Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Sudoku Solving on Sudoku 512 tokens
Loading...
80.3
Pass@1
d-TreeRPO
2.508
22.704
42.9
63.096
Dec 10, 2025
Pass@1
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@1
d-TreeRPO
Base Model=LLaDA-8B-In...
2025.12
80.3
d-TreeRPO
Base Model=LLaDA-MoE-7...
2025.12
72
wd1
Base Model=LLaDA-MoE-7...
2025.12
35.4
GDPO
Base Model=LLaDA-MoE-7...
2025.12
30.6
TraceRL
Base Model=LLaDA-8B-In...
2025.12
25.4
TraceRL
Base Model=LLaDA-MoE-7...
2025.12
25.2
GDPO
Base Model=LLaDA-8B-In...
2025.12
24.8
wd1
Base Model=LLaDA-8B-In...
2025.12
24.2
SAPO
Base Model=LLaDA-MoE-7...
2025.12
18.7
SAPO
Base Model=LLaDA-8B-In...
2025.12
16.1
Diffu-GRPO
Base Model=LLaDA-MoE-7...
2025.12
15.4
Diffu-GRPO
Base Model=LLaDA-8B-In...
2025.12
11.2
VRPO (LLaDA-1.5)
Base Model=LLaDA-8B-In...
2025.12
9.6
LLaDA-MoE-7BA1B-Instruct
Base Model=LLaDA-MoE-7...
2025.12
8.1
LLaDA-8B-Instruct
Base Model=LLaDA-8B-In...
2025.12
5.5
Feedback
Search any
task
Search any
task