SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
Open paper
Benchmark
Model
Rank
Results
spatial-reasoning-on-6-dof-spatialbench
SpaceLLaVA
–
Total: 28.2
Position-rel: 32.4
Position-abs: 30.5
…
spatial-reasoning-on-6-dof-spatialbench
SpaceMantis
–
Total: 28.9
Position-rel: 33.6
Position-abs: 29.2
…
Rank counts only results with a code link.