SpatialReasoner: benchmark results
Provider: Johns Hopkins University. Access: Open.
Aggregate Rating 1543 ± 50, rank #1796 of 10916 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SpatialThinker Release - SpatialReasonerEval | 76.4 | Accuracy (%) | 66.7 |
| MultihopSpatial - 3-Hop Ego-Centric | 18 | Multiple-choice accuracy (%) on the 3-hop ego-centric questi | 61.1 |
| MultihopSpatial - Acc@50IoU | 8.7 | Acc@50IoU (%): a prediction counts only when the answer is r | 33.3 |
| SpatialThinker Release - SpatialBench | 59.2 | Accuracy (%) | 33.3 |
| MultihopSpatial - 2-Hop Exo-Centric | 46 | Multiple-choice accuracy (%) on the 2-hop exo-centric questi | 19.4 |
| MultihopSpatial - 3-Hop Exo-Centric | 34 | Multiple-choice accuracy (%) on the 3-hop exo-centric questi | 19.4 |
| MultihopSpatial - 2-Hop Ego-Centric | 19.6 | Multiple-choice accuracy (%) on the 2-hop ego-centric questi | 18.1 |
| MultihopSpatial - 1-Hop Exo-Centric | 51.5 | Multiple-choice accuracy (%) on the 1-hop exo-centric questi | 16.7 |
| MultihopSpatial | 31.7 | Multiple-choice accuracy (%) over all 4,500 MultihopSpatial | 13.9 |
| SpatialThinker Release - MMVP | 64 | Accuracy (%) | 13.3 |
| MultihopSpatial - 1-Hop Ego-Centric | 21.3 | Multiple-choice accuracy (%) on the 1-hop ego-centric questi | 11.1 |
Interactive version: theaggregate.ai/model?slug=spatialreasoner · How It Works · Data refreshed daily, snapshot 2026-11-08.