CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
If find this benchmark useful, please consider citing with the following BibTex entry:
@misc{leng2025crosswordbenchevaluatingreasoningcapabilities,
title={CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation},
author={Jixuan Leng… See the full description on the dataset page:
https://huggingface.co/datasets/HINT-lab/CrossWordBench.
