| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Calibration | BEAR (test) | Brier Score0.083 | 96 | |
| Multimodal Embodied Reasoning | BEAR 1.0 (test) | Task Process Reasoning (PRG)87.5 | 17 | |
| Embodied Skill Evaluation | BEAR | Task Plan Success (PRG)87.5 | 12 | |
| Time-series forecasting | Bear | MSE0.41 | 3 |