| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Autonomous Driving | HUGSIM Easy | Reachability Coverage (RC)84.1 | 25 | |
| Autonomous Driving | HUGSIM Overall | Reachability Coverage (RC)47.5 | 17 | |
| Autonomous Driving | HUGSIM Extreme | Reachability Coverage (RC)39.1 | 17 | |
| Autonomous Driving | HUGSIM Hard | Reachability Coverage (RC)40.4 | 17 | |
| Autonomous Driving | HUGSIM Medium | Reachability Coverage (RC)50.9 | 17 | |
| Closed-loop planning | HUGSIM photorealistic (Average) | RC50.1 | 8 | |
| Closed-loop planning | HUGSIM photorealistic (Extreme) | RC Score47.1 | 8 | |
| Closed-loop planning | HUGSIM photorealistic (Hard) | RC33.8 | 8 | |
| Closed-loop planning | HUGSIM photorealistic (Medium) | RC Score60.7 | 8 | |
| Autonomous Driving | HUGSim nuScenes-derived 88 scenarios | HD-Score (Easy)0.78 | 7 | |
| Closed-loop evaluation | HUGSIM pre-challenge v1 (test) | RC (Easy)84.2 | 5 | |
| Closed-loop autonomous driving | HUGSIM zero-shot | RC (Easy)80.9 | 4 |