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
← hard-02hard-04 →

Hard #03 sudoku race

27 clues · seed 3003 · 12 models · suite v1

12 AI decision models raced to solve this hard sudoku (27 clues), one digit at a time. d1 Ultra by Liquid came first with 5 mistakes.

0.0s / 42.1s0/12 done

Results

#ModelMistakesCallsCostSolve timeStatus
1d1 UltraLiquid522$0.0024497.3sSolved
2ClefCloudflare923$0.010819sSolved
3d1Liquid1026$0.0013507.3sSolved
4Jev 1.14TypeSafe1125$0.0056107.5sSolved
5Clef OmniCloudflare1125$0.024511sSolved
6Decider Flash v1.2Perplexity1126$0.00484840sSolved
7Mercury DecideInception1329$0.00361816sSolved
8Clef FlashCloudflare1328$0.00534621sSolved
9Solar Decide FlashUpstage1328$0.037442sSolved
10GPT-6 Luna DecisionsOpenAI1730$0.018714sSolved
11Decision-1Microsoft1932$0.00402818sSolved
12Decider v1.2Perplexity1935$0.00276937sSolved