Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Sudoku

Benchmarks

Task NameDataset NameSOTA ResultTrend
Logical ReasoningSudoku
Accuracy94.3
152
PlanningSudoku
Accuracy92.7
141
ReasoningSudoku
Pass@196
60
Puzzle SolvingSudoku
Test Accuracy27.2
42
Sudoku SolvingSudoku (test)
Accuracy100
33
ReasoningSudoku
Accuracy (Sudoku Reasoning)91.9
25
SudokuSudoku 4x4 (test)
Accuracy (Avg)14.7
25
Logical planningSudoku (test)
Accuracy91.7
24
ReasoningSudoku Extreme
Pass@1 Accuracy99.8
21
SudokuSudoku
Accuracy91.82
19
ReasoningSudoku (test)
Accuracy100
19
Sudoku SolvingSudoku 25x25 (90% masking)
VPR (%)52.2
18
Sudoku SolvingSudoku 25x25 80% masking
VPR (%)100
18
Sudoku SolvingSudoku 25x25 70% masking
VPR (%)100
18
Agent TaskSudoku
Success Rate (SR)99
17
Agent Behavior AdaptationSudoku (Su) (test)
Loop Ratio34.3
17
Sudoku SolvingSudoku 512 tokens
Pass@180.3
15
Sudoku SolvingSudoku 256 tokens
Pass@192.9
15
Planning and ReasoningSudoku
Accuracy99.4
14
Sudoku SolvingSudoku 2x2
Final Reward1.3
14
Puzzle SolvingSudoku Out Of Distribution
Average @12877.8
12
Puzzle SolvingSudoku In Distribution
Average Score @12897.1
12
Sudoku SolvingSudoku 10k 9x9 boards (val)
Board Accuracy93.4
12
Constraint SatisfactionSudoku
CSP Result Index 3557
12
Sudoku SolvingSudoku
Success Rate (pass@1)100
12
Showing 25 of 75 rows