How Prompt Style Affects AI Accuracy and Speed in Competitive Programming

An exploratory study of GPT-5.5 on three International Olympiad in Informatics accuracy tasks and two NP-hard speed tasks found no single prompt style was best across nine styles tested, with the strongest prompt depending on task type and on whether results were summarized by mean or median. The authors, posting as arXiv:2610.30223v1, reported that many mean-score differences came from a few outlier runs, and that against human IOI contestants working under different conditions the AI exceeded the average contestant on one task but fell short on the other two. The study extends prompt comparison from accuracy to runtime speed and argues prompt style should be matched to the objective rather than treated as universal.

arXiv:2610.30223v1 Announce Type: new Abstract: Large language models are increasingly used in competitive programming, and their outputs are sensitive to how a prompt is phrased. Prior work has compared prompt strategies for accuracy on competitive programming, but not for runtime speed, and has not situated the results against human performance. In an exploratory study of one prompt in each of nine styles on GPT-5.5 across three accuracy tasks from the International Olympiad in Informatics IOI and two NP-hard speed tasks, we found that no single prompt was best: the strongest prompt depended on the task type and on whether results were summarized by the mean or the median, suggesting that, at least for these tasks, prompt style should be matched to the objective rather than treated as universal. Many differences in mean scores came from a few outlier runs, showing that evaluating prompting by a single metric can obscure how much its effectiveness varies. Compared descriptively with human IOI contestants, who worked under different conditions, the AI was neither strictly better nor strictly worse, exceeding the average contestant on one task but falling short on the other two. By extending prompt comparison from accuracy to runtime speed and grounding it against human performance, this study gives a broader picture of how prompt style affects competitive programming performance.