issai/MMLU-Pro_Kazakh_Russian
收藏Hugging Face2026-02-18 更新2026-04-05 收录
下载链接：
https://hf-mirror.com/datasets/issai/MMLU-Pro_Kazakh_Russian
下载链接
链接失效反馈官方服务：
资源简介：
---
dataset_info:
- config_name: kazakh
features:
- name: question_id
dtype: string
- name: question
dtype: string
- name: options
list: string
- name: answer_index
dtype: int32
- name: category
dtype: string
- name: src
dtype: string
splits:
- name: test
num_bytes: 13729535
num_examples: 12032
download_size: 5474637
dataset_size: 13729535
- config_name: russian
features:
- name: question_id
dtype: int64
- name: question
dtype: string
- name: options
list: string
- name: answer_index
dtype: int64
- name: category
dtype: string
- name: src
dtype: string
splits:
- name: test
num_bytes: 14552889
num_examples: 12032
download_size: 5912337
dataset_size: 14552889
configs:
- config_name: kazakh
data_files:
- split: test
path: kazakh/test-*
- config_name: russian
data_files:
- split: test
path: russian/test-*
task_categories:
- question-answering
language:
- kk
size_categories:
- 10K<n<100K
license: mit
---
## Dataset Summary
These are the machine-translated Kazakh and Russian versions of the [MMLU-Pro (Massive Multitask Language Understanding Pro)](https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro) dataset (test set).
These datasets are used to test the world knowledge and problem-solving capabilities of large language models across a vast range of subjects in the Kazakh and Russian languages. As an enhanced version of the original MMLU, it serves as a more rigorous benchmark for evaluating how well models understand complex academic and professional topics when prompted in Kazakh, featuring more options per question and more challenging reasoning tasks.
提供机构：
issai
