Expert #01 sudoku race
23 clues · seed 4001 · 19 models · suite v1
19 AI decision models raced to solve this expert sudoku (23 clues), one digit at a time. d1 Ultra by Liquid came first with 10 mistakes.
Results
| # | Model | Mistakes | Calls | Cost | Solve time | Status |
|---|---|---|---|---|---|---|
| 1 | d1 UltraLiquid | 10 | 26 | $0.003166 | 21s | Solved |
| 2 | Span-02Respan | 15 | 31 | $0.005607 | 71s | Solved |
| 3 | Jev 1.13TypeSafeolder | 16 | 30 | $0.007172 | 6.5s | Solved |
| 4 | Drex v2.0Nace.AI | 18 | 32 | $0.007214 | 24s | Solved |
| 5 | Clef FlashCloudflare | 18 | 34 | $0.007400 | 27s | Solved |
| 6 | Clef OmniCloudflare | 20 | 34 | $0.0352 | 12s | Solved |
| 7 | d1Liquid | 21 | 34 | $0.001963 | 11s | Solved |
| 8 | Decision-1Microsoft | 21 | 33 | $0.004389 | 19s | Solved |
| 9 | Jev 1.14TypeSafe | 22 | 38 | $0.009587 | 11s | Solved |
| 10 | Kev 4BJared Palmer | 23 | 37 | $0.004996 | 26s | Solved |
| 11 | Drex v1.5Nace.AIolder | 24 | 39 | $0.005068 | 38s | Solved |
| 12 | Decider v1.2Perplexity | 24 | 40 | $0.003316 | 85s | Solved |
| 13 | Mercury DecideInception | 25 | 36 | $0.004601 | 21s | Solved |
| 14 | Decider Flash v1.2Perplexity | 26 | 40 | $0.008781 | 64s | Solved |
| 15 | GPT-6 Luna DecisionsOpenAI | 27 | 43 | $0.0290 | 20s | Solved |
| 16 | Solar Decide FlashUpstage | 29 | 43 | $0.0674 | 77s | Solved |
| 17 | Tev1 4B ExperimentalTogether | 30 | 43 | $0.0451 | 50s | Solved |
| 18 | Classify-1ScaleDown | 30 | 45 | $0.0552 | 52s | Solved |
| 19 | ClefCloudflare | 31 | 43 | $0.0151 | 33s | Solved |