Arithmetic Reasoning on Countdown 256 tokens
71.1Pass@1d-TreeRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| d-TreeRPOBase Model=LLaDA-8B-Instruct, Generation Length=2562025.12 | 71.1 | |
| d-TreeRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.12 | 67.2 | |
| GDPOBase Model=LLaDA-8B-Instruct, Generation Length=2562025.12 | 64.1 | |
| GDPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.12 | 58.1 | |
| wd1Base Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.12 | 56.6 | |
| SAPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.12 | 54.2 | |
| TraceRLBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.12 | 54.2 | |
| SAPOBase Model=LLaDA-8B-Instruct, Generation Length=2562025.12 | 52 | |
| wd1Base Model=LLaDA-8B-Instruct, Generation Length=2562025.12 | 51.2 | |
| TraceRLBase Model=LLaDA-8B-Instruct, Generation Length=2562025.12 | 50.4 | |
| Diffu-GRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.12 | 50.1 | |
| LLaDA-MoE-7BA1B-InstructBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.12 | 42.6 | |
| Diffu-GRPOBase Model=LLaDA-8B-Instruct, Generation Length=2562025.12 | 31.3 | |
| VRPO (LLaDA-1.5)Base Model=LLaDA-8B-Instruct, Generation Length=2562025.12 | 22.3 | |
| LLaDA-8B-InstructBase Model=LLaDA-8B-Instruct, Generation Length=2562025.12 | 19.5 |