GPT-6 Sol
Openai · released 2026-09-22 · route gpt-6-sol · Model profile · Chess results
Results
- Score
- 9095%: 80 to 100
- Grids solved
- 38 of 42
- Blank cells filled correctly
- 93.7%
- Wrong cells / empty cells / changed a given / no grid
- 2 / 2 / 0 / 0
- Broke the rules (complete grid repeating a digit)
- 2
- Near misses (three cells or fewer wrong)
- 0
- Average stated confidence
- 95%
- Average confidence when it had not solved it
- 50%
- Sure but wrong (90% or more, unsolved)
- 2
- Calibration (Brier, lower is better)
- 0.048
- API-equivalent cost per grid
- $0.149
- API-equivalent cost per solved grid
- $0.165
- Seconds per grid
- 142
- Tokens per grid (in / out)
- 30,983 / 12,925
- Reasoning tokens per grid
- 12,465
- Retries for an unreadable reply
- 1
- Aborted on our side (not counted)
- 0
By tier
| Tier | Needs | Solved | Output tokens | Seconds |
|---|---|---|---|---|
| Cozy | Singles only | 6 of 6 | 4,229 | 50 |
| Gentle | Scanning | 6 of 6 | 9,606 | 104 |
| Steady | Locked candidates | 6 of 6 | 11,675 | 124 |
| Tricky | Hidden pairs and triples | 6 of 6 | 15,702 | 172 |
| Devious | Wings and fish | 4 of 6 | 7,839 | 88 |
| Expert | Deep wings and fish | 6 of 6 | 12,594 | 136 |
| Beyond | No human technique finishes it | 4 of 6 | 28,828 | 317 |
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 | 99.8% |
| Scanning | 674 | 99.1% |
| Locked candidates | 274 | 94.5% |
| Hidden pairs and triples | 258 | 100.0% |
| Wings and fish | 165 | 75.1% |
| Deep wings and fish | 181 | 100.0% |
| Search | 249 | 69.1% |
Every answer
Cozy #1Solved 50 of 50 cells100% sure · 4,474 tokens · $0.057Cozy #2Solved 48 of 48 cells100% sure · 4,261 tokens · $0.050Cozy #3Solved 49 of 49 cells100% sure · 4,952 tokens · $0.073Cozy #4Solved 50 of 50 cells100% sure · 4,319 tokens · $0.050Cozy #5Solved 49 of 49 cells100% sure · 4,261 tokens · $0.066Cozy #6Solved 39 of 39 cells100% sure · 3,109 tokens · $0.038Gentle #1Solved 56 of 56 cells100% sure · 9,882 tokens · $0.125Gentle #2Solved 51 of 51 cells100% sure · 6,949 tokens · $0.077Gentle #3Solved 52 of 52 cells100% sure · 15,272 tokens · $0.180Gentle #4Solved 51 of 51 cells100% sure · 7,232 tokens · $0.080Gentle #5Solved 56 of 56 cells100% sure · 11,127 tokens · $0.118Gentle #6Solved 52 of 52 cells100% sure · 7,171 tokens · $0.079Steady #1Solved 53 of 53 cells100% sure · 8,168 tokens · $0.099Steady #2Solved 53 of 53 cells100% sure · 7,645 tokens · $0.084Steady #3Solved 49 of 49 cells100% sure · 6,259 tokens · $0.070Steady #4Solved 54 of 54 cells100% sure · 23,165 tokens · $0.269Steady #5Solved 53 of 53 cells100% sure · 13,807 tokens · $0.167Steady #6Solved 54 of 54 cells100% sure · 11,008 tokens · $0.128Tricky #1Solved 55 of 55 cells100% sure · 11,877 tokens · $0.145Tricky #2Solved 57 of 57 cells100% sure · 15,483 tokens · $0.202Tricky #3Solved 57 of 57 cells100% sure · 18,684 tokens · $0.227Tricky #4Solved 54 of 54 cells100% sure · 12,299 tokens · $0.151Tricky #5Solved 55 of 55 cells100% sure · 9,873 tokens · $0.109Tricky #6Solved 56 of 56 cells100% sure · 25,999 tokens · $0.315Devious #1Solved 55 of 55 cells100% sure · 9,006 tokens · $0.097Devious #2Solved 55 of 55 cells100% sure · 11,309 tokens · $0.126Devious #3Wrong cells 29 of 49 cells100% sure · 7,701 tokens · $0.084Devious #4Solved 40 of 40 cells100% sure · 4,302 tokens · $0.052Devious #5Solved 47 of 47 cells100% sure · 5,556 tokens · $0.063Devious #6Wrong cells 33 of 54 cells100% sure · 9,159 tokens · $0.115Expert #1Solved 58 of 58 cells100% sure · 28,442 tokens · $0.299Expert #2Solved 53 of 53 cells100% sure · 6,360 tokens · $0.089Expert #3Solved 54 of 54 cells100% sure · 8,595 tokens · $0.093Expert #4Solved 57 of 57 cells100% sure · 9,575 tokens · $0.106Expert #5Solved 58 of 58 cells100% sure · 11,886 tokens · $0.126Expert #6Solved 54 of 54 cells100% sure · 10,705 tokens · $0.126Beyond #1Solved 60 of 60 cells100% sure · 23,873 tokens · $0.254Beyond #2Solved 57 of 57 cells100% sure · 16,181 tokens · $0.174Beyond #3Solved 56 of 56 cells100% sure · 26,854 tokens · $0.339Beyond #4Solved 57 of 57 cells100% sure · 18,065 tokens · $0.211Beyond #5Left cells empty 17 of 59 cells0% sure · 17,776 tokens · $0.196Beyond #6Left cells empty 0 of 57 cells0% sure · 70,219 tokens · $0.747