| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Spatial Reasoning | SPAR-Bench | Overall Score67.3 | 45 | |
| Spatial Reasoning (Multi-Image) | SPAR-Bench | Accuracy67.3 | 28 | |
| Spatial Relationship Reasoning | SPAR-Bench | Accuracy (Avg)59.9 | 26 | |
| Spatial Reasoning | SPAR-Bench full | Average Score68.35 | 23 | |
| Single-image spatial reasoning | SPAR-Bench SI | Low Score54.3 | 15 | |
| Multi-image Spatial Reasoning | SPAR-Bench-MV (test) | Score (Low Difficulty)43.7 | 15 | |
| Spatial Reasoning | SPAR-Bench tiny | Medium Difficulty Score72.32 | 12 | |
| Spatial Reasoning | SPAR-Bench SI, MV 91 | Accuracy63.3 | 11 | |
| High-level spatial reasoning | SPAR-Bench high-level tasks | High Average Score51.28 | 8 |