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-01expert-03 →

Expert #02 sudoku race

24 clues · seed 4002 · 19 models · suite v1

19 AI decision models raced to solve this expert sudoku (24 clues), one digit at a time. Clef Omni by Cloudflare came first with 11 mistakes.

0.0s / 72.6s0/19 done

Results

#ModelMistakesCallsCostSolve timeStatus
1Clef OmniCloudflare1129$0.029412sSolved
2Span-02Respan1127$0.00440858sSolved
3d1Liquid1227$0.0015669.8sSolved
4Jev 1.14TypeSafe1328$0.0065798.8sSolved
5Drex v1.5Nace.AIolder1429$0.00347719sSolved
6Decider v1.2Perplexity1430$0.00234131sSolved
7Clef FlashCloudflare1532$0.00643426sSolved
8Jev 1.13TypeSafeolder1631$0.0074787.8sSolved
9Decision-1Microsoft1731$0.00404618sSolved
10Drex v2.0Nace.AI1732$0.00727928sSolved
11d1 UltraLiquid1833$0.00412729sSolved
12ClefCloudflare1933$0.010326sSolved
13Decider Flash v1.2Perplexity1933$0.00690855sSolved
14Solar Decide FlashUpstage2537$0.056366sSolved
15GPT-6 Luna DecisionsOpenAI2641$0.028120sSolved
16Mercury DecideInception2740$0.00537633sSolved
17Tev1 4B ExperimentalTogether2744$0.045049sSolved
18Classify-1ScaleDown2841$0.049773sSolved
19Kev 4BJared Palmer3045$0.00636132sSolved