Skip to content
decisionbench
OverallSudokuTriageRobustness

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

← All races
← medium-01medium-03 →

Medium #02 sudoku race

32 clues · seed 2002 · 12 models · suite v1

12 AI decision models raced to solve this medium sudoku (32 clues), one digit at a time. Jev 1.14 by TypeSafe came first with 6 mistakes.

0.0s / 49.0s0/12 done

Results

#ModelMistakesCallsCostSolve timeStatus
1Jev 1.14TypeSafe621$0.0043606.1sSolved
2d1Liquid823$0.0012359.6sSolved
3GPT-6 Luna DecisionsOpenAI1024$0.01389.8sSolved
4ClefCloudflare1024$0.00755218sSolved
5Decider Flash v1.2Perplexity1124$0.00407233sSolved
6d1 UltraLiquid1224$0.0026309.4sSolved
7Clef FlashCloudflare1226$0.00472020sSolved
8Decider v1.2Perplexity1225$0.00172721sSolved
9Mercury DecideInception1427$0.00326914sSolved
10Clef OmniCloudflare1527$0.02649.7sSolved
11Decision-1Microsoft1527$0.00344516sSolved
12Solar Decide FlashUpstage1631$0.040549sSolved