Medium #04 sudoku race
32 clues · seed 2004 · 19 models · suite v1
19 AI decision models raced to solve this medium sudoku (32 clues), one digit at a time. d1 Ultra by Liquid came first with 6 mistakes.
Results
| # | Model | Mistakes | Calls | Cost | Solve time | Status |
|---|
| 1 | d1 UltraLiquid | 6 | 21 | $0.002366 | 7.7s | Solved |
| 2 | d1Liquid | 7 | 22 | $0.001197 | 10s | Solved |
| 3 | Decision-1Microsoft | 7 | 22 | $0.002654 | 12s | Solved |
| 4 | Span-02Respan | 7 | 21 | $0.003170 | 46s | Solved |
| 5 | Clef OmniCloudflare | 8 | 22 | $0.0208 | 7.4s | Solved |
| 6 | Drex v2.0Nace.AI | 8 | 23 | $0.004897 | 18s | Solved |
| 7 | Decider Flash v1.2Perplexity | 9 | 24 | $0.003893 | 32s | Solved |
| 8 | Tev1 4B ExperimentalTogether | 9 | 24 | $0.0180 | 33s | Solved |
| 9 | Jev 1.13TypeSafeolder | 10 | 24 | $0.005053 | 6.8s | Solved |
| 10 | Jev 1.14TypeSafe | 10 | 24 | $0.005265 | 7.5s | Solved |
| 11 | Decider v1.2Perplexity | 10 | 25 | $0.001829 | 64s | Solved |
| 12 | Kev 4BJared Palmer | 13 | 26 | $0.002981 | 16s | Solved |
| 13 | Clef FlashCloudflare | 13 | 26 | $0.005413 | 34s | Solved |
| 14 | Mercury DecideInception | 16 | 29 | $0.003552 | 15s | Solved |
| 15 | Solar Decide FlashUpstage | 16 | 30 | $0.0410 | 46s | Solved |
| 16 | Drex v1.5Nace.AIolder | 18 | 31 | $0.003786 | 35s | Solved |
| 17 | ClefCloudflare | 18 | 30 | $0.0295 | 59s | Solved |
| 18 | GPT-6 Luna DecisionsOpenAI | 19 | 30 | $0.0183 | 15s | Solved |
| 19 | Classify-1ScaleDown | 21 | 33 | $0.0350 | 30s | Solved |