EduBench: A Portuguese Benchmark for Open-Ended Discursive Question Answering

Pedro Henrique Paiola, Luís Gabriel Damiati Mendes, Bruno de Oliveira Monchelato, André da Fonseca Schuck, Gabriel Lino Garcia, Douglas Rodrigues, Helena de Medeiros Caseli, João Paulo Papa


Abstract
Evaluating open-ended text generation in large language models remains challenging, particularly for non-English languages. We introduce EduBench, a comprehensive Portuguese-language benchmark comprising 3,149 discursive questions from Brazilian university entrance examinations spanning 2015–2025. Unlike multiple-choice or extractive QA benchmarks, EduBench requires extended, argumentative responses across diverse domains, including Humanities, Exact and Natural Sciences, and Languages. Each question includes expert-curated reference answers from official sources, rich metadata, and automated image descriptions to support text-only evaluation. We establish baseline results using nine contemporary models, ranging from 4B-parameter SLMs to state-of-the-art reasoning-capable LLMs, and evaluate them using complementary metrics (BLEU, BERTScore, G-Eval). Our results reveal substantial metric disagreement and highlight the complexity of assessing discursive generation, with models achieving 54–71% alignment with expert answers. We release EduBench publicly to support research on Portuguese NLP and open-ended generation evaluation.
Anthology ID:
2026.lrec-1.360
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
4587–4596
Language:
External URL:
https://lrec.elra.info/lrec2026-main-360
DOI:
10.63317/4nocig8f36r9
Bibkey:
Cite (ACL):
Pedro Henrique Paiola, Luís Gabriel Damiati Mendes, Bruno de Oliveira Monchelato, André da Fonseca Schuck, Gabriel Lino Garcia, Douglas Rodrigues, Helena de Medeiros Caseli, and João Paulo Papa. 2026. EduBench: A Portuguese Benchmark for Open-Ended Discursive Question Answering. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4587–4596, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
EduBench: A Portuguese Benchmark for Open-Ended Discursive Question Answering (Paiola et al., LREC 2026)
Copy Citation: