Evaluating ChatGPT-4 Vision on Brazil's National Undergraduate Computer Science Exam

TL;DR

This study evaluates ChatGPT-4 Vision's performance on Brazil's 2021 National Undergraduate Computer Science Exam, demonstrating its strengths in visual question handling and highlighting the importance of question quality and human oversight.

Contribution

First large-scale assessment of ChatGPT-4 Vision on a national exam, revealing its capabilities and limitations in academic evaluation contexts.

Findings

ChatGPT-4 Vision outperformed average students, ranking in the top 10 percentile.

The model excelled in visual questions but struggled with interpretation and reasoning.

Some exam questions were poorly constructed, affecting evaluation accuracy.

Abstract

The recent integration of visual capabilities into Large Language Models (LLMs) has the potential to play a pivotal role in science and technology education, where visual elements such as diagrams, charts, and tables are commonly used to improve the learning experience. This study investigates the performance of ChatGPT-4 Vision, OpenAI's most advanced visual model at the time the study was conducted, on the Bachelor in Computer Science section of Brazil's 2021 National Undergraduate Exam (ENADE). By presenting the model with the exam's open and multiple-choice questions in their original image format and allowing for reassessment in response to differing answer keys, we were able to evaluate the model's reasoning and self-reflecting capabilities in a large-scale academic assessment involving textual and visual content. ChatGPT-4 Vision significantly outperformed the average exam participant, positioning itself within the top 10 best score percentile. While it excelled in questions that incorporated visual elements, it also encountered challenges with question interpretation, logical reasoning, and visual acuity. The involvement of an independent expert panel to review cases of disagreement between the model and the answer key revealed some poorly constructed questions containing vague or ambiguous statements, calling attention to the critical need for improved question design in future exams. Our findings suggest that while ChatGPT-4 Vision shows promise in multimodal academic evaluations, human oversight remains crucial for verifying the model's accuracy and ensuring the fairness of high-stakes educational exams. The paper's research materials are publicly available at https://github.com/nabormendonca/gpt-4v-enade-cs-2021.