List your company

Spatial Reasoning on SAT iid (val)

92.7AccuracyThinking with Blueprint
50.99661.82372.6583.477Jan 5, 2026

Evaluation results

MethodLinks
Thinking with BlueprintModel Size=7B, Reasoning Mode=Thinking with Blueprint2026.0192.7
VigoRLModel Size=7B, Reasoning Mode=Thinking with Coordinates2026.0167.5
gpt-5-ThinkingModel Size=-, Reasoning Mode=Naive CoT2026.0158.3
gpt-4oModel Size=-, Reasoning Mode=Naive CoT2026.0157.7
ViLASRModel Size=7B, Reasoning Mode=Thinking with Images2026.0157.7
gpt-4oModel Size=-, Reasoning Mode=No2026.0157.2
Qwen2.5-VLModel Size=7B, Reasoning Mode=No2026.0156.8
Qwen2.5-VLModel Size=7B, Reasoning Mode=Naive CoT2026.0152.6