FarsEval-PKBETS: A new diverse benchmark for evaluating Persian large language models
Preprint
Abstract
Research on evaluating and analyzing large language models (LLMs) has been extensive for resource-rich languages such as English, yet their performance in languages such as Persian has received considerably less attention. This paper introduces FarsEval-PKBETS benchmark, a subset of FarsEval project for evaluating large language models in Persian. This benchmark consists of 4000 questions and answers in various formats, including multiple choice, short answer and descriptive responses. It covers a wide range of domains and tasks,including medicine, law, religion, Persian language, encyclopedic knowledge, human preferences, social knowledge, ethics and bias, text generation, and respecting others' rights. This bechmark incorporates linguistics, cultural, and local considerations relevant to the Persian language and Iran. To ensure the questions are challenging for current LLMs, three models -- Llama3-70B, PersianMind, and Dorna -- were evaluated using this benchmark. Their average accuracy was below 50%, meaning they provided fully correct answers to fewer than half of the questions. These results indicate that current language models are still far from being able to solve this benchmarkKeywords
All Related Versions
This publication has 18 references indexed in Scilit:
- ArmanEmo: a Persian dataset for text-based emotion detectionLanguage Resources and Evaluation, 2025
- A dataset for evaluating clinical research claims in large language modelsScientific Data, 2025
- PharmaBench: Enhancing ADMET benchmarks with large language modelsScientific Data, 2024
- Evaluating the strengths and weaknesses of large language models in answering neurophysiology questionsScientific Reports, 2024
- Gender bias and stereotypes in Large Language Models2023
- Application of ChatGPT in multilingual medical education: How does ChatGPT fare in 2023's Iranian residency entrance examinationInformatics in Medicine Unlocked, 2023
- TruthfulQA: Measuring How Models Mimic Human Falsehoods2022
- ParsiNLU: A Suite of Language Understanding Challenges for PersianTransactions of the Association for Computational Linguistics, 2021
- Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification2019
- Ex Machina2017