BIM-Edit benchmark finds best LLM scores only 49.5% average across geometric, semantic, and topological metrics on 324 IFC editing tasks, with no model fully solving more than 3.4%.
BIM-GPT: A prompt-based virtual assistant framework for bim information retrieval.arXiv preprint arXiv:2304.09333, 2023
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Presents Ishigaki-IDS-Bench, the first benchmark for LLM-based IDS generation from BIM requirements, with baseline results showing max 65.6% Facet F1 and 33.1% content pass rate across 10 models.
A zero-shot multi-agent framework routes queries through semantic decomposition and generates Python code for precise building analytics, tested on data from over 200 commercial buildings.
citing papers explorer
-
BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling
BIM-Edit benchmark finds best LLM scores only 49.5% average across geometric, semantic, and topological metrics on 324 IFC editing tasks, with no model fully solving more than 3.4%.
-
Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
Presents Ishigaki-IDS-Bench, the first benchmark for LLM-based IDS generation from BIM requirements, with baseline results showing max 65.6% Facet F1 and 33.1% content pass rate across 10 models.
-
A Zero-Shot Multi-Agent Framework for Human-Building Interaction via Programmatic Reasoning
A zero-shot multi-agent framework routes queries through semantic decomposition and generates Python code for precise building analytics, tested on data from over 200 commercial buildings.