@article{beyondbenchcontaminationresistantevaluat, title = {BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models}, author = {Gaurav Srivastava and Aafiya Hussain and Zhenyu Bi and Swastik Roy and Priya Pitre and Meng Lu and Morteza Ziyadi and Xuan Wang}, year = {2025}, eprint = {2509.24210}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.24210}, }