Physical Commonsense Reasoning on PIQA (0-shot and 32-shot)
79.8Accuracy (0-shot)
OPT-IML 175B
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2022.12 | 79.8 | 80.5 | |
2022.12 | 79.5 | 81.6 | |
2022.12 | 77.5 | 78.8 | |
2022.12 | 77.3 | 69.2 | |
2022.12 | 72.3 | 72.6 | |
2022.12 | 71.8 | 72.1 |