Synthetic GRF
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Policy Identity Recovery | Synthetic GRF 10x all-policy (GENERALIZATION) | Probe Accuracy61.1 | 7 | |
| Behavior Representation Generalization | Synthetic GRF 10x all policies (aggregate) | P Score61.1 | 4 |
Showing 2 of 2 rows