@article{turtlebenchevaluatingtoplanguagemodels, title = {TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzles}, author = {Qingchen Yu and Shichao Song and Ke Fang and Yunfeng Shi and Zifan Zheng and Hanyu Wang and Simin Niu and Zhiyu Li}, year = {2024}, eprint = {2410.05262}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.05262v1}, }