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
← medium-05hard-02 →

Hard #01 sudoku race

27 clues · seed 3001 · 19 models · suite v1

19 AI decision models raced to solve this hard sudoku (27 clues), one digit at a time. Span-02 by Respan came first with 7 mistakes.

0.0s / 62.2s0/19 done

Results

#ModelMistakesCallsCostSolve timeStatus
1Span-02Respan723$0.00361551sSolved
2Decider Flash v1.2Perplexity924$0.00422235sSolved
3Jev 1.14TypeSafe1024$0.0051677.5sSolved
4Jev 1.13TypeSafeolder1126$0.0061026.7sSolved
5d1 UltraLiquid1329$0.00355312sSolved
6Drex v2.0Nace.AI1429$0.00613228sSolved
7Classify-1ScaleDown1428$0.029935sSolved
8Clef FlashCloudflare1531$0.00645829sSolved
9Decision-1Microsoft1632$0.00437019sSolved
10d1Liquid1730$0.00177415sSolved
11ClefCloudflare1731$0.00926924sSolved
12Mercury DecideInception1832$0.00412616sSolved
13Kev 4BJared Palmer1932$0.00418722sSolved
14Drex v1.5Nace.AIolder2034$0.00435036sSolved
15Tev1 4B ExperimentalTogether2035$0.033362sSolved
16Clef OmniCloudflare2134$0.035514sSolved
17Decider v1.2Perplexity2337$0.00298948sSolved
18Solar Decide FlashUpstage2337$0.055559sSolved
19GPT-6 Luna DecisionsOpenAI1923$0.01769.2sError