| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| OOD Detection | OOD Datasets Mean | FPR@9538.7 | 20 | |
| LLM Routing | OOD datasets (test) | Accuracy89 | 11 | |
| Few-shot classification | OOD Datasets (test) | Accuracy (Traffic Signs)91.33 | 11 | |
| Uncertainty Estimation | 23 OOD datasets | Mean AURC10.2 | 2 |