Question Answering on Race, Winogrande, PIQA, BoolQ, OpenBookQA, and SciQ
70Average Accuracy
Llama 3 8B Instruct
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.05 | 70 | 100 | |
2025.05 | 64.6 | - | |
2025.05 | 63 | 89.9 | |
2025.05 | 63 | 90.9 | |
2025.05 | 63 | 90 | |
2025.05 | 60.7 | - | |
2025.05 | 60 | 85.3 | |
2025.05 | 59.9 | - | |
2025.05 | 59 | 85.3 | |
2025.05 | 58 | 82.5 | |
2025.05 | 51 | - | |
2025.05 | 50.4 | - | |
2025.05 | 41 | - | |
2025.05 | 38.6 | - | |
2025.05 | 30.4 | - |