Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sudoku Solving on Sudoku 4x4 with reasoning traces (expert) (val)
Loading...
34
Accuracy
Pyligent
-1.36
7.82
17
26.18
Jul 8, 2026
Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
Pyligent
Architecture=Linear, B...
2026.07
34
Gold-only SFT
Backbone=Qwen3-4B
2026.07
20
Base model
Backbone=Qwen3-4B
2026.07
0
Feedback
Search any
task
Search any
task
