Logical Reasoning on Sudoku 9x9
0.11AccuracyMargin
Evaluation Results
| Method | Links | |
|---|---|---|
| MarginOrder score=Margin, Backbone=LLaDA-8B2026.02 | 0.11 | |
| Gt-MarginOrder score=Ours, Backbone=LLaDA-8B2026.02 | 0.085 | |
| Gt-MarginOrder score=Ours w/o partial plan, partial plan=false, Backbone=LLaDA-8B2026.02 | 0.045 | |
| RandomOrder score=Random, Backbone=LLaDA-8B2026.02 | 0 | |
| Gt-MarginOrder score=Ours w/o token pred, token prediction hypothesis=false, Backbone=LLaDA-8B2026.02 | 0 |