List your company
ResearchFormerly WizWand

Sudoku Solving on Sudoku 256 tokens

92.9Pass@1d-TreeRPO
3.25226.52649.873.074Dec 10, 2025
Updated 8mo ago

Evaluation results

MethodLinks
d-TreeRPOBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.1292.9
d-TreeRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.1278.3
wd1Base Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.1240.6
GDPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.1231.2
TraceRLBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.1227.4
GDPOBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.1225.7
TraceRLBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.1225.6
wd1Base Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.1225.2
SAPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.1221.2
SAPOBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.1220.3
Diffu-GRPOBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.1217.3
Diffu-GRPOBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.1212.9
VRPO (LLaDA-1.5)Base Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.1212.8
LLaDA-MoE-7BA1B-InstructBase Model=LLaDA-MoE-7BA1B-Instruct, Generation Length=256, Zero-shot=true2025.1212.7
LLaDA-8B-InstructBase Model=LLaDA-8B-Instruct, Generation Length=256, Zero-shot=true2025.126.7