Expert #03 sudoku race
25 clues · seed 4003 · 19 models · suite v1
19 AI decision models raced to solve this expert sudoku (25 clues), one digit at a time. Jev 1.13 by TypeSafe came first with 7 mistakes.
Results
| # | Model | Mistakes | Calls | Cost | Solve time | Status |
|---|---|---|---|---|---|---|
| 1 | Jev 1.13TypeSafeolder | 7 | 24 | $0.005441 | 5.5s | Solved |
| 2 | Clef OmniCloudflare | 12 | 27 | $0.0272 | 11s | Solved |
| 3 | d1 UltraLiquid | 12 | 27 | $0.003232 | 12s | Solved |
| 4 | Span-02Respan | 13 | 30 | $0.005132 | 67s | Solved |
| 5 | Jev 1.14TypeSafe | 15 | 28 | $0.006736 | 9.6s | Solved |
| 6 | Tev1 4B ExperimentalTogether | 15 | 32 | $0.0293 | 37s | Solved |
| 7 | Solar Decide FlashUpstage | 15 | 30 | $0.0407 | 49s | Solved |
| 8 | Decider v1.2Perplexity | 16 | 31 | $0.002475 | 32s | Solved |
| 9 | Kev 4BJared Palmer | 18 | 33 | $0.004233 | 23s | Solved |
| 10 | Drex v2.0Nace.AI | 20 | 35 | $0.007703 | 25s | Solved |
| 11 | d1Liquid | 21 | 34 | $0.001919 | 12s | Solved |
| 12 | Decider Flash v1.2Perplexity | 21 | 35 | $0.007619 | 59s | Solved |
| 13 | Drex v1.5Nace.AIolder | 22 | 35 | $0.004304 | 26s | Solved |
| 14 | Mercury DecideInception | 23 | 39 | $0.005157 | 22s | Solved |
| 15 | Decision-1Microsoft | 23 | 37 | $0.005141 | 23s | Solved |
| 16 | Clef FlashCloudflare | 23 | 39 | $0.007312 | 30s | Solved |
| 17 | ClefCloudflare | 24 | 38 | $0.0131 | 32s | Solved |
| 18 | GPT-6 Luna DecisionsOpenAI | 28 | 44 | $0.0296 | 21s | Solved |
| 19 | Classify-1ScaleDown | 34 | 48 | $0.0619 | 76s | Solved |