Commonsense Reasoning on BigBenchHard
71.7Accuracy
Phi-3 Mini-4k
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2024.10 | 71.7 | |
2024.10 | 69.7 | |
2024.10 | 59.6 | |
2024.10 | 58.2 | |
2024.10 | 57.3 | |
2024.10 | 51.5 | |
2026.01 | 45.27 | |
2026.01 | 45 | |
2026.01 | 44.9 | |
2026.01 | 44.82 | |
2026.01 | 44.6 | |
2026.01 | 44.59 | |
2026.01 | 44.48 | |
2026.01 | 44.41 | |
2026.01 | 44.17 | |
2026.01 | 43.95 | |
2026.01 | 43.19 | |
2026.01 | 43.1 |