OOD Suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Out-of-distribution Detection | OOD Suite Mean | FPR@9543.74 | 27 | |
| OOD detection | OOD Suite Average | AUROC0.9011 | 6 | |
| Out-of-Domain Generalization | OOD Suite BBH, HumanEval, MMLU, TruthfulQA | BBH Score59.1 | 4 |
Showing 3 of 3 rows