# Why o1's Planning Accuracy Collapses 78% When Spatial Reasoning Joins Verbal - slug: why-o1s-planning-accuracy-collapses-78-when-spatial-reasoning-joins-verbal - date: 2026-03-23 - category: Artificial Intelligence When a new paper asks whether large language models can actually plan a trip — not just describe one — the answer turns out to be nearly zero. ItinBench, a benchmark developed by researchers at the University of Virginia, tests LLMs on itinerary planning across two cognitive dimensions simultane... ---