohn, Jiapeng Chen, Jiayi Zhang, Jinyu Xiang, Fang Wu, Yilun Zhao, Chenglin Wu, Wenqi Shi, Arman Cohan, Mark Gerstein,
• Abstract summary: Large Language Models (LLMs) have shown impressive performance on existing medical question-answering benchmarks.<n>We present MedAgentsBench, a benchmark that focuses on challenging medical questions requiring multi-step clinical reasoning, diagnosis formulation, and treatment planning-scenarios.
• Score: 34.93995619867384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have shown impressive performance on existing medical question-answering benchmarks. This high performance makes it increasingly difficult to meaningfully evaluate and differentiate advanced methods. We present MedAgentsBench, a benchmark that focuses on challenging medical questions requiring multi-step clinical reasoning, diagnosis formulation, and treatment planning-scenarios where current models still struggle despite their strong performance on standard tests. Drawing from seven established medical datasets, our benchmark addresses three key limitations in existing evaluations: (1) the prevalence of straightforward questions where even base models achieve high performance, (2) inconsistent sampling and evaluation protocols across studies, and (3) lack of systematic analysis of the interplay between performance, cost, and inference time. Through experiments with various base models and reasoning methods, we demonstrate that the latest thinking models, DeepSeek R1 and OpenAI o3, exhibit exceptional performance in complex medical reasoning tasks. Additionally, advanced search-based agent methods offer promising performance-to-cost ratios compared to traditional approaches. Our analysis reveals substantial performance gaps between model families on complex questions and identifies optimal model selections for different computational constraints. Our benchmark and evaluation framework are publicly available at https://github.com/gersteinlab/medagents-benchmark.

Related papers

• Evaluating Vision Language Models (VLMs) for Radiology: A Comprehensive Analysis [4.803310914375717]
  This study evaluates three vision-language foundation models (RAD-DINO, CheXagent, and BiomedCLIP) on their ability to capture fine-grained imaging features for radiology tasks. The models were assessed across classification, segmentation, and regression tasks for pneumothorax and cardiomegaly on chest radiographs.
  arXiv  Detail & Related papers  (2025-04-22T17:20:34Z)
• Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases [48.87360916431396]
  We introduce MedR-Bench, a benchmarking dataset of 1,453 structured patient cases, annotated with reasoning references.<n>We propose a framework encompassing three critical examination recommendation, diagnostic decision-making, and treatment planning, simulating the entire patient care journey.<n>Using this benchmark, we evaluate five state-of-the-art reasoning LLMs, including DeepSeek-R1, OpenAI-o3-mini, and Gemini-2.0-Flash Thinking, etc.
  arXiv  Detail & Related papers  (2025-03-06T18:35:39Z)
• LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models [18.6994780408699]
  Large Language Models (LLMs) face significant challenges in medical question answering. We propose a novel approach incorporating similar case generation within a multi-agent medical question-answering system. Our method capitalizes on the model's inherent medical knowledge and reasoning capabilities, eliminating the need for additional training data.
  arXiv  Detail & Related papers  (2024-12-31T19:55:45Z)
• Superhuman performance of a large language model on the reasoning tasks of a physician [10.043418251604624]
  Performance of large language models (LLMs) on medical tasks has traditionally been evaluated using multiple choice question benchmarks.<n>We evaluate OpenAI's o1-preview model, a model developed to increase run-time via chain of thought processes prior to generating a response.
  arXiv  Detail & Related papers  (2024-12-14T14:46:18Z)
• SemiHVision: Enhancing Medical Multimodal Models with a Semi-Human Annotated Dataset and Fine-Tuned Instruction Generation [13.672776832197918]
  Multimodal large language models (MLLMs) have made significant strides, yet they face challenges in the medical domain due to limited specialized knowledge. We seek to address this gap at various stages of the end-to-end learning pipeline, including data collection, model fine-tuning, and evaluation.
  arXiv  Detail & Related papers  (2024-10-19T02:35:35Z)
• How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation [6.547981908229007]
  We show how architectural and framework biases combine to influence model performance.<n>Experiments show imputation performance variations of up to 20% based on preprocessing and implementation choices.<n>We identify critical gaps between current deep imputation methods and medical requirements.
  arXiv  Detail & Related papers  (2024-07-11T12:33:28Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models [56.63218531256961]
  We introduce GenBench, a benchmarking suite specifically tailored for evaluating the efficacy of Genomic Foundation Models. GenBench offers a modular and expandable framework that encapsulates a variety of state-of-the-art methodologies. We provide a nuanced analysis of the interplay between model architecture and dataset characteristics on task-specific performance.
  arXiv  Detail & Related papers  (2024-06-01T08:01:05Z)
• Rethinking Model Prototyping through the MedMNIST+ Dataset Collection [0.11999555634662634]
  This work presents a benchmark for the MedMNIST+ database to diversify the evaluation landscape. We conduct a thorough analysis of common convolutional neural networks (CNNs) and Transformer-based architectures, for medical image classification. Our findings suggest that computationally efficient training schemes and modern foundation models hold promise in bridging the gap between expensive end-to-end training and more resource-refined approaches.
  arXiv  Detail & Related papers  (2024-04-24T10:19:25Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study [60.56194508762205]
  We reproduce, compare, and analyze state-of-the-art automated medical coding machine learning models. We show that several models underperform due to weak configurations, poorly sampled train-test splits, and insufficient evaluation. We present the first comprehensive results on the newly released MIMIC-IV dataset using the reproduced models.
  arXiv  Detail & Related papers  (2023-04-21T11:54:44Z)
• Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model [71.80319052891817]
  We present a relation-driven semi-supervised framework for medical image classification. It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
  arXiv  Detail & Related papers  (2020-05-15T06:57:54Z)

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.