Saved in:
Bibliographic Details
Main Authors: Mankodiya, Harsh, Gallik, Chase, Galanos, Theodoros, Mulyar, Andriy
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.29199
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911556432822272
author Mankodiya, Harsh
Gallik, Chase
Galanos, Theodoros
Mulyar, Andriy
author_facet Mankodiya, Harsh
Gallik, Chase
Galanos, Theodoros
Mulyar, Andriy
contents The AEC-Bench is a multimodal benchmark for evaluating agentic systems on real-world tasks in the Architecture, Engineering, and Construction (AEC) domain. The benchmark covers tasks requiring drawing understanding, cross-sheet reasoning, and construction project-level coordination. This report describes the benchmark motivation, dataset taxonomy, evaluation protocol, and baseline results across several domain-specific foundation model harnesses. We use AEC-Bench to identify consistent tools and harness design techniques that uniformly improve performance across foundation models in their own base harnesses, such as Claude Code and Codex. We openly release our benchmark dataset, agent harness, and evaluation code for full replicability at https://github.com/nomic-ai/aec-bench under an Apache 2 license.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29199
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construction
Mankodiya, Harsh
Gallik, Chase
Galanos, Theodoros
Mulyar, Andriy
Artificial Intelligence
The AEC-Bench is a multimodal benchmark for evaluating agentic systems on real-world tasks in the Architecture, Engineering, and Construction (AEC) domain. The benchmark covers tasks requiring drawing understanding, cross-sheet reasoning, and construction project-level coordination. This report describes the benchmark motivation, dataset taxonomy, evaluation protocol, and baseline results across several domain-specific foundation model harnesses. We use AEC-Bench to identify consistent tools and harness design techniques that uniformly improve performance across foundation models in their own base harnesses, such as Claude Code and Codex. We openly release our benchmark dataset, agent harness, and evaluation code for full replicability at https://github.com/nomic-ai/aec-bench under an Apache 2 license.
title AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construction
topic Artificial Intelligence
url https://arxiv.org/abs/2603.29199