List your company

Spatial Reasoning on Blink (ood)

60.7AccuracyThinking with Blueprint
53.00455.0025758.998Jan 5, 2026

Evaluation results

MethodLinks
Thinking with BlueprintModel Size=7B, Reasoning Mode=Thinking with Blueprint2026.0160.7
gpt-4oModel Size=-, Reasoning Mode=No2026.0159.2
gpt-4oModel Size=-, Reasoning Mode=Naive CoT2026.0159
Qwen2.5-VLModel Size=7B, Reasoning Mode=No2026.0156.4
gpt-5-ThinkingModel Size=-, Reasoning Mode=Naive CoT2026.0156.3
VigoRLModel Size=7B, Reasoning Mode=Thinking with Coordinates2026.0156.1
Qwen2.5-VLModel Size=7B, Reasoning Mode=Naive CoT2026.0153.8
ViLASRModel Size=7B, Reasoning Mode=Thinking with Images2026.0153.3