Review
Jul 2026
SPARC-Rad: A Multimodal Benchmark Dataset and Evaluation Pipeline for Spatial and Anatomical Reasoning in Radiology Vision-Language Models
The SPARC-Rad Benchmark is developed, a manually curated multimodal benchmark dataset and evaluation pipeline for assessing whether VLMs can provide reasoning for radiologic anatomy as a spatial system, supporting future model development, failure-mode analysis, and pre-deployment assessment.
Satvik Tripathi, M. E. Şeker, K. Quevada et al.
· 0 citations