Large Language Models (LLMs) have demonstrated remarkable capabilities in modern medicine, yet their application in Traditional Chinese Medicine (TCM) remains severely limited by the absence of standardized benchmarks and the scarcity of high-quality training data. To address these challenges, we introduce TCM-Eval, the first dynamic and extensible benchmark for TCM, meticulously curated from national medical licensing examinations and validated by TCM experts. Furthermore, we construct a large-scale training corpus and propose Self-Iterative Chain-of-Thought Enhancement (SI-CoTE) to autonomously enrich question-answer pairs with validated reasoning chains through rejection sampling, establishing a virtuous cycle of data and model co-evolution. Using this enriched training data, we develop ZhiMingTang (ZMT), a state-of-the-art LLM specifically designed for TCM, which significantly exceeds the passing threshold for human practitioners. To encourage future research and development, we release a public leaderboard, fostering community engagement and continuous improvement.
@article{arxiv.2511.07148,
title = {TCM-Eval: An Expert-Level Dynamic and Extensible Benchmark for Traditional Chinese Medicine},
author = {Zihao Cheng and Yuheng Lu and Huaiqian Ye and Zeming Liu and Minqi Wang and Jingjing Liu and Zihan Li and Wei Fan and Yuanfang Guo and Ruiji Fu and Shifeng She and Gang Wang and Yunhong Wang},
journal= {arXiv preprint arXiv:2511.07148},
year = {2025}
}