Skip to content
Microsoft Research· Yunfei Ge, Anbang Liu, Qineng Wang, Johnalbert Garnica, Zihan Wang, Reuben Tan, Jianfeng Gao, Ruohan Zhang, Yining Hong, Jiajun Wu, Manling Li·· 2026-08-13

MindTopo reveals VLMs’ spatial reasoning abilities

MindTopo reveals VLMs’ spatial reasoning abilities

AI summary

A path, a fence, a knot. MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning.

Selection record

Not admittedSum of both 76 < twice the threshold 120

Source tier
Official, first-hand; this tier's threshold is 60
Pre-filter
passed:微软研究发布VLM拓扑推理基准MindTopo

A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.

Source: Microsoft Research · microsoft.com