Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Boolean Satisfiability (SAT) on SAT Easy (test)
Loading...
98
Accuracy
Recursive Model
48.08
61.04
74
86.96
Mar 2, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Recursive Model
Backbone=Qwen2.5-3B-In...
2026.03
98
Qwen3-235B
2026.03
88
DeepSeek-Distill-14B
2026.03
84.3
GPT-4o
2026.03
69.9
LLaMA3.3-70B
2026.03
65.1
Random Baseline
2026.03
50
Feedback
Search any
task
Search any
task