Commonsense Reasoning on HellaSwag (Accuracy, Normalized Accuracy)
44.3Accuracy
AIRAhybrid-D
Updated 2mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 44.3 | 57.6 | |
2026.05 | 44.2 | 57.2 | |
2026.05 | 44.2 | 57.6 | |
2026.05 | 44.1 | 57.8 | |
2026.05 | 44.1 | 57.1 | |
2026.05 | 44 | 56.6 | |
2026.05 | 44 | 57.1 | |
2026.05 | 43.9 | 56.9 | |
2026.05 | 43.5 | 56.5 | |
2026.05 | 43.4 | 56.3 | |
2026.05 | 43.3 | 56.1 | |
2026.05 | 43.2 | 55.8 |