ARB
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reasoning | ARB OOD | Accuracy88.7 | 10 | |
| Reasoning | ARB ID | Accuracy (ARB ID)91.2 | 10 | |
| Information Retrieval | ARB internal deployment (val) | Observed False Positives0 | 6 | |
| Information Retrieval | ARB Sem. Relevant (val) | F1 Score99.67 | 5 |
Showing 4 of 4 rows