TurkBench: A Benchmark for Evaluating Turkish Large Language Models
Abstract
With the recent surge in the development of large language models, the need for comprehensive and language-specific evaluation benchmarks has become critical. While significant progress has been made in evaluating English-language models, benchmarks for other languages, particularly those with unique linguistic characteristics such as Turkish, remain less developed. Our study introduces TurkBench, a comprehensive benchmark designed to assess the capabilities of generative large language models in the Turkish language. TurkBench involves 8,151 data samples across 21 distinct subtasks. These are organized under six main categories of evaluation: Knowledge, Language Understanding, Reasoning, Content Moderation, Turkish Grammar and Vocabulary, and Instruction Following. The diverse range of tasks and the culturally relevant data would provide researchers and developers with a valuable tool for evaluating their models and identifying areas for improvement. We further publish our benchmark for online submissions at https://huggingface.co/turkbench
Cite
@article{arxiv.2601.07020,
title = {TurkBench: A Benchmark for Evaluating Turkish Large Language Models},
author = {Çağrı Toraman and Ahmet Kaan Sever and Ayse Aysu Cengiz and Elif Ecem Arslan and Görkem Sevinç and Mete Mert Birdal and Yusuf Faruk Güldemir and Ali Buğra Kanburoğlu and Sezen Felekoğlu and Osman Gürlek and Sarp Kantar and Birsen Şahin Kütük and Büşra Tufan and Elif Genç and Serkan Coşkun and Gupse Ekin Demir and Muhammed Emin Arayıcı and Olgun Dursun and Onur Gungor and Susan Üsküdarlı and Abdullah Topraksoy and Esra Darıcı},
journal= {arXiv preprint arXiv:2601.07020},
year = {2026}
}
Comments
Accepted by EACL 2026 SIGTURK