ARCH-B: Architectural Representation, Comprehension and Hierarchy Benchmark
Multimodal models increasingly interpret visual environments, but their ability to recognize the same building across photographs, floor plans, elevations, sections, and renderings remains poorly characterized. We introduce ARCH-B, a benchmark of 354 four-choice questions across 11 cross-representational archetypes, co...
Kieran Sagar Parikh, J. L. G. del Castillo Y López
· 0 citations