| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Spatial Reasoning | MMSI | Score32.3 | 21 | |
| Social Reasoning | MMSI | STI71.2 | 15 | |
| Multi-image Spatial Reasoning | MMSI | Overall Accuracy38 | 15 | |
| Embodied Spatial Question Answering | MMSI | Score39.6 | 14 | |
| Multi-modal Spatial Intelligence | MMSI | Accuracy38 | 14 | |
| Real-world cross-view spatial reasoning | MMSI | Overall Accuracy32 | 13 | |
| Multi-view Spatial Reasoning | MMSI | Overall Score48.77 | 12 | |
| Multi-view spatial reasoning | MMSI 2025 | Accuracy53.9 | 12 | |
| Spatial-Temporal Reasoning | MMSI | Accuracy41.8 | 9 | |
| Spatial & Vision Grounding | MMSI | Pass@566.4 | 8 | |
| Spatial Understanding | MMSI | Accuracy41.8 | 6 | |
| Multi-view spatial reasoning | MMSI | Accuracy51.3 | 3 |