Saved in:
Bibliographic Details
Main Authors: Abdelatty, Manar, Nouh, Maryam, Rosenstein, Jacob K., Reda, Sherief
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.14756
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917019609202688
author Abdelatty, Manar
Nouh, Maryam
Rosenstein, Jacob K.
Reda, Sherief
author_facet Abdelatty, Manar
Nouh, Maryam
Rosenstein, Jacob K.
Reda, Sherief
contents Large Language Models (LLMs) are increasingly used to automate hardware design tasks, including the generation of Verilog code. While early benchmarks focus primarily on functional correctness, efficient hardware design demands additional optimization for synthesis metrics such as area, delay, and power. Existing benchmarks fall short in evaluating these aspects comprehensively: they often lack optimized baselines or testbenches for verification. To address these gaps, we present Pluto, a benchmark and evaluation framework designed to assess the efficiency of LLM-generated Verilog designs. Pluto presents a comprehensive evaluation set of 114 problems with self-checking testbenches and multiple Pareto-optimal reference implementations. Experimental results show that state-of-the-art LLMs can achieve high functional correctness, reaching 78.3\% at pass@1, but their synthesis efficiency still lags behind expert-crafted implementations, with area efficiency of 63.8\%, delay efficiency of 65.9\%, and power efficiency of 64.0\% at eff@1. This highlights the need for efficiency-aware evaluation frameworks such as Pluto to drive progress in hardware-focused LLM research.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14756
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pluto: A Benchmark for Evaluating Efficiency of LLM-generated Hardware Code
Abdelatty, Manar
Nouh, Maryam
Rosenstein, Jacob K.
Reda, Sherief
Computation and Language
Large Language Models (LLMs) are increasingly used to automate hardware design tasks, including the generation of Verilog code. While early benchmarks focus primarily on functional correctness, efficient hardware design demands additional optimization for synthesis metrics such as area, delay, and power. Existing benchmarks fall short in evaluating these aspects comprehensively: they often lack optimized baselines or testbenches for verification. To address these gaps, we present Pluto, a benchmark and evaluation framework designed to assess the efficiency of LLM-generated Verilog designs. Pluto presents a comprehensive evaluation set of 114 problems with self-checking testbenches and multiple Pareto-optimal reference implementations. Experimental results show that state-of-the-art LLMs can achieve high functional correctness, reaching 78.3\% at pass@1, but their synthesis efficiency still lags behind expert-crafted implementations, with area efficiency of 63.8\%, delay efficiency of 65.9\%, and power efficiency of 64.0\% at eff@1. This highlights the need for efficiency-aware evaluation frameworks such as Pluto to drive progress in hardware-focused LLM research.
title Pluto: A Benchmark for Evaluating Efficiency of LLM-generated Hardware Code
topic Computation and Language
url https://arxiv.org/abs/2510.14756