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-04

Expert #05 sudoku race

23 clues · seed 4005 · 19 models · suite v1

19 AI decision models raced to solve this expert sudoku (23 clues), one digit at a time. Span-02 by Respan came first with 11 mistakes.

0.0s / 90.8s0/19 done

Results

#ModelMistakesCallsCostSolve timeStatus
1Span-02Respan1128$0.00508263sSolved
2d1 UltraLiquid1227$0.00336011sSolved
3Kev 4BJared Palmer1327$0.00338017sSolved
4ClefCloudflare1328$0.00796222sSolved
5Clef OmniCloudflare1430$0.029915sSolved
6Clef FlashCloudflare1834$0.00622621sSolved
7d1Liquid2032$0.00193311sSolved
8Jev 1.14TypeSafe2134$0.00827011sSolved
9Drex v2.0Nace.AI2338$0.00837226sSolved
10Decider Flash v1.2Perplexity2337$0.00779663sSolved
11Decider v1.2Perplexity2337$0.00313388sSolved
12Decision-1Microsoft2538$0.00529125sSolved
13Jev 1.13TypeSafeolder2741$0.010011sSolved
14GPT-6 Luna DecisionsOpenAI2743$0.028823sSolved
15Classify-1ScaleDown2942$0.050529sSolved
16Tev1 4B ExperimentalTogether2941$0.041646sSolved
17Mercury DecideInception3245$0.00622126sSolved
18Solar Decide FlashUpstage3246$0.074591sSolved
19Drex v1.5Nace.AIolder3650$0.00673044sSolved