Medium #02 sudoku race
32 clues · seed 2002 · 19 models · suite v1
19 AI decision models raced to solve this medium sudoku (32 clues), one digit at a time. Jev 1.14 by TypeSafe came first with 6 mistakes.
Results
| # | Model | Mistakes | Calls | Cost | Solve time | Status |
|---|
| 1 | Jev 1.14TypeSafe | 6 | 21 | $0.004360 | 6.1s | Solved |
| 2 | d1Liquid | 8 | 23 | $0.001235 | 9.6s | Solved |
| 3 | Span-02Respan | 8 | 21 | $0.003263 | 42s | Solved |
| 4 | GPT-6 Luna DecisionsOpenAI | 10 | 24 | $0.0138 | 9.8s | Solved |
| 5 | ClefCloudflare | 10 | 24 | $0.007552 | 18s | Solved |
| 6 | Kev 4BJared Palmer | 11 | 26 | $0.003106 | 15s | Solved |
| 7 | Drex v2.0Nace.AI | 11 | 24 | $0.004726 | 22s | Solved |
| 8 | Drex v1.5Nace.AIolder | 11 | 25 | $0.002799 | 23s | Solved |
| 9 | Decider Flash v1.2Perplexity | 11 | 24 | $0.004072 | 33s | Solved |
| 10 | d1 UltraLiquid | 12 | 24 | $0.002630 | 9.4s | Solved |
| 11 | Clef FlashCloudflare | 12 | 26 | $0.004720 | 20s | Solved |
| 12 | Decider v1.2Perplexity | 12 | 25 | $0.001727 | 21s | Solved |
| 13 | Mercury DecideInception | 14 | 27 | $0.003269 | 14s | Solved |
| 14 | Tev1 4B ExperimentalTogether | 14 | 27 | $0.0221 | 31s | Solved |
| 15 | Clef OmniCloudflare | 15 | 27 | $0.0264 | 9.7s | Solved |
| 16 | Decision-1Microsoft | 15 | 27 | $0.003445 | 16s | Solved |
| 17 | Classify-1ScaleDown | 15 | 29 | $0.0319 | 26s | Solved |
| 18 | Jev 1.13TypeSafeolder | 16 | 28 | $0.006043 | 7.7s | Solved |
| 19 | Solar Decide FlashUpstage | 16 | 31 | $0.0405 | 49s | Solved |