@article{multichallengearealisticmultiturn, title = {MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs}, author = {Ved Sirdeshmukh and Kaustubh Deshpande and Johannes Mols and Lifeng Jin and Ed-Yeremai Cardona and Dean Lee and Jeremy Kritz and Willow Primack and Summer Yue and Chen Xing}, year = {2025}, eprint = {2501.17399}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.17399v1}, }