@inproceedings{tavares-etal-2026-pheb,
title = "{PHEB}: An {E}uropean {P}ortuguese High School-Level {LLM} Benchmark",
author = "Tavares, Diogo C. and
Ferreira, Rafael and
Simpl{\'i}cio, Afonso and
Vinagre, Gon{\c{c}}alo and
Condez, Ana Carolina and
Calvo, In{\^e}s and
Vieira, In{\^e}s and
Semedo, David and
Magalhaes, Joao",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.367/",
doi = "10.63317/2o3fvueefvwj",
pages = "4673--4683",
abstract = "We present PHEB, a comprehensive benchmark designed to evaluate Large Language Models (LLMs) on real high school level national exams in European Portuguese. The goal is to promote the development of NLP tools and provide a reliable resource for benchmarking multilingual and educational capabilities of LLMs. Covering over 3,500 questions spanning 18 years (2006{--}2023) across six core subjects, the benchmark compiles high-quality questions from Portuguese National Exams, written and thoroughly curated by professors to ensure topic diversity, linguistic accuracy, and alignment with national curricula. PHEB spans a wide range of subjects, including Mathematics, Portuguese Language and Literature, History, Geography, Biology/Geology, and Philosophy. Questions incorporate both multiple-choice and long-form answers to assess factual knowledge, reasoning capabilities, and language understanding. We comprehensively benchmark state-of-the-art LLMs, shedding light on key challenges such as models' knowledge, language coverage, answer format biases and robustness to machine translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tavares-etal-2026-pheb">
<titleInfo>
<title>PHEB: An European Portuguese High School-Level LLM Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diogo</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Tavares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afonso</namePart>
<namePart type="family">Simplício</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gonçalo</namePart>
<namePart type="family">Vinagre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">Carolina</namePart>
<namePart type="family">Condez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inês</namePart>
<namePart type="family">Calvo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inês</namePart>
<namePart type="family">Vieira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Semedo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joao</namePart>
<namePart type="family">Magalhaes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present PHEB, a comprehensive benchmark designed to evaluate Large Language Models (LLMs) on real high school level national exams in European Portuguese. The goal is to promote the development of NLP tools and provide a reliable resource for benchmarking multilingual and educational capabilities of LLMs. Covering over 3,500 questions spanning 18 years (2006–2023) across six core subjects, the benchmark compiles high-quality questions from Portuguese National Exams, written and thoroughly curated by professors to ensure topic diversity, linguistic accuracy, and alignment with national curricula. PHEB spans a wide range of subjects, including Mathematics, Portuguese Language and Literature, History, Geography, Biology/Geology, and Philosophy. Questions incorporate both multiple-choice and long-form answers to assess factual knowledge, reasoning capabilities, and language understanding. We comprehensively benchmark state-of-the-art LLMs, shedding light on key challenges such as models’ knowledge, language coverage, answer format biases and robustness to machine translation.</abstract>
<identifier type="citekey">tavares-etal-2026-pheb</identifier>
<identifier type="doi">10.63317/2o3fvueefvwj</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.367/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4673</start>
<end>4683</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PHEB: An European Portuguese High School-Level LLM Benchmark
%A Tavares, Diogo C.
%A Ferreira, Rafael
%A Simplício, Afonso
%A Vinagre, Gonçalo
%A Condez, Ana Carolina
%A Calvo, Inês
%A Vieira, Inês
%A Semedo, David
%A Magalhaes, Joao
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F tavares-etal-2026-pheb
%X We present PHEB, a comprehensive benchmark designed to evaluate Large Language Models (LLMs) on real high school level national exams in European Portuguese. The goal is to promote the development of NLP tools and provide a reliable resource for benchmarking multilingual and educational capabilities of LLMs. Covering over 3,500 questions spanning 18 years (2006–2023) across six core subjects, the benchmark compiles high-quality questions from Portuguese National Exams, written and thoroughly curated by professors to ensure topic diversity, linguistic accuracy, and alignment with national curricula. PHEB spans a wide range of subjects, including Mathematics, Portuguese Language and Literature, History, Geography, Biology/Geology, and Philosophy. Questions incorporate both multiple-choice and long-form answers to assess factual knowledge, reasoning capabilities, and language understanding. We comprehensively benchmark state-of-the-art LLMs, shedding light on key challenges such as models’ knowledge, language coverage, answer format biases and robustness to machine translation.
%R 10.63317/2o3fvueefvwj
%U https://aclanthology.org/2026.lrec-1.367/
%U https://doi.org/10.63317/2o3fvueefvwj
%P 4673-4683
Markdown (Informal)
[PHEB: An European Portuguese High School-Level LLM Benchmark](https://aclanthology.org/2026.lrec-1.367/) (Tavares et al., LREC 2026)
ACL
- Diogo C. Tavares, Rafael Ferreira, Afonso Simplício, Gonçalo Vinagre, Ana Carolina Condez, Inês Calvo, Inês Vieira, David Semedo, and Joao Magalhaes. 2026. PHEB: An European Portuguese High School-Level LLM Benchmark. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4673–4683, Palma de Mallorca, Spain. ELRA Language Resource Association.