Has GPT-5 Achieved Spatial Intelligence? GPT-5 sets SoTA but not...

GPT‑5 leads overall but is still short of human skill, especially on mentally reconstructing shapes, changing viewpoints, and deformation/assembly tasks.
The authors consolidate prior work into six core SI capabilities (Metric Measurement, Mental Reconstruction, Spatial Relations, Perspective‑taking, Deformation & Assembly, Comprehensive Reasoning) and standardize prompts, answer extraction, and metrics to reduce evaluation variance across datasets.
While proprietary models win on average, their advantage evaporates on the hardest SI categories; several open‑source systems perform similarly, far from human ability on MR/PT/DA/CR.
Non‑SI portions (e.g., CoreCognition’s Formal Operation) can reach near‑human levels.
Case studies show prompt sensitivity for novel‑view generation, blind spots with perspective effects and size constancy, persistent failures on paper‑folding/assembly, and difficulty inferring occluded objects during counting.
Paper: arxiv.org/abs/2508.13142






