Sudoku Solving on Sudoku 512 tokens
80.3Pass@1d-TreeRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| d-TreeRPOBase Model=LLaDA-8B-Instruct, Generation Length=5122025.12 | 80.3 | |
| d-TreeRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=5122025.12 | 72 | |
| wd1Base Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=5122025.12 | 35.4 | |
| GDPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=5122025.12 | 30.6 | |
| TraceRLBase Model=LLaDA-8B-Instruct, Generation Length=5122025.12 | 25.4 | |
| TraceRLBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=5122025.12 | 25.2 | |
| GDPOBase Model=LLaDA-8B-Instruct, Generation Length=5122025.12 | 24.8 | |
| wd1Base Model=LLaDA-8B-Instruct, Generation Length=5122025.12 | 24.2 | |
| SAPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=5122025.12 | 18.7 | |
| SAPOBase Model=LLaDA-8B-Instruct, Generation Length=5122025.12 | 16.1 | |
| Diffu-GRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=5122025.12 | 15.4 | |
| Diffu-GRPOBase Model=LLaDA-8B-Instruct, Generation Length=5122025.12 | 11.2 | |
| VRPO (LLaDA-1.5)Base Model=LLaDA-8B-Instruct, Generation Length=5122025.12 | 9.6 | |
| LLaDA-MoE-7BA1B-InstructBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=5122025.12 | 8.1 | |
| LLaDA-8B-InstructBase Model=LLaDA-8B-Instruct, Generation Length=5122025.12 | 5.5 |