| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MetaDrive | SAGE | Attack Rate21.1 | 16 | 1mo ago | |
| SafeBench CARLA v3 (scenario-level) | ChatScene (CS) + EVODRIVE | Attack Success Rate50.7 | 8 | 1mo ago | |
| nuPlan (test) | SaFeR | Realism Score0.676 | 5 | 4mo ago | |
| Waymo Open Motion Dataset WOMD (test) | SaFeR | Realism Score77.3 | 5 | 4mo ago | |
| Hospital Queuing Scenario | GROVE | Alignment6.86 | 3 | 1mo ago | |
| Hospital Normal Scenario | GROVE | Alignment6.29 | 3 | 1mo ago | |
| Hospital Emergency Scenario | GROVE | Alignment4.5 | 3 | 1mo ago | |
| Scenario S4 | Inference Time (s)41 | 3 | 5mo ago | ||
| Scenario S3 | Inference Time (s)38 | 3 | 5mo ago | ||
| Scenario S2 | Inference Time (s)36 | 3 | 5mo ago | ||
| Scenario S1 | Inference Time (s)33 | 3 | 5mo ago | ||
| OpenForesight 95 economic and business-related market-event queries | Pairwise Distance0.313 | 2 | 25d ago | ||
| Driving | - | - | 0 | 1mo ago |