issai/GSM8k_Kazakh_Russian

---
dataset_info:
- config_name: kazakh
features:
- name: question
dtype: string
- name: answer_text
dtype: string
splits:
- name: test
num_bytes: 1141656
num_examples: 1319
download_size: 521064
dataset_size: 1141656
- config_name: russian
features:
- name: question
dtype: string
- name: answer_text
dtype: string
splits:
- name: test
num_bytes: 1210590
num_examples: 1319
download_size: 574904
dataset_size: 1210590
configs:
- config_name: kazakh
data_files:
- split: test
path: kazakh/test-*
- config_name: russian
data_files:
- split: test
path: russian/test-*
license: mit
task_categories:
- text-generation
language:
- kk
size_categories:
- 1K<n<10K
---

## Dataset Summary

These are the machine-translated Kazakh and Russian versions of the [GSM8K (Grade School Math 8K)](https://huggingface.co/datasets/openai/gsm8k) dataset (test set).

This dataset is used to test the mathematical reasoning of large language models in the Kazakh language. Specifically, GSM8K focuses on high-quality grade school math word problems that require multi-step reasoning to solve. Kazakh and Russian versions serve as a benchmark for evaluating how well models can perform mathematical reasoning and follow logical chains of thought when prompted in Kazakh or Russian.