@article{beyondclassificationaccuracyneuralmedben, title = {Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks}, author = {Miao Jing and Mengting Jia and Junling Lin and Zhongxia Shen and Huan Gao and Mingkun Xu and Shangyang Li}, year = {2025}, eprint = {2509.22258}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.22258}, }