Easy #04 sudoku race
40 clues · seed 1004 · 19 models · suite v1
19 AI decision models raced to solve this easy sudoku (40 clues), one digit at a time. Span-02 by Respan came first with 1 mistake.
Results
| # | Model | Mistakes | Calls | Cost | Solve time | Status |
|---|
| 1 | Span-02Respan | 1 | 14 | $0.001690 | 30s | Solved |
| 2 | Jev 1.14TypeSafe | 3 | 16 | $0.002916 | 4.6s | Solved |
| 3 | ClefCloudflare | 3 | 16 | $0.003544 | 10s | Solved |
| 4 | Jev 1.13TypeSafeolder | 4 | 16 | $0.002947 | 4.7s | Solved |
| 5 | Drex v2.0Nace.AI | 4 | 16 | $0.002503 | 12s | Solved |
| 6 | Clef FlashCloudflare | 4 | 18 | $0.002765 | 13s | Solved |
| 7 | d1 UltraLiquid | 5 | 18 | $0.001786 | 6.3s | Solved |
| 8 | Decision-1Microsoft | 5 | 18 | $0.001960 | 9.0s | Solved |
| 9 | Clef OmniCloudflare | 6 | 19 | $0.0146 | 6.2s | Solved |
| 10 | Mercury DecideInception | 6 | 17 | $0.001681 | 8.0s | Solved |
| 11 | d1Liquid | 7 | 18 | $0.000881 | 10s | Solved |
| 12 | Kev 4BJared Palmer | 7 | 19 | $0.001887 | 12s | Solved |
| 13 | Classify-1ScaleDown | 7 | 20 | $0.0164 | 22s | Solved |
| 14 | Drex v1.5Nace.AIolder | 8 | 19 | $0.001916 | 16s | Solved |
| 15 | Decider Flash v1.2Perplexity | 8 | 18 | $0.002809 | 25s | Solved |
| 16 | GPT-6 Luna DecisionsOpenAI | 9 | 21 | $0.0105 | 8.3s | Solved |
| 17 | Decider v1.2Perplexity | 10 | 22 | $0.001488 | 18s | Solved |
| 18 | Tev1 4B ExperimentalTogether | 10 | 20 | $0.0140 | 20s | Solved |
| 19 | Solar Decide FlashUpstage | 10 | 22 | $0.0272 | 32s | Solved |