Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Combinatorial Reasoning on 3-SAT
Loading...
90.9
Accuracy
Policy
75.3
79.35
83.4
87.45
May 29, 2026
Accuracy
Updated 1d ago
Evaluation Results
Method
Method
Links
Accuracy
Policy
Training protocol=Join...
2026.05
90.9
High conf.
Training protocol=Join...
2026.05
89.8
Baseline
Training protocol=Join...
2026.05
88.8
Margin
Training protocol=Join...
2026.05
85.2
Oracle policy
Training protocol=Poli...
2026.05
82.3
Policy
Training protocol=Poli...
2026.05
76.1
Margin
Training protocol=Poli...
2026.05
76
High conf.
Training protocol=Poli...
2026.05
75.9
Feedback
Search any
task
Search any
task