Monolingual Sindhi LLM Evaluation Dataset

This dataset contains 100 multiple-choice questions in Sindhi, developed as part of a research project investigating the performance of Large Language Models (LLMs) on monolingual and code-switched Sindhi-English inputs. The questions cover Pakistani culture, geography, and history. The dataset includes unique question identifiers, questions, answer options, correct answers, and source information. The resource is intended to support research on low-resource language processing and the evaluation of Sindhi-language large language models. The dataset includes source information to document the provenance of the questions.