This task evaluates the ability of systems to understand a text and select the correct answer among several possible options. Each exercise presents a text accompanied by multiple-choice questions, where only one answer is correct. The objective is to measure automated reading comprehension in a traditional format widely used in human assessments.
Publication
Rodrigo, A. et al. 2025. Overview of PROFE at IberLEF 2025: Language Proficiency Evaluation. Procesamiento del Lenguaje Natural, 75, pp. 487-497.
Competition
Language
Spanish
NLP topic
Dataset
Year
2025
Publication link
Ranking metric
Accuracy
Task results
| System | Accuracy Sort ascending |
|---|---|
| Vicomtech_ezotova | 0.9550 |
| JFra-Team_responder | 0.9300 |
| JFra-Team_multi_agent | 0.9290 |
| The Vikings_submission4_G2 | 0.9200 |
| SINAI_zero_shot_multiple_choice | 0.9110 |
