Logical Reasoning on RP Npred ≤ 30, 6 < δ ≤ 12 (train)
99.5Accuracy (RP Npred ≤ 30, 6 < δ ≤ 12 train)cot w. L = 64
Evaluation results
| Method | Links | |
|---|---|---|
| cot w. L = 64Reasoning Strategy=CoT, Number of Layers=642026.05 | 99.5 | |
| cot w. L = 128Reasoning Strategy=CoT, Number of Layers=1282026.05 | 99.4 | |
| direct w. L = 128Reasoning Strategy=Direct, Number of Layers=1282026.05 | 98.5 | |
| cot (baseline)Reasoning Strategy=CoT2026.05 | 96.8 | |
| direct (baseline)Reasoning Strategy=Direct2026.05 | 72.9 |