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-03expert-05 →

Expert #04 sudoku race

24 clues · seed 4004 · 19 models · suite v1

19 AI decision models raced to solve this expert sudoku (24 clues), one digit at a time. Span-02 by Respan came first with 10 mistakes.

0.0s / 97.0s0/19 done

Results

#ModelMistakesCallsCostSolve timeStatus
1Span-02Respan1027$0.00483659sSolved
2Decision-1Microsoft1229$0.00369217sSolved
3d1Liquid1531$0.00187911sSolved
4Clef OmniCloudflare1530$0.030812sSolved
5Classify-1ScaleDown1530$0.031631sSolved
6d1 UltraLiquid1631$0.00400714sSolved
7Clef FlashCloudflare1630$0.00564222sSolved
8Jev 1.13TypeSafeolder1733$0.0079378.1sSolved
9Drex v2.0Nace.AI1932$0.00713323sSolved
10Drex v1.5Nace.AIolder1934$0.00421136sSolved
11Decider v1.2Perplexity1934$0.00279041sSolved
12Jev 1.14TypeSafe2034$0.00850813sSolved
13Tev1 4B ExperimentalTogether2035$0.032739sSolved
14Decider Flash v1.2Perplexity2031$0.00602548sSolved
15Mercury DecideInception2134$0.00439024sSolved
16ClefCloudflare2135$0.00996230sSolved
17Kev 4BJared Palmer2235$0.00461924sSolved
18GPT-6 Luna DecisionsOpenAI3146$0.030823sSolved
19Solar Decide FlashUpstage3448$0.079497sSolved