Hard #04 sudoku race
27 clues · seed 3004 · 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.
Results
| # | Model | Mistakes | Calls | Cost | Solve time | Status |
|---|
| 1 | Span-02Respan | 7 | 23 | $0.003620 | 51s | Solved |
| 2 | Jev 1.13TypeSafeolder | 11 | 27 | $0.006257 | 8.7s | Solved |
| 3 | d1 UltraLiquid | 12 | 25 | $0.002943 | 8.9s | Solved |
| 4 | Decision-1Microsoft | 13 | 28 | $0.003580 | 16s | Solved |
| 5 | Jev 1.14TypeSafe | 14 | 27 | $0.005845 | 8.3s | Solved |
| 6 | Clef FlashCloudflare | 14 | 29 | $0.005803 | 22s | Solved |
| 7 | Decider Flash v1.2Perplexity | 14 | 29 | $0.005766 | 46s | Solved |
| 8 | d1Liquid | 15 | 29 | $0.001705 | 9.5s | Solved |
| 9 | Drex v1.5Nace.AIolder | 15 | 30 | $0.003608 | 19s | Solved |
| 10 | Drex v2.0Nace.AI | 15 | 29 | $0.006563 | 21s | Solved |
| 11 | Clef OmniCloudflare | 17 | 31 | $0.0318 | 14s | Solved |
| 12 | ClefCloudflare | 17 | 31 | $0.0105 | 24s | Solved |
| 13 | Tev1 4B ExperimentalTogether | 17 | 32 | $0.0305 | 43s | Solved |
| 14 | GPT-6 Luna DecisionsOpenAI | 22 | 37 | $0.0239 | 15s | Solved |
| 15 | Decider v1.2Perplexity | 22 | 36 | $0.002955 | 41s | Solved |
| 16 | Solar Decide FlashUpstage | 23 | 35 | $0.0522 | 57s | Solved |
| 17 | Mercury DecideInception | 25 | 36 | $0.004828 | 24s | Solved |
| 18 | Kev 4BJared Palmer | 27 | 39 | $0.005388 | 89s | Solved |
| 19 | Classify-1ScaleDown | 29 | 38 | $0.0445 | 32s | Solved |