SpaceR: benchmark results
Provider: Other.
Aggregate Rating 1584 ± 43, rank #1197 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UAV-DualCog - Landmark-Driven Action Decision | 48.8 | Answer accuracy (%; 1,024 questions asking which way the UAV | 62.9 |
| UAV-DualCog - Flight Behavior Recognition (Composite) | 22.2 | Composite-level behavior accuracy (%; 1,024 first-person UAV | 61.5 |
| SpatialGen-Bench (Text Answering) | 45.7 | Overall Accuracy (%) | 53.8 |
| SiT-Bench - Global Perception & Mapping | 19.4 | Accuracy (%; item-weighted over the category's subtasks) | 43.3 |
| UAV-DualCog - Flight Behavior Recognition (Atomic) | 26.8 | Atomic-level behavior accuracy (%; the atomic flight actions | 42.3 |
| UAV-DualCog - Landmark-Relative Direction | 42.4 | Answer accuracy (%; 1,024 questions asking where a landmark | 37.1 |
| SiT-Bench - Multi-View & Geometric Reasoning | 43.9 | Accuracy (%; item-weighted over the category's subtasks) | 36.7 |
| SiT-Bench - Navigation & Planning | 44.22 | Accuracy (%; item-weighted over the category's subtasks) | 35 |
| SiT-Bench | 36.42 | Accuracy (%; item-weighted over the 17 subtasks) | 34.5 |
| SiT-Bench - Embodied & Fine-grained Perception | 37.56 | Accuracy (%; item-weighted over the category's subtasks) | 33.3 |
| SiT-Bench - Logic & Anomaly Detection | 26.89 | Accuracy (%; item-weighted over the category's subtasks) | 26.7 |
| UAV-DualCog - Landmark Visibility Counting | 32.6 | Visibility-count accuracy (%; 1,024 flight videos in which t | 19.6 |
Interactive version: theaggregate.ai/model?slug=spacer · How It Works · Data refreshed daily, snapshot 2026-11-08.