@inproceedings{ghahroodi-etal-2026-meena,
title = "{MEENA} ({P}ersian{MMMU}): Multimodal-Multilingual Educational Exams for N-level Assessment",
author = "Ghahroodi, Omid and
Hemmat, Arshia and
Nouri, Marzia and
Hosseini, Seyed Mohammad Hadi and
Dastgheib, Doratossadat and
Sanian, Mohammad Vali and
Sahebi, Alireza and
Zohrabi, Reihaneh and
Rohban, Mohammad Hossein and
Asgari, Ehsaneddin and
Baghshah, Mahdieh Soleymani",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.340/",
pages = "6457--6491",
ISBN = "979-8-89176-386-9",
abstract = "Recent advancements in large vision-language models (VLMs) have primarily focused on English, with limited attention given to other languages. To address this gap, we introduce MEENA (also known as PersianMMMU), the first dataset designed to evaluate Persian VLMs across scientific, reasoning, and human-level understanding tasks. Our dataset comprises approximately 7,500 Persian and 3,000 English questions, covering a wide range of topics such as reasoning, mathematics, physics, diagrams, charts, and Persian art and literature. Key features of MEENA include: (1) diverse subject coverage spanning various educational levels, from primary to upper secondary school, (2) rich metadata, including difficulty levels and descriptive answers, (3) original Persian data that preserves cultural nuances, (4) a bilingual structure to assess cross-linguistic performance, and (5) a series of diverse experiments assessing various capabilities, including overall performance, the model{'}s ability to attend to images, and its tendency to generate hallucinations. We hope this benchmark contributes to enhancing VLM capabilities beyond English."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghahroodi-etal-2026-meena">
<titleInfo>
<title>MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omid</namePart>
<namePart type="family">Ghahroodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arshia</namePart>
<namePart type="family">Hemmat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzia</namePart>
<namePart type="family">Nouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Mohammad</namePart>
<namePart type="given">Hadi</namePart>
<namePart type="family">Hosseini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doratossadat</namePart>
<namePart type="family">Dastgheib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Vali</namePart>
<namePart type="family">Sanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alireza</namePart>
<namePart type="family">Sahebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reihaneh</namePart>
<namePart type="family">Zohrabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Rohban</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsaneddin</namePart>
<namePart type="family">Asgari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahdieh</namePart>
<namePart type="given">Soleymani</namePart>
<namePart type="family">Baghshah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Recent advancements in large vision-language models (VLMs) have primarily focused on English, with limited attention given to other languages. To address this gap, we introduce MEENA (also known as PersianMMMU), the first dataset designed to evaluate Persian VLMs across scientific, reasoning, and human-level understanding tasks. Our dataset comprises approximately 7,500 Persian and 3,000 English questions, covering a wide range of topics such as reasoning, mathematics, physics, diagrams, charts, and Persian art and literature. Key features of MEENA include: (1) diverse subject coverage spanning various educational levels, from primary to upper secondary school, (2) rich metadata, including difficulty levels and descriptive answers, (3) original Persian data that preserves cultural nuances, (4) a bilingual structure to assess cross-linguistic performance, and (5) a series of diverse experiments assessing various capabilities, including overall performance, the model’s ability to attend to images, and its tendency to generate hallucinations. We hope this benchmark contributes to enhancing VLM capabilities beyond English.</abstract>
<identifier type="citekey">ghahroodi-etal-2026-meena</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.340/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>6457</start>
<end>6491</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment
%A Ghahroodi, Omid
%A Hemmat, Arshia
%A Nouri, Marzia
%A Hosseini, Seyed Mohammad Hadi
%A Dastgheib, Doratossadat
%A Sanian, Mohammad Vali
%A Sahebi, Alireza
%A Zohrabi, Reihaneh
%A Rohban, Mohammad Hossein
%A Asgari, Ehsaneddin
%A Baghshah, Mahdieh Soleymani
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F ghahroodi-etal-2026-meena
%X Recent advancements in large vision-language models (VLMs) have primarily focused on English, with limited attention given to other languages. To address this gap, we introduce MEENA (also known as PersianMMMU), the first dataset designed to evaluate Persian VLMs across scientific, reasoning, and human-level understanding tasks. Our dataset comprises approximately 7,500 Persian and 3,000 English questions, covering a wide range of topics such as reasoning, mathematics, physics, diagrams, charts, and Persian art and literature. Key features of MEENA include: (1) diverse subject coverage spanning various educational levels, from primary to upper secondary school, (2) rich metadata, including difficulty levels and descriptive answers, (3) original Persian data that preserves cultural nuances, (4) a bilingual structure to assess cross-linguistic performance, and (5) a series of diverse experiments assessing various capabilities, including overall performance, the model’s ability to attend to images, and its tendency to generate hallucinations. We hope this benchmark contributes to enhancing VLM capabilities beyond English.
%U https://aclanthology.org/2026.findings-eacl.340/
%P 6457-6491
Markdown (Informal)
[MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment](https://aclanthology.org/2026.findings-eacl.340/) (Ghahroodi et al., Findings 2026)
ACL
- Omid Ghahroodi, Arshia Hemmat, Marzia Nouri, Seyed Mohammad Hadi Hosseini, Doratossadat Dastgheib, Mohammad Vali Sanian, Alireza Sahebi, Reihaneh Zohrabi, Mohammad Hossein Rohban, Ehsaneddin Asgari, and Mahdieh Soleymani Baghshah. 2026. MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment. In Findings of the Association for Computational Linguistics: EACL 2026, pages 6457–6491, Rabat, Morocco. Association for Computational Linguistics.