Commonsense Reasoning on Hellaswag (Score, Relative Change, Gate Density)
78.5Score
Vanilla
Updated 18d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 78.5 | - | - | |
2026.05 | 78.4 | 0 | 40.5 | |
2026.07 | 44.17 | - | - | |
2026.07 | 43.25 | - | - | |
2026.07 | 42.96 | - | - | |
2026.07 | 38.71 | - | - | |
2026.07 | 34.24 | - | - | |
2026.07 | 33.17 | - | - |