Evaluating GPT-4's Vision Capabilities on Brazilian University Admission Exams

TL;DR

This paper evaluates GPT-4's ability to handle complex Brazilian university entrance exam questions involving both text and visuals, highlighting strengths in multidisciplinary questions and challenges in mathematical reasoning.

Contribution

It introduces a comprehensive multimodal evaluation framework for language models on real-world exams, focusing on Portuguese tests and visual comprehension.

Findings

GPT-4 excels in multidisciplinary questions

Text captions outperform direct image use

Mathematical questions remain challenging

Abstract

Recent advancements in language models have showcased human-comparable performance in academic entrance exams. However, existing studies often overlook questions that require the integration of visual comprehension, thus compromising the full spectrum and complexity inherent in real-world scenarios. To address this gap, we present a comprehensive framework to evaluate language models on entrance exams, which incorporates both textual and visual elements. We evaluate the two most recent editions of Exame Nacional do Ensino M\'edio (ENEM), the main standardized entrance examination adopted by Brazilian universities. Our study not only reaffirms the capabilities of GPT-4 as the state of the art for handling complex multidisciplinary questions, but also pioneers in offering a realistic assessment of multimodal language models on Portuguese examinations. One of the highlights is that text captions transcribing visual content outperform the direct use of images, suggesting that the vision model has room for improvement. Yet, despite improvements afforded by images or captions, mathematical questions remain a challenge for these state-of-the-art models. The code and data used on experiments are available at https://github.com/piresramon/gpt-4-enem.