LLM_Benchmark

简介

Mongolian LLM Benchmark A multi-task evaluation benchmark for large language models on the Mongolian language (Cyrillic script). Six task configurations cover open-ended QA, multiple-choice, code generation, instruction following, math, and culturally grounded knowledge. Configurations Config Rows Format Key fields culture 150 Multiple choice (A–D) prompt, options, answer, source_url math 150 Numeric / short answer prompt, answer, accepted_formats, rationale… See the full description on the dataset page: https://huggingface.co/datasets/Bokhbat/LLM_Benchmark.