List your company

Spatial Reasoning on SAT ood (test)

79.7AccuracyThinking with Blueprint
50.37257.98665.673.214Jan 5, 2026

Evaluation results

MethodLinks
Thinking with BlueprintModel Size=7B, Reasoning Mode=Thinking with Blueprint2026.0179.7
RobixModel Size=32B, Reasoning Mode=Naive CoT2026.0179.6
gpt-5-ThinkingModel Size=-, Reasoning Mode=Naive CoT2026.0172.7
MirageModel Size=7B, Reasoning Mode=Thinking with (Latent) Images2026.0172
RobixModel Size=7B, Reasoning Mode=Naive CoT2026.0171.1
gpt-4oModel Size=-, Reasoning Mode=Naive CoT2026.0163.3
Qwen2.5-VLModel Size=7B, Reasoning Mode=No2026.0163.3
ViLASRModel Size=7B, Reasoning Mode=Thinking with Images2026.0160.7
VigoRLModel Size=7B, Reasoning Mode=Thinking with Coordinates2026.0157.3
Qwen2.5-VLModel Size=7B, Reasoning Mode=Naive CoT2026.0154.7
gpt-4oModel Size=-, Reasoning Mode=No2026.0151.5