AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construction
This provides a domain-specific benchmark for evaluating AI agents in the AEC industry, which is incremental as it applies existing benchmarking concepts to a new application area.
The paper introduces AEC-Bench, a multimodal benchmark for evaluating agentic systems on real-world tasks in the Architecture, Engineering, and Construction domain, covering tasks like drawing understanding and project coordination, and it identifies tools and harness design techniques that improve performance across foundation models.
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.