QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture

ICLR 2026 Conference Submission14083 Authors

Keywords: benchmark, computer architecture, dataset, language models, question-answering

TL;DR: We present QuArch, the first question-answering benchmark for the field of computer architecture, and find state-of-the-art models struggle with skills that require higher-order thinking.

Abstract: The field of computer architecture, which bridges high-level software abstractions and low-level hardware implementations, remains absent from current large language model (LLM) evaluations. To this end, we present QuArch (pronounced 'quark'), the first benchmark designed to facilitate the development and evaluation of LLM knowledge and reasoning capabilities specifically in computer architecture. QuArch provides a comprehensive collection of 2,671 expert-validated question-answer (QA) pairs covering various aspects of computer architecture, including processor design, memory systems, and interconnection networks. Our evaluation reveals that while frontier models possess domain-specific knowledge, they struggle with skills that require higher-order thinking in computer architecture. Frontier model accuracies vary widely (from 34% to 72%) on these advanced questions, highlighting persistent gaps in architectural reasoning across analysis, design, and implementation QAs. By holistically assessing fundamental skills, QuArch provides a foundation for building and measuring LLM capabilities that can accelerate innovation in computing systems.

Primary Area: datasets and benchmarks

Submission Number: 14083