Commonsense Reasoning on Winogrande (0-shot and 32-shot evaluation)
73.7Accuracy (0-shot)
OPT 175B
Updated 2d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2022.12 | 73.7 | 77.6 | |
2022.12 | 73 | 74.4 | |
2025.10 | 72.14 | - | |
2025.10 | 72.14 | - | |
2025.10 | 71.98 | - | |
2025.10 | 71.9 | - | |
2025.10 | 71.43 | - | |
2025.10 | 71.35 | - | |
2025.10 | 70.56 | - | |
2025.10 | 70.32 | - | |
2025.10 | 70 | - | |
2022.12 | 69.7 | 71.7 | |
2025.10 | 69.14 | - | |
2025.10 | 68.19 | - | |
2025.10 | 67.88 | - | |
2022.12 | 67.8 | 69 | |
2025.10 | 67.8 | - | |
2025.10 | 65.35 | - | |
2025.10 | 65.35 | - | |
2025.10 | 64.56 | - | |
2025.10 | 60.93 | - | |
2025.10 | 60.38 | - | |
2022.12 | 59.5 | 56.4 | |
2025.10 | 58.96 | - | |
2022.12 | 58 | 58.7 | |
2025.10 | 57.46 | - | |
2025.10 | 54.93 | - | |
2025.10 | 53.75 | - | |
2025.10 | 53.43 | - | |
2025.10 | 53.28 | - | |
2025.10 | 51.78 | - | |
2025.10 | 51.54 | - | |
2025.10 | 50.83 | - | |
2025.10 | 50.51 | - | |
2025.10 | 50.43 | - | |
2025.10 | 50.04 | - | |
2025.10 | 50.04 | - | |
2025.10 | 49.49 | - | |
2025.10 | 49.33 | - | |
2025.10 | 49.25 | - | |
2025.10 | 49.25 | - | |
2025.10 | 48.3 | - |