Sentence Completion on HellaSwag 2019
80.12Normalized Accuracy
Baseline
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 80.12 | |
2026.06 | 76.49 | |
2026.06 | 76.14 | |
2026.06 | 75.98 | |
2026.06 | 74.35 | |
2026.06 | 68.49 | |
2026.06 | 68.33 | |
2026.06 | 68.09 | |
2026.06 | 65.41 | |
2026.06 | 64.71 | |
2026.06 | 62.48 | |
2026.06 | 61.5 | |
2026.06 | 61.41 | |
2026.06 | 59.16 | |
2026.06 | 58.81 | |
2026.06 | 58.71 | |
2026.06 | 56.14 | |
2026.06 | 53.84 | |
2026.06 | 47.66 | |
2026.06 | 39.49 | |
2026.06 | 39.48 | |
2026.06 | 39.4 | |
2026.06 | 36.3 | |
2026.06 | 33.98 | |
2026.06 | 33.62 | |
2026.06 | 33.26 |