paper-with-me

Papers

OJBench: A Competition Level Code Benchmark For Large Language Models

2025-06-19 · Zhexu Wang, Yiping Liu, Yejie Wang, Wenyang He, Bofei Gao, Muxi Diao, Yanxu Chen, Kelin Fu, Flood Sung, Zhilin Yang, Tianyu Liu, Weiran Xu

Recent advancements in large language models (LLMs) have demonstrated significant progress in math and code reasoning capabilities. However, existing code benchmark are limited in their ability to evaluate the full spectrum of these capabilities, particularly at the competitive level. To bridge this gap, we introduce OJBench, a novel and challenging benchmark designed to assess the competitive-level code reasoning abilities of LLMs. OJBench comprises 232 programming competition problems from NOI and ICPC, providing a more rigorous test of models' reasoning skills. We conducted a comprehensive evaluation using OJBench on 37 models, including both closed-source and open-source models, reasoning-oriented and non-reasoning-oriented models. Our results indicate that even state-of-the-art reasoning-oriented models, such as o4-mini and Gemini-2.5-pro-exp, struggle with highly challenging competition-level problems. This highlights the significant challenges that models face in competitive-level code reasoning.

📄 PDF Abstract BibTeX arXiv:2506.16395

Code (1)

he-ren/ojbench 공식 구현

Tasks

Math

Similar Papers 제목 키워드 기반

Enhancing Project-Specific Code Completion by Inferring Internal API Information

2025-07-28 · Le Deng, Xiaoxue Ren, Chao Ni, Ming Liang 외 arxiv

Project-specific code completion is a critical task that leverages context from a project to generate accurate code. State-of-the-art methods use retrieval-augmented generation (RAG) with large language models (LLMs) and…

Code Completion

Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation

2023-05-18 · Xin-Ye Li, Jiang-Tian Xue, Zheng Xie, Ming Li

Code generation aims to automatically generate source code from high-level task specifications, which can significantly increase productivity of software engineering. Recently, approaches based on large language models (…

Code Generation

CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings

2025-01-02 · Shanghaoran Quan, Jiaxi Yang, Bowen Yu, Bo Zheng 외

With the increasing code reasoning capabilities of existing large language models (LLMs) and breakthroughs in reasoning models like OpenAI o1 and o3, there is a growing need to develop more challenging and comprehensive …

BenchmarkingCode Generation

Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasks

2024-12-17 · Hao Wang, Boyi Liu, Yufeng Zhang, Jie Chen

Competition-level code generation tasks pose significant challenges for current state-of-the-art large language models (LLMs). For example, on the LiveCodeBench-Hard dataset, models such as O1-Mini and O1-Preview achieve…

Code Generation

Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems

2025-06-07 · Yuhan Cao, Zian Chen, Kun Quan, Ziliang Zhang 외

Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, capable of tackling complex tasks during inference. However, the extent to which LLMs can be utilized for code checking or debugg…

Code Generationvalid