List your company
ResearchFormerly WizWand

Grade School Math Word Problems on GSM8K (256 tokens context)

81.2Pass@1d-TreeRPO
71.42473.96276.579.038Dec 10, 2025
Updated 8mo ago

Evaluation results

MethodLinks
d-TreeRPOBase Model=LLaDA-8B-Instruct, Generation Length=2562025.1281.2
GDPOBase Model=LLaDA-8B-Instruct, Generation Length=2562025.1281.1
wd1Base Model=LLaDA-8B-Instruct, Generation Length=2562025.1280.8
SAPOBase Model=LLaDA-8B-Instruct, Generation Length=2562025.1280.6
TraceRLBase Model=LLaDA-8B-Instruct, Generation Length=2562025.1280.3
VRPO (LLaDA-1.5)Base Model=LLaDA-8B-Instruct, Generation Length=2562025.1280.1
Diffu-GRPOBase Model=LLaDA-8B-Instruct, Generation Length=2562025.1279.8
LLaDA-8B-InstructBase Model=LLaDA-8B-Instruct, Generation Length=2562025.1276.7
wd1Base Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.1276.2
d-TreeRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.1275.5
TraceRLBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.1275.4
SAPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.1275.2
GDPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.1274.8
Diffu-GRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.1274.2
LLaDA-MoE-7BA1B-InstructBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=2562025.1271.8