List your company

Visual Spatial Reasoning on VSP

85.83AccuracyVisual-OPSD
-3.433219.740942.91566.0891Jun 17, 2026

Evaluation results

MethodLinks
Visual-OPSD3-run average=true, Latency (s)=10.02026.0685.83
ThinkMorph3-run average=true, Latency (s)=142.82026.0675.83
GPT-53-run average=true2026.0657.33
Visual-OPSD-Noise3-run average=true, Latency (s)=14.92026.0650.83
Text-only SFT3-run average=true, Latency (s)=28.52026.0649.17
Qwen3-VL-32B3-run average=true2026.0643.5
GPT-4o3-run average=true2026.0633.5
Qwen3-VL-8B3-run average=true2026.0622
InternVL3.5-38B3-run average=true2026.0620.16
InternVL3.5-8B3-run average=true2026.068.17
Chameleon-7B3-run average=true2026.060.83
BAGEL-7B3-run average=true2026.060.83
Janus-Pro-7B3-run average=true2026.060