List your company

Visual Reasoning on SAT

76AccuracyQwen3-VL-32B
8.056825.695943.33560.9741Jun 17, 2026

Evaluation results

MethodLinks
Qwen3-VL-32B3-run average=true2026.0676
GPT-53-run average=true2026.0673.3
Qwen3-VL-8B3-run average=true2026.0654
Visual-OPSD3-run average=true, Latency (s)=10.02026.0654
ThinkMorph3-run average=true, Latency (s)=142.82026.0652.67
InternVL3.5-38B3-run average=true2026.0649.33
Visual-OPSD-Noise3-run average=true, Latency (s)=14.92026.0648
Text-only SFT3-run average=true, Latency (s)=28.52026.0646.63
InternVL3.5-8B3-run average=true2026.0645.33
BAGEL-7B3-run average=true2026.0644.67
GPT-4o3-run average=true2026.0628
Janus-Pro-7B3-run average=true2026.0622
Chameleon-7B3-run average=true2026.0610.67