A small-scale Cloze-style multiple-choice benchmark for evaluating Turkish legal-domain language models. The dataset is designed to test whether models understand legal terminology, doctrinal structure, and domain-specific phrasing in Turkish law.

Dataset Format

Each example is stored as one JSON object per line (JSONL).

Schema

{ "id": "string", "sentence": "string with [MASK] placeholder", "options": ["choice1"… See the full description on the dataset page: https://huggingface.co/datasets/turkhukuk/hukukbert-cloze-benchmark.