paper-with-me

Papers

PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization

2026-05-13 · Huihao Jing, Wenbin Hu, Haochen Shi, Hanyu Yang, Sirui Zhang, Shaojin Chen, Haoran Li, Yangqiu Song arxiv

Large language models (LLMs) can often generate functionally correct code, but their ability to produce efficient implementations for performance-critical systems tasks remains limited. Existing code benchmarks mainly emphasize correctness or algorithmic problem solving, while realistic systems-level optimization is still underexplored. To address this gap, we introduce PerfCodeBench, an executable benchmark for evaluating LLMs on high-performance code optimization. The tasks require system-level implementation choices, hardware-aware optimization, and careful handling of performance bottlenecks. Each task includes executable correctness checks, a baseline implementation, and a reference optimized solution. This allows us to evaluate both correctness and runtime-oriented efficiency. Our evaluation on a broad set of state-of-the-art LLMs shows a clear gap between model-generated code and expert-optimized implementations. The gap is especially large on tasks involving parallelism and GPU operations. Current models also show weaknesses in cross-language robustness and in consistently reaching expert-level efficiency. These results suggest that performance-aware evaluation are still needed. LLMs should move beyond generating merely correct code toward producing efficient systems software. We submit the benchmark data, evaluation infrastructure, and complete logs of all LLMs-generated code at https://anonymous.4open.science/r/perfcodebench-7CDE.

📄 PDF Abstract BibTeX arXiv:2605.15222

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

2025-09-05 · Gagan Mundada, Yash Vishe, Amit Namburi, Xin Xu 외 arxiv

Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in the multimodal symbolic music domain remai…

Question Answering

Benchmarking LLMs for Mimicking Child-Caregiver Language in Interaction

2024-12-12 · Jing Liu, Abdellah Fourtassi

LLMs can generate human-like dialogues, yet their ability to simulate early child-adult interactions remains largely unexplored. In this paper, we examined how effectively LLMs can capture the distinctive features of chi…

BenchmarkingDiversity

Bench4HLS: End-to-End Evaluation of LLMs in High-Level Synthesis Code Generation

2026-01-16 · M Zafir Sadik Khan, Kimia Azar, Hadi Kamali arxiv

In last two years, large language models (LLMs) have shown strong capabilities in code generation, including hardware design at register-transfer level (RTL). While their use in high-level synthesis (HLS) remains compara…

Code Generation

Flaws in the LLM Automation Narrative

2026-06-09 · George Perrett, Javae Elliott, Jennifer Hill, Marc Scott arxiv

Large Language Models (LLMs) are increasingly described as performing at the level of human experts on knowledge economy tasks. These claims are primarily based on how LLMs perform on benchmarking tasks that measure aver…

PATENTWRITER: A Benchmarking Study for Patent Drafting with LLMs

2025-07-30 · Homaira Huda Shomee, Suman Kalyan Maity, Sourav Medya arxiv

Large language models (LLMs) have emerged as transformative approaches in several important fields. This paper aims for a paradigm shift for patent writing by leveraging LLMs to overcome the tedious patent-filing process…