Common Sense Reasoning on PIQA
91.89Accuracy
Llama-3.3-70B-Instruct
Updated 27d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 91.89 | - | |
2026.04 | 89.88 | - | |
2026.04 | 88.41 | - | |
2026.04 | 87.21 | - | |
2026.04 | 87.11 | - | |
2026.04 | 86.4 | - | |
2026.03 | 83 | - | |
2025.07 | 82.2 | - | |
2025.07 | 81.5 | - | |
2025.07 | 81.4 | - | |
2025.10 | 80.8 | 0.6 | |
2026.04 | 80.6 | - | |
2026.04 | 80.4 | - | |
2026.04 | 80.3 | - | |
2026.04 | 80.3 | - | |
2025.10 | 80.2 | -0.3 | |
2026.04 | 80.1 | - | |
2026.04 | 80.1 | - | |
2025.07 | 79.9 | - | |
2026.04 | 79.7 | - | |
2026.04 | 79.4 | - | |
2026.04 | 78.9 | - | |
2025.10 | 78.8 | 1.1 | |
2025.07 | 78.8 | - | |
2025.10 | 78.6 | 0 | |
2026.03 | 78.5 | - | |
2026.03 | 78.2 | - | |
2026.03 | 78.1 | - | |
2025.10 | 77.9 | -3.4 | |
2026.03 | 77.9 | - | |
2026.03 | 77.45 | - | |
2026.03 | 77.1 | - | |
2026.03 | 77 | - | |
2026.04 | 76.8 | - | |
2025.10 | 76 | 2.8 | |
2026.03 | 76 | - | |
2026.03 | 76 | - | |
2026.04 | 75.7 | - | |
2026.03 | 75.68 | - | |
2026.03 | 75.52 | - | |
2026.03 | 75.41 | - | |
2026.03 | 75.23 | - | |
2026.03 | 75.19 | - | |
2026.03 | 75.14 | - | |
2026.03 | 75.08 | - | |
2026.04 | 74.9 | - | |
2026.03 | 74.86 | - | |
2026.03 | 74.65 | - | |
2026.03 | 74.54 | - | |
2026.03 | 74.48 | - | |
2026.03 | 74.48 | - | |
2026.03 | 74.2 | - | |
2025.09 | 73.6 | - | |
2026.04 | 73.29 | - | |
2026.03 | 73 | - | |
2025.09 | 73 | - | |
2026.02 | 72.74 | - | |
2026.04 | 72.63 | - | |
| 72.58 | - | ||
2026.02 | 72.25 | - | |
2026.02 | 72.2 | - | |
2026.02 | 72.03 | - | |
2026.04 | 72.03 | - | |
2026.02 | 71.87 | - | |
2026.03 | 71 | - | |
2025.09 | 69.7 | - | |
2025.09 | 69.6 | - | |
2026.02 | 69.26 | - | |
2026.02 | 69.26 | - | |
2026.05 | 68.9 | - | |
2026.02 | 68.88 | - | |
2026.02 | 68.77 | - | |
2026.02 | 68.61 | - | |
2026.05 | 67.4 | - | |
2026.05 | 66.8 | - | |
2026.04 | 65.3 | - | |
2026.04 | 65.3 | - | |
2026.03 | 63.93 | - | |
2026.03 | 63.6 | - | |
2026.03 | 63.44 | - | |
2025.09 | 63.3 | - | |
2026.04 | 63.2 | - | |
2026.04 | 63.1 | - | |
2026.03 | 63 | - | |
2026.04 | 62.9 | - | |
2026.04 | 62.9 | - | |
2026.04 | 62.9 | - | |
2026.04 | 62.7 | - | |
2026.03 | 62.4 | - | |
2026.03 | 60.72 | - | |
2026.03 | 60.55 | - | |
2026.05 | 59.6 | - | |
2026.03 | 58 | - | |
2026.05 | 56.1 | - | |
2026.03 | 56 | - | |
2026.03 | 49.72 | - | |
2026.04 | 46.57 | - | |
2026.03 | 26.06 | - | |
2026.03 | 18.3 | - | |
2026.03 | 0 | - |