Evaluating the Performance of Large Language Models for Spanish Language in Undergraduate Admissions Exams

TL;DR

This study assesses GPT-3.5 and BARD's abilities on Mexican undergraduate admissions exams, showing both models perform well with GPT-3.5 generally outperforming BARD in most subjects.

Contribution

First comprehensive evaluation of large language models' performance on real-world university entrance exams in Spanish.

Findings

GPT-3.5 scored higher overall than BARD.

Both models exceeded minimum acceptance scores.

GPT-3.5 excelled in Mathematics and Physics.

Abstract

This study evaluates the performance of large language models, specifically GPT-3.5 and BARD (supported by Gemini Pro model), in undergraduate admissions exams proposed by the National Polytechnic Institute in Mexico. The exams cover Engineering/Mathematical and Physical Sciences, Biological and Medical Sciences, and Social and Administrative Sciences. Both models demonstrated proficiency, exceeding the minimum acceptance scores for respective academic programs to up to 75% for some academic programs. GPT-3.5 outperformed BARD in Mathematics and Physics, while BARD performed better in History and questions related to factual information. Overall, GPT-3.5 marginally surpassed BARD with scores of 60.94% and 60.42%, respectively.