Medium #03 sudoku race
32 clues · seed 2003 · 19 models · suite v1
19 AI decision models raced to solve this medium sudoku (32 clues), one digit at a time. Span-02 by Respan came first with 4 mistakes.
Results
| # | Model | Mistakes | Calls | Cost | Solve time | Status |
|---|
| 1 | Span-02Respan | 4 | 18 | $0.002449 | 40s | Solved |
| 2 | ClefCloudflare | 5 | 19 | $0.0149 | 37s | Solved |
| 3 | Clef OmniCloudflare | 7 | 22 | $0.0203 | 7.6s | Solved |
| 4 | Kev 4BJared Palmer | 7 | 22 | $0.002429 | 15s | Solved |
| 5 | Drex v2.0Nace.AI | 7 | 21 | $0.003922 | 19s | Solved |
| 6 | Jev 1.14TypeSafe | 8 | 21 | $0.004471 | 6.3s | Solved |
| 7 | d1Liquid | 9 | 23 | $0.001279 | 9.7s | Solved |
| 8 | Decider Flash v1.2Perplexity | 9 | 22 | $0.003641 | 30s | Solved |
| 9 | Clef FlashCloudflare | 11 | 24 | $0.004627 | 27s | Solved |
| 10 | d1 UltraLiquid | 12 | 24 | $0.002601 | 12s | Solved |
| 11 | Drex v1.5Nace.AIolder | 12 | 25 | $0.002932 | 26s | Solved |
| 12 | Tev1 4B ExperimentalTogether | 13 | 26 | $0.0185 | 27s | Solved |
| 13 | Solar Decide FlashUpstage | 13 | 26 | $0.0334 | 39s | Solved |
| 14 | Jev 1.13TypeSafeolder | 14 | 27 | $0.005952 | 6.4s | Solved |
| 15 | Mercury DecideInception | 14 | 27 | $0.003336 | 23s | Solved |
| 16 | Decider v1.2Perplexity | 14 | 27 | $0.002035 | 75s | Solved |
| 17 | Decision-1Microsoft | 15 | 29 | $0.003615 | 16s | Solved |
| 18 | Classify-1ScaleDown | 19 | 33 | $0.0336 | 29s | Solved |
| 19 | GPT-6 Luna DecisionsOpenAI | 22 | 33 | $0.0206 | 13s | Solved |