Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Combinatorial Reasoning on Sudoku
Loading...
100
Accuracy
Oracle policy
88.2168
91.2759
94.335
97.3941
May 29, 2026
Accuracy
Updated 1d ago
Evaluation Results
Method
Method
Links
Accuracy
Oracle policy
Training protocol=Poli...
2026.05
100
Policy
Training protocol=Join...
2026.05
92.87
Baseline
Training protocol=Join...
2026.05
92.72
High conf.
Training protocol=Join...
2026.05
92.68
Margin
Training protocol=Join...
2026.05
91
Policy
Training protocol=Poli...
2026.05
90.82
High conf.
Training protocol=Poli...
2026.05
89.84
Margin
Training protocol=Poli...
2026.05
88.67
Feedback
Search any
task
Search any
task