MedRepBench: A Comprehensive Benchmark for Medical Report Interpretation

TL;DR

MedRepBench is a new comprehensive benchmark for evaluating medical report interpretation models, focusing on structured understanding, with diverse real-world Chinese reports and multiple evaluation protocols.

Contribution

Introduces MedRepBench, a large-scale, multi-faceted benchmark for assessing vision-language models in medical report understanding, including objective and subjective evaluation methods.

Findings

VLMs improved by 6% recall using reward optimization

OCR+LLM pipeline shows layout-blindness and latency issues

Benchmark covers diverse clinical reports and evaluation protocols

Abstract

Medical report interpretation plays a crucial role in healthcare, enabling both patient-facing explanations and effective information flow across clinical systems. While recent vision-language models (VLMs) and large language models (LLMs) have demonstrated general document understanding capabilities, there remains a lack of standardized benchmarks to assess structured interpretation quality in medical reports. We introduce MedRepBench, a comprehensive benchmark built from 1,900 de-identified real-world Chinese medical reports spanning diverse departments, patient demographics, and acquisition formats. The benchmark is designed primarily to evaluate end-to-end VLMs for structured medical report understanding. To enable controlled comparisons, we also include a text-only evaluation setting using high-quality OCR outputs combined with LLMs, allowing us to estimate the upper-bound performance when character recognition errors are minimized. Our evaluation framework supports two complementary protocols: (1) an objective evaluation measuring field-level recall of structured clinical items, and (2) an automated subjective evaluation using a powerful LLM as a scoring agent to assess factuality, interpretability, and reasoning quality. Based on the objective metric, we further design a reward function and apply Group Relative Policy Optimization (GRPO) to improve a mid-scale VLM, achieving up to 6% recall gain. We also observe that the OCR+LLM pipeline, despite strong performance, suffers from layout-blindness and latency issues, motivating further progress toward robust, fully vision-based report understanding.