Saved in:
Bibliographic Details
Main Authors: Xuan, Weihao, Yang, Rui, Qi, Heli, Zeng, Qingcheng, Xiao, Yunze, Feng, Aosong, Liu, Dairui, Xing, Yun, Wang, Junjue, Gao, Fan, Lu, Jinghui, Jiang, Yuang, Li, Huitao, Li, Xin, Yu, Kunyu, Dong, Ruihai, Gu, Shangding, Li, Yuekang, Xie, Xiaofei, Juefei-Xu, Felix, Khomh, Foutse, Yoshie, Osamu, Chen, Qingyu, Teodoro, Douglas, Liu, Nan, Goebel, Randy, Ma, Lei, Marrese-Taylor, Edison, Lu, Shijian, Iwasawa, Yusuke, Matsuo, Yutaka, Li, Irene
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.10497
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910968391401472
author Xuan, Weihao
Yang, Rui
Qi, Heli
Zeng, Qingcheng
Xiao, Yunze
Feng, Aosong
Liu, Dairui
Xing, Yun
Wang, Junjue
Gao, Fan
Lu, Jinghui
Jiang, Yuang
Li, Huitao
Li, Xin
Yu, Kunyu
Dong, Ruihai
Gu, Shangding
Li, Yuekang
Xie, Xiaofei
Juefei-Xu, Felix
Khomh, Foutse
Yoshie, Osamu
Chen, Qingyu
Teodoro, Douglas
Liu, Nan
Goebel, Randy
Ma, Lei
Marrese-Taylor, Edison
Lu, Shijian
Iwasawa, Yusuke
Matsuo, Yutaka
Li, Irene
author_facet Xuan, Weihao
Yang, Rui
Qi, Heli
Zeng, Qingcheng
Xiao, Yunze
Feng, Aosong
Liu, Dairui
Xing, Yun
Wang, Junjue
Gao, Fan
Lu, Jinghui
Jiang, Yuang
Li, Huitao
Li, Xin
Yu, Kunyu
Dong, Ruihai
Gu, Shangding
Li, Yuekang
Xie, Xiaofei
Juefei-Xu, Felix
Khomh, Foutse
Yoshie, Osamu
Chen, Qingyu
Teodoro, Douglas
Liu, Nan
Goebel, Randy
Ma, Lei
Marrese-Taylor, Edison
Lu, Shijian
Iwasawa, Yusuke
Matsuo, Yutaka
Li, Irene
contents Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-linguistic reasoning abilities. This dual limitation makes it challenging to comprehensively assess LLMs' performance in the multilingual setting. To fill this gap, we introduce MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark. Each language version consists of 11,829 identical questions, enabling direct cross-linguistic comparisons. Additionally, to meet efficient evaluation needs, we provide a lite version containing 658 questions per language. To ensure the high quality of MMLU-ProX, we employ a rigorous development process that involves multiple powerful LLMs for translation, followed by expert review to ensure accurate expression, consistent terminology, and cultural relevance. Building on this, we systematically evaluate 36 state-of-the-art LLMs, including reasoning-enhanced and multilingual-optimized LLMs. The results reveal significant disparities in the multilingual capabilities of LLMs: While they perform well in high-resource languages, their performance declines markedly in low-resource languages, with gaps of up to 24.3%. Through MMLU-ProX, we aim to advance the development of more inclusive AI systems and promote equitable access to technology across global contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10497
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation
Xuan, Weihao
Yang, Rui
Qi, Heli
Zeng, Qingcheng
Xiao, Yunze
Feng, Aosong
Liu, Dairui
Xing, Yun
Wang, Junjue
Gao, Fan
Lu, Jinghui
Jiang, Yuang
Li, Huitao
Li, Xin
Yu, Kunyu
Dong, Ruihai
Gu, Shangding
Li, Yuekang
Xie, Xiaofei
Juefei-Xu, Felix
Khomh, Foutse
Yoshie, Osamu
Chen, Qingyu
Teodoro, Douglas
Liu, Nan
Goebel, Randy
Ma, Lei
Marrese-Taylor, Edison
Lu, Shijian
Iwasawa, Yusuke
Matsuo, Yutaka
Li, Irene
Computation and Language
Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-linguistic reasoning abilities. This dual limitation makes it challenging to comprehensively assess LLMs' performance in the multilingual setting. To fill this gap, we introduce MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark. Each language version consists of 11,829 identical questions, enabling direct cross-linguistic comparisons. Additionally, to meet efficient evaluation needs, we provide a lite version containing 658 questions per language. To ensure the high quality of MMLU-ProX, we employ a rigorous development process that involves multiple powerful LLMs for translation, followed by expert review to ensure accurate expression, consistent terminology, and cultural relevance. Building on this, we systematically evaluate 36 state-of-the-art LLMs, including reasoning-enhanced and multilingual-optimized LLMs. The results reveal significant disparities in the multilingual capabilities of LLMs: While they perform well in high-resource languages, their performance declines markedly in low-resource languages, with gaps of up to 24.3%. Through MMLU-ProX, we aim to advance the development of more inclusive AI systems and promote equitable access to technology across global contexts.
title MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation
topic Computation and Language
url https://arxiv.org/abs/2503.10497