Expert #05 sudoku race
23 clues · seed 4005 · 19 models · suite v1
19 AI decision models raced to solve this expert sudoku (23 clues), one digit at a time. Span-02 by Respan came first with 11 mistakes.
Results
| # | Model | Mistakes | Calls | Cost | Solve time | Status |
|---|---|---|---|---|---|---|
| 1 | Span-02Respan | 11 | 28 | $0.005082 | 63s | Solved |
| 2 | d1 UltraLiquid | 12 | 27 | $0.003360 | 11s | Solved |
| 3 | Kev 4BJared Palmer | 13 | 27 | $0.003380 | 17s | Solved |
| 4 | ClefCloudflare | 13 | 28 | $0.007962 | 22s | Solved |
| 5 | Clef OmniCloudflare | 14 | 30 | $0.0299 | 15s | Solved |
| 6 | Clef FlashCloudflare | 18 | 34 | $0.006226 | 21s | Solved |
| 7 | d1Liquid | 20 | 32 | $0.001933 | 11s | Solved |
| 8 | Jev 1.14TypeSafe | 21 | 34 | $0.008270 | 11s | Solved |
| 9 | Drex v2.0Nace.AI | 23 | 38 | $0.008372 | 26s | Solved |
| 10 | Decider Flash v1.2Perplexity | 23 | 37 | $0.007796 | 63s | Solved |
| 11 | Decider v1.2Perplexity | 23 | 37 | $0.003133 | 88s | Solved |
| 12 | Decision-1Microsoft | 25 | 38 | $0.005291 | 25s | Solved |
| 13 | Jev 1.13TypeSafeolder | 27 | 41 | $0.0100 | 11s | Solved |
| 14 | GPT-6 Luna DecisionsOpenAI | 27 | 43 | $0.0288 | 23s | Solved |
| 15 | Classify-1ScaleDown | 29 | 42 | $0.0505 | 29s | Solved |
| 16 | Tev1 4B ExperimentalTogether | 29 | 41 | $0.0416 | 46s | Solved |
| 17 | Mercury DecideInception | 32 | 45 | $0.006221 | 26s | Solved |
| 18 | Solar Decide FlashUpstage | 32 | 46 | $0.0745 | 91s | Solved |
| 19 | Drex v1.5Nace.AIolder | 36 | 50 | $0.006730 | 44s | Solved |