What it measures
Visual-Spatial Intelligence benchmark measuring 3D room layout, object distance, relative direction, and camera motion from video.
Reading the measurement
Ask whether the evaluation rewards recalling a fact, constructing a model, running an experiment or supporting a discovery. Those tasks require different evidence. For research claims, inspect reproducibility, uncertainty and what was actually checked.
Published evaluation
Published mean over the spatial video tasks. Tiny-set human and random/frequency baselines are excluded; the source full-set model cohort is retained.
Where this fits in an evaluation suite
A correct multiple-choice answer and a supported scientific contribution demand different evidence. Check whether the score rewards a proposal, an executed experiment, or a completed research target.
Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.
A reproducible comparison
Published mean over the spatial video tasks. Tiny-set human and random/frequency baselines are excluded; the source full-set model cohort is retained.
Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-27. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.