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

← All races
← expert-02expert-04 →

Expert #03 sudoku race

25 clues · seed 4003 · 19 models · suite v1

19 AI decision models raced to solve this expert sudoku (25 clues), one digit at a time. Jev 1.13 by TypeSafe came first with 7 mistakes.

0.0s / 76.3s0/19 done

Results

#ModelMistakesCallsCostSolve timeStatus
1Jev 1.13TypeSafeolder724$0.0054415.5sSolved
2Clef OmniCloudflare1227$0.027211sSolved
3d1 UltraLiquid1227$0.00323212sSolved
4Span-02Respan1330$0.00513267sSolved
5Jev 1.14TypeSafe1528$0.0067369.6sSolved
6Tev1 4B ExperimentalTogether1532$0.029337sSolved
7Solar Decide FlashUpstage1530$0.040749sSolved
8Decider v1.2Perplexity1631$0.00247532sSolved
9Kev 4BJared Palmer1833$0.00423323sSolved
10Drex v2.0Nace.AI2035$0.00770325sSolved
11d1Liquid2134$0.00191912sSolved
12Decider Flash v1.2Perplexity2135$0.00761959sSolved
13Drex v1.5Nace.AIolder2235$0.00430426sSolved
14Mercury DecideInception2339$0.00515722sSolved
15Decision-1Microsoft2337$0.00514123sSolved
16Clef FlashCloudflare2339$0.00731230sSolved
17ClefCloudflare2438$0.013132sSolved
18GPT-6 Luna DecisionsOpenAI2844$0.029621sSolved
19Classify-1ScaleDown3448$0.061976sSolved