Video spatial & 4D reasoning on VSTI-Bench
67.6AccuracySpatialClaw
Evaluation Results
| Method | Links | |
|---|---|---|
| SpatialClawBackbone=Gemma4-31B2026.06 | 67.6 | |
| SpaceTools ToolshedBackbone=Gemma4-31B2026.06 | 56 | |
| pySpatialBackbone=Gemma4-31B2026.06 | 55 |
Loading the SOTA2 catalog…