MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models

TL;DR

MedBench is a comprehensive benchmarking system designed to evaluate Chinese medical large language models across multiple specialties, ensuring reliable, standardized, and unbiased assessment for real-world medical applications.

Contribution

This work introduces MedBench, the largest evaluation dataset and a fully automated, dynamic evaluation infrastructure specifically for Chinese medical LLMs, addressing current evaluation gaps.

Findings

Evaluation results align with medical professionals' perspectives.

MedBench provides unbiased and reproducible assessments.

The system covers 43 clinical specialties with over 300,000 questions.

Abstract

Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, especially in the Chinese context, remains to be established. In this work, we introduce "MedBench", a comprehensive, standardized, and reliable benchmarking system for Chinese medical LLM. First, MedBench assembles the currently largest evaluation dataset (300,901 questions) to cover 43 clinical specialties and performs multi-facet evaluation on medical LLM. Second, MedBench provides a standardized and fully automatic cloud-based evaluation infrastructure, with physical separations for question and ground truth. Third, MedBench implements dynamic evaluation mechanisms to prevent shortcut learning and answer remembering. Applying MedBench to popular general and medical LLMs, we observe unbiased, reproducible evaluation results largely aligning with medical professionals' perspectives. This study establishes a significant foundation for preparing the practical applications of Chinese medical LLMs. MedBench is publicly accessible at https://medbench.opencompass.org.cn.