Skip to content
decisionbench
OverallSudokuRulebookConsistencyOdds

Independent benchmark. Not affiliated with or endorsed by OpenRouter or any model provider. Company and model names are trademarks of their respective owners.

How ranking worksPrivacyTermsContact

© 2026 editid0

← Sudoku leaderboard

Jev 1.13

older

TypeSafe · typesafe/jev-1.13 · added 20 Oct 2026

Newest version: Jev 1.14. Ranks on this page count every version, older ones included.

Jev 1.13 by TypeSafe, an older version of Jev 1.14, ranks #4 of 19 AI decision models on the DecisionBench Sudoku benchmark (logical reasoning), with accuracy 82.4%. View on OpenRouter.

Overall#5Sudoku#4Rulebook#10Consistency#8Odds#8
Sudoku rank
#4 of 19
Accuracy
82.4%
Solved
20/20
Mistakes / puzzle
10.8
Solve time / puzzle
6.9s
Cost / puzzle
$0.005520

By difficulty

DifficultyRankAccuracySolvedMistakesSolve timeCost
Easy#590.7%5/54.25.0s$0.003120
Medium#783.6%5/59.66.6s$0.004970
Hard#481.1%5/512.68.1s$0.006373
Expert#477.5%5/516.67.8s$0.007615

Every race

PuzzleMistakesCallsSolve timeCostStatus
easy-015183.8s$0.003573Solved
easy-022156.0s$0.002764Solved
easy-036176.5s$0.003395Solved
easy-044164.7s$0.002947Solved
easy-054164.0s$0.002922Solved
medium-015208.5s$0.004057Solved
medium-0216287.7s$0.006043Solved
medium-0314276.4s$0.005952Solved
medium-0410246.8s$0.005053Solved
medium-053193.8s$0.003744Solved
hard-0111266.7s$0.006102Solved
hard-0215298.5s$0.006600Solved
hard-0312269.4s$0.006100Solved
hard-0411278.7s$0.006257Solved
hard-0514297.2s$0.006807Solved
expert-0116306.5s$0.007172Solved
expert-0216317.8s$0.007478Solved
expert-037245.5s$0.005441Solved
expert-0417338.1s$0.007937Solved
expert-05274111s$0.0100Solved

Jev 1.13 across all benchmarks · How Sudoku works