Humans are Still Better than ChatGPT: Case of the IEEEXtreme Competition

TL;DR

This study compares human and ChatGPT performance on IEEExtreme programming challenges, revealing that humans still outperform ChatGPT in problem-solving accuracy across multiple programming languages.

Contribution

The paper provides empirical evidence that humans outperform ChatGPT in certain programming tasks, challenging assumptions about AI's dominance in problem-solving.

Findings

Humans scored significantly higher than ChatGPT on IEEExtreme problems.

ChatGPT's average score was 3.9 to 5.8 times lower than human scores.

Humans maintain a competitive edge in programming problem-solving.

Abstract

Since the release of ChatGPT, numerous studies have highlighted the remarkable performance of ChatGPT, which often rivals or even surpasses human capabilities in various tasks and domains. However, this paper presents a contrasting perspective by demonstrating an instance where human performance excels in typical tasks suited for ChatGPT, specifically in the domain of computer programming. We utilize the IEEExtreme Challenge competition as a benchmark, a prestigious, annual international programming contest encompassing a wide range of problems with different complexities. To conduct a thorough evaluation, we selected and executed a diverse set of 102 challenges, drawn from five distinct IEEExtreme editions, using three major programming languages: Python, Java, and C++. Our empirical analysis provides evidence that contrary to popular belief, human programmers maintain a competitive edge over ChatGPT in certain aspects of problem-solving within the programming context. In fact, we found that the average score obtained by ChatGPT on the set of IEEExtreme programming problems is 3.9 to 5.8 times lower than the average human score, depending on the programming language. This paper elaborates on these findings, offering critical insights into the limitations and potential areas of improvement for AI-based language models like ChatGPT.