Sudoku Solving on Sudoku 256 tokens
92.9Pass@1d-TreeRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| d-TreeRPOBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 92.9 | |
| d-TreeRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 78.3 | |
| wd1Base Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 40.6 | |
| GDPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 31.2 | |
| TraceRLBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 27.4 | |
| GDPOBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 25.7 | |
| TraceRLBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 25.6 | |
| wd1Base Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 25.2 | |
| SAPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 21.2 | |
| SAPOBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 20.3 | |
| Diffu-GRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 17.3 | |
| Diffu-GRPOBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 12.9 | |
| VRPO (LLaDA-1.5)Base Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 12.8 | |
| LLaDA-MoE-7BA1B-InstructBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 12.7 | |
| LLaDA-8B-InstructBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.12 | 6.7 |