Commonsense Reasoning on HellaSwag Spanish (test)
53.1AccuracyML
Evaluation Results
| Method | Links | |
|---|---|---|
| MLFiltering Strategy=Multilingual (ML) classifier, Model size=1B2026.04 | 53.1 | |
| HQFiltering Strategy=Monolingual high-quality (HQ), Model size=1B2026.04 | 52.63 | |
| No filteringFiltering Strategy=None, Model size=1B2026.04 | 50.06 |