@inproceedings{han-etal-2026-mubench,
title = "{M}u{B}ench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages",
author = "Han, Wenhan and
Zhang, Yifan and
Chen, Zhixun and
Binbinliu and
Pechenizkiy, Mykola and
Fang, Meng and
Zheng, Yin",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.794/",
pages = "16163--16192",
ISBN = "979-8-89176-395-1",
abstract = "Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation datasets are limited and lack cross-lingual alignment, leaving assessments of multilingual capabilities fragmented in both language and skill coverage. To address this, we introduce MuBench, a benchmark covering 61 languages with 3.9M samples and evaluating a broad range of capabilities. We evaluate several state-of-the-art multilingual LLMs and find notable gaps between claimed and actual language coverage, particularly a persistent performance disparity between English and low-resource languages. Leveraging MuBench{'}s alignment, we propose Multilingual Consistency (MLC) as a complementary metric to accuracy for analyzing performance bottlenecks and guiding model improvement. MuBench provides flexible evaluation formats, including mixed-language testing. Experimental results show that increasing model size does not improve its ability to handle mixed-language contexts. We recruited human experts to evaluate translation quality and cultural sensitivity for 34k samples across 17 languages, and combined these assessments with an LLM-as-a-Judge approach to ensure overall data quality in low resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2026-mubench">
<titleInfo>
<title>MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhan</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhixun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Binbinliu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mykola</namePart>
<namePart type="family">Pechenizkiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation datasets are limited and lack cross-lingual alignment, leaving assessments of multilingual capabilities fragmented in both language and skill coverage. To address this, we introduce MuBench, a benchmark covering 61 languages with 3.9M samples and evaluating a broad range of capabilities. We evaluate several state-of-the-art multilingual LLMs and find notable gaps between claimed and actual language coverage, particularly a persistent performance disparity between English and low-resource languages. Leveraging MuBench’s alignment, we propose Multilingual Consistency (MLC) as a complementary metric to accuracy for analyzing performance bottlenecks and guiding model improvement. MuBench provides flexible evaluation formats, including mixed-language testing. Experimental results show that increasing model size does not improve its ability to handle mixed-language contexts. We recruited human experts to evaluate translation quality and cultural sensitivity for 34k samples across 17 languages, and combined these assessments with an LLM-as-a-Judge approach to ensure overall data quality in low resource languages.</abstract>
<identifier type="citekey">han-etal-2026-mubench</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.794/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>16163</start>
<end>16192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages
%A Han, Wenhan
%A Zhang, Yifan
%A Chen, Zhixun
%A Pechenizkiy, Mykola
%A Fang, Meng
%A Zheng, Yin
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%A Binbinliu
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F han-etal-2026-mubench
%X Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation datasets are limited and lack cross-lingual alignment, leaving assessments of multilingual capabilities fragmented in both language and skill coverage. To address this, we introduce MuBench, a benchmark covering 61 languages with 3.9M samples and evaluating a broad range of capabilities. We evaluate several state-of-the-art multilingual LLMs and find notable gaps between claimed and actual language coverage, particularly a persistent performance disparity between English and low-resource languages. Leveraging MuBench’s alignment, we propose Multilingual Consistency (MLC) as a complementary metric to accuracy for analyzing performance bottlenecks and guiding model improvement. MuBench provides flexible evaluation formats, including mixed-language testing. Experimental results show that increasing model size does not improve its ability to handle mixed-language contexts. We recruited human experts to evaluate translation quality and cultural sensitivity for 34k samples across 17 languages, and combined these assessments with an LLM-as-a-Judge approach to ensure overall data quality in low resource languages.
%U https://aclanthology.org/2026.findings-acl.794/
%P 16163-16192
Markdown (Informal)
[MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages](https://aclanthology.org/2026.findings-acl.794/) (Han et al., Findings 2026)
ACL
- Wenhan Han, Yifan Zhang, Zhixun Chen, Binbinliu, Mykola Pechenizkiy, Meng Fang, and Yin Zheng. 2026. MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages. In Findings of the Association for Computational Linguistics: ACL 2026, pages 16163–16192, San Diego, California, United States. Association for Computational Linguistics.