Logical Reasoning on RP Distribution, Npred ≤ 60, 6 < δ ≤ 12 (train)
88.9Accuracydirect w. L = 128
Evaluation results
| Method | Links | |
|---|---|---|
| direct w. L = 128Reasoning Strategy=Direct, Number of Layers=1282026.05 | 88.9 | |
| cot w. L = 64Reasoning Strategy=CoT, Number of Layers=642026.05 | 85.8 | |
| cot w. L = 128Reasoning Strategy=CoT, Number of Layers=1282026.05 | 81 | |
| cot (baseline)Reasoning Strategy=CoT2026.05 | 75.2 | |
| direct (baseline)Reasoning Strategy=Direct2026.05 | 74.9 |