@article{glotocrbenchocrmodelsstillstrugglebeyond, title = {GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts}, author = {Amir Hossein Kargaran and Nafiseh Nikeghbal and Jana Diesner and François Yvon and Hinrich Schütze}, year = {2026}, eprint = {2604.12978}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.12978}, }