Benchmarks
347 sources · 1,258 models × 3,038 benchmarks · 158,912 scoresMindCube evaluates whether vision-language models can build spatial mental models from limited multi-view observations. Its 21,154 questions across 3,268 images test cognitive mapping, perspective taking, and mental simulation, and scores are reported as accuracy.
No signal or difficulty estimate. No usable scores.
This is a benchmark-family page. Scores are recorded on the component benchmarks below rather than directly on the parent, because the components use different score scales and directions.
| Metric | Models | Leader | Direction | Date |
|---|---|---|---|---|
| MindCube Tiny | 57 | Gemini 4 Argon96.7 | higher is better | 2026-10-27 |