| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ToM-BPD (test) | TTBYS | Strategy Accuracy39.78 | 27 | 2mo ago | |
| ESC (test) | Error Rate Metric (EMR)0.67 | 10 | 3mo ago | ||
| P4G | PRINCIPLES | Macro F10.1496 | 6 | 3mo ago | |
| ESConv | PRINCIPLES | Macro F110.52 | 6 | 3mo ago | |
| CARLA Town10 behavior-annotated (held-out set) | SemNav-VLM | Latency (ms)1,701 | 3 | 1mo ago |