paper-with-me

Papers

ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code

2025-06-02 · Tianyu Hua, Harper Hua, Violet Xiang, Benjamin Klieger, Sang T. Truong, Weixin Liang, Fan-Yun Sun, Nick Haber

Large language models (LLMs) have shown promise in transforming machine learning research, yet their capability to faithfully implement novel ideas from recent research papers-ideas unseen during pretraining-remains unclear. We introduce ResearchCodeBench, a benchmark of 212 coding challenges that evaluates LLMs' ability to translate cutting-edge ML contributions from top 2024-2025 research papers into executable code. We assessed 30+ proprietary and open-source LLMs, finding that even the best models correctly implement less than 40% of the code. We find Gemini-2.5-Pro-Preview to perform best at 37.3% success rate, with O3 (High) and O4-mini (High) following behind at 32.3% and 30.8% respectively. We present empirical findings on performance comparison, contamination, and error patterns. By providing a rigorous and community-driven evaluation platform, ResearchCodeBench enables continuous understanding and advancement of LLM-driven innovation in research code generation.

📄 PDF Abstract BibTeX arXiv:2506.02314

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingCode Generation

Similar Papers 제목 키워드 기반

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

2024-06-13 · Zhao Xu, Fan Liu, Hao liu

Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outpu…

BenchmarkingGPU

Benchmarking Energy Efficiency of Large Language Models Using vLLM

2025-09-10 · K. Pronk, Q. Zhao arxiv

The prevalence of Large Language Models (LLMs) is having an growing impact on the climate due to the substantial energy required for their deployment and use. To create awareness for developers who are implementing LLMs …

REVERE: Reflective Evolving Research Engineer for Scientific Workflows

2026-03-21 · Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan arxiv

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or…

Continual Learning

mlr3proba: An R Package for Machine Learning in Survival Analysis

2020-08-18 · Raphael Sonabend, Franz J. Király, Andreas Bender, Bernd Bischl 외

As machine learning has become increasingly popular over the last few decades, so too has the number of machine learning interfaces for implementing these models. Whilst many R libraries exist for machine learning, very …

BenchmarkingBIG-bench Machine LearningSurvival Analysis

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

2021-03-23 · Meng Liu, Youzhi Luo, Limei Wang, Yaochen Xie 외

Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning. In the research community, implementing and benchmarking various advanced task…

BenchmarkingDeep LearningGraph GenerationSelf-Supervised Learning