SenseNova-SI-1.3-InternVL3-8B: benchmark results
Provider: SenseTime. Access: API.
Aggregate Rating 1595 ± 42, rank #1053 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MultihopSpatial - 2-Hop Ego-Centric | 25.2 | Multiple-choice accuracy (%) on the 2-hop ego-centric questi | 86.1 |
| MultihopSpatial - 1-Hop Ego-Centric | 34.5 | Multiple-choice accuracy (%) on the 1-hop ego-centric questi | 83.3 |
| MultihopSpatial - 3-Hop Ego-Centric | 20.4 | Multiple-choice accuracy (%) on the 3-hop ego-centric questi | 81.9 |
| MultihopSpatial | 42.3 | Multiple-choice accuracy (%) over all 4,500 MultihopSpatial | 75 |
| MultihopSpatial - 1-Hop Exo-Centric | 73.2 | Multiple-choice accuracy (%) on the 1-hop exo-centric questi | 69.4 |
| MultihopSpatial - 3-Hop Exo-Centric | 45.2 | Multiple-choice accuracy (%) on the 3-hop exo-centric questi | 68.1 |
| SpatialUAV - Aerial-Aerial Shared Association | 6.6 | Shared Association Pair F1 (%; region-pair correspondences b | 64.7 |
| SpatialUAV - Object Matching | 8.5 | Object Matching Accuracy (%; box accepted at a composite IoU | 64.7 |
| SpatialUAV - Occlusion Removal | 41.3 | Occlusion Removal Accuracy (%; exact region IDs of targets h | 64.7 |
| SpatialUAV - Region Recognition | 50 | Region Recognition Score (%; region-ID sets, partial credit, | 64.7 |
| PinpointQA - Structured Spatial Prediction | 12 | Structured spatial prediction score (times 100, micro over Q | 64.3 |
| MultihopSpatial - Acc@50IoU | 17.3 | Acc@50IoU (%): a prediction counts only when the answer is r | 58.3 |
Interactive version: theaggregate.ai/model?slug=sensenova-si-1-3-internvl3-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.