Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sudoku Solving on Sudoku 3x3
Loading...
160
Final Reward
NSAM(ours)
-245.6
-140.3
-35
70.3
Feb 11, 2026
Final Reward
Violation Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Final Reward
Violation Rate
NSAM(ours)
2026.02
160
0.3
KCAC
2026.02
150
57.1
Rainbow
2026.02
80
88.2
PPO
2026.02
-40
99.6
PPO-lagrangian
2026.02
-40
99.9
PLPG
2026.02
-90
8.9
RC-PPO
2026.02
-230
99
Feedback
Search any
task
Search any
task