MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model
-
etri-vilab/MultihopSpatial
Viewer • Updated • 15.8k • 903 • 6 -
etri-vilab/MultiHopSpatial-Qwen3-VL-4B-Instruct
Image-Text-to-Text • 4B • Updated • 68 • 3 -
etri-vilab/MultiHopSpatial-Qwen3-VL-8B-Instruct
Image-Text-to-Text • 9B • Updated • 15 • 1 -
etri-vilab/MultiHopSpatial-Qwen3-VL-32B-Instruct
Image-Text-to-Text • 33B • Updated • 14 • 1