GPT-6.1 Sol
Openai · released 2026-09-29 · route gpt-6.1-sol · Model profile · Chess results
Results
- Score
- 8395%: 72 to 94
- Grids solved
- 35 of 42
- Blank cells filled correctly
- 94.1%
- Wrong cells / empty cells / changed a given / no grid
- 7 / 0 / 0 / 0
- Broke the rules (complete grid repeating a digit)
- 7
- Near misses (three cells or fewer wrong)
- 0
- Average stated confidence
- 95%
- Average confidence when it had not solved it
- 71%
- Sure but wrong (90% or more, unsolved)
- 5
- Calibration (Brier, lower is better)
- 0.119
- API-equivalent cost per grid
- $0.112
- API-equivalent cost per solved grid
- $0.134
- Seconds per grid
- 195
- Tokens per grid (in / out)
- 27,423 / 8,723
- Reasoning tokens per grid
- 8,345
- Retries for an unreadable reply
- 0
- Aborted on our side (not counted)
- 0
By tier
| Tier | Needs | Solved | Output tokens | Seconds |
|---|---|---|---|---|
| Cozy | Singles only | 6 of 6 | 3,938 | 95 |
| Gentle | Scanning | 6 of 6 | 6,007 | 136 |
| Steady | Locked candidates | 4 of 6 | 8,432 | 196 |
| Tricky | Hidden pairs and triples | 5 of 6 | 8,794 | 196 |
| Devious | Wings and fish | 5 of 6 | 6,595 | 153 |
| Expert | Deep wings and fish | 4 of 6 | 9,598 | 221 |
| Beyond | No human technique finishes it | 5 of 6 | 17,701 | 368 |
Cells by the technique they needed
Each blank cell is tagged with the simplest technique that fills it, given everything a solver could fill before it.
| Technique | Cells | Filled correctly |
|---|---|---|
| Last free cell | 432 | 100.0% |
| Scanning | 674 | 99.9% |
| Locked candidates | 274 | 90.5% |
| Hidden pairs and triples | 258 | 91.1% |
| Wings and fish | 165 | 93.9% |
| Deep wings and fish | 181 | 76.8% |
| Search | 249 | 87.9% |
Every answer
Cozy #1Solved 50 of 50 cells100% sure · 2,405 tokens · $0.035Cozy #2Solved 48 of 48 cells100% sure · 1,872 tokens · $0.041Cozy #3Solved 49 of 49 cells100% sure · 2,536 tokens · $0.047Cozy #4Solved 50 of 50 cells100% sure · 9,181 tokens · $0.126Cozy #5Solved 49 of 49 cells100% sure · 5,912 tokens · $0.089Cozy #6Solved 39 of 39 cells100% sure · 1,719 tokens · $0.028Gentle #1Solved 56 of 56 cells100% sure · 5,547 tokens · $0.085Gentle #2Solved 51 of 51 cells100% sure · 9,006 tokens · $0.126Gentle #3Solved 52 of 52 cells100% sure · 6,051 tokens · $0.083Gentle #4Solved 51 of 51 cells100% sure · 2,728 tokens · $0.040Gentle #5Solved 56 of 56 cells100% sure · 9,542 tokens · $0.118Gentle #6Solved 52 of 52 cells100% sure · 3,167 tokens · $0.054Steady #1Wrong cells 38 of 53 cells100% sure · 10,720 tokens · $0.129Steady #2Wrong cells 41 of 53 cells100% sure · 9,115 tokens · $0.109Steady #3Solved 49 of 49 cells100% sure · 8,780 tokens · $0.110Steady #4Solved 54 of 54 cells100% sure · 10,975 tokens · $0.138Steady #5Solved 53 of 53 cells100% sure · 4,025 tokens · $0.049Steady #6Solved 54 of 54 cells100% sure · 6,975 tokens · $0.092Tricky #1Solved 55 of 55 cells100% sure · 7,097 tokens · $0.082Tricky #2Wrong cells 34 of 57 cells100% sure · 6,585 tokens · $0.101Tricky #3Solved 57 of 57 cells100% sure · 12,068 tokens · $0.142Tricky #4Solved 54 of 54 cells100% sure · 12,103 tokens · $0.143Tricky #5Solved 55 of 55 cells100% sure · 4,780 tokens · $0.075Tricky #6Solved 56 of 56 cells100% sure · 10,134 tokens · $0.114Devious #1Solved 55 of 55 cells100% sure · 18,426 tokens · $0.211Devious #2Wrong cells 45 of 55 cells100% sure · 3,459 tokens · $0.047Devious #3Solved 49 of 49 cells100% sure · 3,912 tokens · $0.083Devious #4Solved 40 of 40 cells100% sure · 2,672 tokens · $0.037Devious #5Solved 47 of 47 cells100% sure · 6,988 tokens · $0.080Devious #6Solved 54 of 54 cells100% sure · 4,115 tokens · $0.063Expert #1Wrong cells 39 of 58 cells100% sure · 10,374 tokens · $0.126Expert #2Solved 53 of 53 cells100% sure · 4,874 tokens · $0.059Expert #3Solved 54 of 54 cells100% sure · 8,647 tokens · $0.109Expert #4Solved 57 of 57 cells100% sure · 8,110 tokens · $0.086Expert #5Wrong cells 35 of 58 cells0% sure · 19,902 tokens · $0.248Expert #6Solved 54 of 54 cells100% sure · 5,679 tokens · $0.062Beyond #1Solved 60 of 60 cells100% sure · 6,897 tokens · $0.112Beyond #2Wrong cells 27 of 57 cells0% sure · 47,554 tokens · $0.567Beyond #3Solved 56 of 56 cells100% sure · 16,873 tokens · $0.177Beyond #4Solved 57 of 57 cells100% sure · 17,190 tokens · $0.242Beyond #5Solved 59 of 59 cells100% sure · 9,025 tokens · $0.101Beyond #6Solved 57 of 57 cells100% sure · 8,666 tokens · $0.134