Hossain, Md SifatTabassum, AnikaArefin, Md FahimZaman, Tarannum Shaila2025-04-012025-04-012025-02-04https://doi.org/10.48550/arXiv.2502.04355http://hdl.handle.net/11603/37936LLM4Code 2025: The Second International Workshop on Large Language Models for CodeThe rapid advancement of large language models has opened new avenues for automating complex problem-solving tasks such as algorithmic coding and competitive programming. This paper introduces a novel evaluation technique, LLM-ProS, to assess the performance of state-of-the-art LLMs on International Collegiate Programming Contest (ICPC) problems. Using a curated dataset of 166 World Finals problems from 2011 to 2024, we benchmark the models' reasoning, accuracy, and efficiency. We evaluate the five models-GPT-4o, Mistral Large, Llama-3.1-405B, and the o1 family, consisting of o1-mini and o1-preview, across critical metrics like correctness, resource utilization, and response calibration. Our results reveal significant differences in the models' abilities to generalize, adapt, and solve novel problems. We also investigated the impact of training methodologies, dataset contamination, and chain-of-thought reasoning on model performance. The findings provide new insights into optimizing LLMs for algorithmic tasks, highlighting both strengths and limitations of current models.8 pagesen-US?2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.ICPCChain-of-Thought ReasoningArtificial IntelligenceCompetitive ProgrammingComputer ScienceComputation and LanguageLarge Language ModelsPerformance EvaluationText