SpaceOm: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1581 ± 33, rank #1231 of 10916 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UAV-DualCog - Flight Behavior Recognition (Composite) | 35.9 | Composite-level behavior accuracy (%; 1,024 first-person UAV | 90.4 |
| SpatialQuery-1M - Proximity Decision | 66.68 | Accuracy (%; binary decision whether the closest same-catego | 90 |
| SpatialQuery-1M - Closest-Instance Distance | 28.5 | Acc@0.2m (%; share of 5,000 fixed closest-instance distance | 80 |
| SpatialThinker Release - CV-Bench2D | 72.1 | Accuracy (%) | 80 |
| SpatialThinker Release - 3DSRBench | 52.2 | Accuracy (%) | 75 |
| SpatialThinker Release - BLINKSpatialRelation | 81.1 | Accuracy (%) | 72.2 |
| SpatialThinker Release - BLINKAverage | 73.2 | Accuracy (%) | 66.7 |
| SpatialThinker Release - CV-BenchAverage | 70.7 | Accuracy (%) | 66.7 |
| SpatialThinker Release - HallusionBench | 62.9 | Accuracy (%) | 66.7 |
| MultihopSpatial - Acc@50IoU | 22.7 | Acc@50IoU (%): a prediction counts only when the answer is r | 61.1 |
| SpatialThinker Release - CV-Bench3D | 69.3 | Accuracy (%) | 57.9 |
| SpatialThinker Release - BLINKMultiView | 48.9 | Accuracy (%) | 50 |
Interactive version: theaggregate.ai/model?slug=spaceom · How It Works · Data refreshed daily, snapshot 2026-11-08.