| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Waymo Open Sim Agents Challenge 2025 | SMART-R1 | Realism Score78.58 | 14 | 1mo ago | |
| WOMD (val) | EvoQRE | NLL (bits)2.83 | 8 | 1mo ago | |
| WOMD Sim Agents 2024 | SMART | Realism Score75.11 | 7 | 1mo ago | |
| PhyGenBench PhysGen scenes | ECMS0.54 | 3 | 1mo ago |