Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiangyang, Li, Xiaopeng, Dong, Kuicai, Zhang, Quanhu, Ruan, Rongju, Dai, Xinyi, Liu, Xiaoshuang, Xu, Shengchun, Wang, Yasheng, Tang, Ruiming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912656372269056
author Li, Xiangyang
Li, Xiaopeng
Dong, Kuicai
Zhang, Quanhu
Ruan, Rongju
Dai, Xinyi
Liu, Xiaoshuang
Xu, Shengchun
Wang, Yasheng
Tang, Ruiming
author_facet Li, Xiangyang
Li, Xiaopeng
Dong, Kuicai
Zhang, Quanhu
Ruan, Rongju
Dai, Xinyi
Liu, Xiaoshuang
Xu, Shengchun
Wang, Yasheng
Tang, Ruiming
contents Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and pose no challenge to advanced LLMs. To better reflected the advanced reasoning and code generation ability, We introduce Humanity's Last Code Exam (HLCE), comprising 235 most challenging problems from the International Collegiate Programming Contest (ICPC World Finals) and the International Olympiad in Informatics (IOI) spanning 2010 - 2024. As part of HLCE, we design a harmonized online-offline sandbox that guarantees fully reproducible evaluation. Through our comprehensive evaluation, we observe that even the strongest reasoning LLMs: o4-mini(high) and Gemini-2.5 Pro, achieve pass@1 rates of only 15.9% and 11.4%, respectively. Meanwhile, we propose a novel "self-recognition" task to measure LLMs' awareness of their own capabilities. Results indicate that LLMs' self-recognition abilities are not proportionally correlated with their code generation performance. Finally, our empirical validation of test-time scaling laws reveals that current advanced LLMs have substantial room for improvement on complex programming tasks. We expect HLCE to become a milestone challenge for code generation and to catalyze advances in high-performance reasoning and human-AI collaborative programming. Our code and dataset are also public available(https://github.com/Humanity-s-Last-Code-Exam/HLCE).
format Preprint
id arxiv_https___arxiv_org_abs_2506_12713
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
Li, Xiangyang
Li, Xiaopeng
Dong, Kuicai
Zhang, Quanhu
Ruan, Rongju
Dai, Xinyi
Liu, Xiaoshuang
Xu, Shengchun
Wang, Yasheng
Tang, Ruiming
Software Engineering
Computation and Language
Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and pose no challenge to advanced LLMs. To better reflected the advanced reasoning and code generation ability, We introduce Humanity's Last Code Exam (HLCE), comprising 235 most challenging problems from the International Collegiate Programming Contest (ICPC World Finals) and the International Olympiad in Informatics (IOI) spanning 2010 - 2024. As part of HLCE, we design a harmonized online-offline sandbox that guarantees fully reproducible evaluation. Through our comprehensive evaluation, we observe that even the strongest reasoning LLMs: o4-mini(high) and Gemini-2.5 Pro, achieve pass@1 rates of only 15.9% and 11.4%, respectively. Meanwhile, we propose a novel "self-recognition" task to measure LLMs' awareness of their own capabilities. Results indicate that LLMs' self-recognition abilities are not proportionally correlated with their code generation performance. Finally, our empirical validation of test-time scaling laws reveals that current advanced LLMs have substantial room for improvement on complex programming tasks. We expect HLCE to become a milestone challenge for code generation and to catalyze advances in high-performance reasoning and human-AI collaborative programming. Our code and dataset are also public available(https://github.com/Humanity-s-Last-Code-Exam/HLCE).
title Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
topic Software Engineering
Computation and Language
url https://arxiv.org/abs/2506.12713