MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
This work addresses the need for better evaluation in medical AI by providing a benchmark for complex reasoning, which is incremental as it builds on existing datasets and methods.
The authors tackled the problem of evaluating advanced methods in medical question-answering by introducing MedAgentsBench, a benchmark focusing on complex medical reasoning tasks, and found that models like DeepSeek R1 and OpenAI o3 show exceptional performance, with analysis revealing performance gaps and optimal model selections for computational constraints.
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.