_version_ 1866918252810076160
author Mang, Qiuyang
Chai, Wenhao
Li, Zhifei
Mao, Huanzhi
Zhou, Shang
Du, Alexander
Li, Hanchen
Liu, Shu
Chen, Edwin
Wang, Yichuan
Chu, Xieting
Cheng, Zerui
Xu, Yuan
Xia, Tian
Wang, Zirui
Shi, Tianneng
Yao, Jianzhu
Zhao, Yilong
Zhang, Qizheng
Ruan, Charlie
Shen, Zeyu
Liu, Kaiyuan
He, Runyuan
Xing, Dong
Li, Zerui
Zeng, Zirong
Jiang, Yige
Cheng, Lufeng
Zhao, Ziyi
Sun, Youran
Zheng, Wesley
Zhang, Meiyuwang
Ji, Ruyi
Tu, Xuechang
Zheng, Zihan
Chen, Zexing
Zhou, Kangyang
Wang, Zhaozi
Chen, Jingbang
Korolova, Aleksandra
Henderson, Peter
Viswanath, Pramod
Ganesh, Vijay
Xie, Saining
Liu, Zhuang
Song, Dawn
Min, Sewon
Stoica, Ion
Gonzalez, Joseph E.
Shang, Jingbo
Cheung, Alvin
author_facet Mang, Qiuyang
Chai, Wenhao
Li, Zhifei
Mao, Huanzhi
Zhou, Shang
Du, Alexander
Li, Hanchen
Liu, Shu
Chen, Edwin
Wang, Yichuan
Chu, Xieting
Cheng, Zerui
Xu, Yuan
Xia, Tian
Wang, Zirui
Shi, Tianneng
Yao, Jianzhu
Zhao, Yilong
Zhang, Qizheng
Ruan, Charlie
Shen, Zeyu
Liu, Kaiyuan
He, Runyuan
Xing, Dong
Li, Zerui
Zeng, Zirong
Jiang, Yige
Cheng, Lufeng
Zhao, Ziyi
Sun, Youran
Zheng, Wesley
Zhang, Meiyuwang
Ji, Ruyi
Tu, Xuechang
Zheng, Zihan
Chen, Zexing
Zhou, Kangyang
Wang, Zhaozi
Chen, Jingbang
Korolova, Aleksandra
Henderson, Peter
Viswanath, Pramod
Ganesh, Vijay
Xie, Saining
Liu, Zhuang
Song, Dawn
Min, Sewon
Stoica, Ion
Gonzalez, Joseph E.
Shang, Jingbo
Cheung, Alvin
contents We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competitive programming participants and problem setters. Unlike existing benchmarks that focus on tasks with known optimal solutions, FrontierCS targets problems where the optimal solution is unknown, but the quality of a solution can be objectively evaluated. Models solve these tasks by implementing executable programs rather than outputting a direct answer. FrontierCS includes algorithmic problems, which are often NP-hard variants of competitive programming problems with objective partial scoring, and research problems with the same property. For each problem we provide an expert reference solution and an automatic evaluator. Combining open-ended design, measurable progress, and expert curation, FrontierCS provides a benchmark at the frontier of computer-science difficulty. Empirically, we find that frontier reasoning models still lag far behind human experts on both the algorithmic and research tracks, that increasing reasoning budgets alone does not close this gap, and that models often over-optimize for generating merely workable code instead of discovering high-quality algorithms and system designs.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15699
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FrontierCS: Evolving Challenges for Evolving Intelligence
Mang, Qiuyang
Chai, Wenhao
Li, Zhifei
Mao, Huanzhi
Zhou, Shang
Du, Alexander
Li, Hanchen
Liu, Shu
Chen, Edwin
Wang, Yichuan
Chu, Xieting
Cheng, Zerui
Xu, Yuan
Xia, Tian
Wang, Zirui
Shi, Tianneng
Yao, Jianzhu
Zhao, Yilong
Zhang, Qizheng
Ruan, Charlie
Shen, Zeyu
Liu, Kaiyuan
He, Runyuan
Xing, Dong
Li, Zerui
Zeng, Zirong
Jiang, Yige
Cheng, Lufeng
Zhao, Ziyi
Sun, Youran
Zheng, Wesley
Zhang, Meiyuwang
Ji, Ruyi
Tu, Xuechang
Zheng, Zihan
Chen, Zexing
Zhou, Kangyang
Wang, Zhaozi
Chen, Jingbang
Korolova, Aleksandra
Henderson, Peter
Viswanath, Pramod
Ganesh, Vijay
Xie, Saining
Liu, Zhuang
Song, Dawn
Min, Sewon
Stoica, Ion
Gonzalez, Joseph E.
Shang, Jingbo
Cheung, Alvin
Machine Learning
Software Engineering
We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competitive programming participants and problem setters. Unlike existing benchmarks that focus on tasks with known optimal solutions, FrontierCS targets problems where the optimal solution is unknown, but the quality of a solution can be objectively evaluated. Models solve these tasks by implementing executable programs rather than outputting a direct answer. FrontierCS includes algorithmic problems, which are often NP-hard variants of competitive programming problems with objective partial scoring, and research problems with the same property. For each problem we provide an expert reference solution and an automatic evaluator. Combining open-ended design, measurable progress, and expert curation, FrontierCS provides a benchmark at the frontier of computer-science difficulty. Empirically, we find that frontier reasoning models still lag far behind human experts on both the algorithmic and research tracks, that increasing reasoning budgets alone does not close this gap, and that models often over-optimize for generating merely workable code instead of discovering high-quality algorithms and system designs.
title FrontierCS: Evolving Challenges for Evolving Intelligence
topic Machine Learning
Software Engineering
url https://arxiv.org/abs/2512.15699