GPT-6.1 Sol
Openai · released 2026-09-29 · route gpt-6.1-sol · Model profile · Chess results · Sudoku results · FreeCell results · Hustle Sim results · Elemental Armory results · Micro Mouse results
Results
- Score
- 6795%: 36 to 98 · 3 of 24 base boards so far
- Boards won
- 2 of 3
- Safe cells cleared beyond the opening
- 88.9%
- Won / hit a mine / unfinished / unreadable
- 2 / 1 / 0 / 0
- Ended for changing nothing five turns running
- 0
- Reached the turn cap
- 0
- Flags left on safe cells
- 2 in 1 boards
- Illegal actions
- 0 of 453 (0.0%)
- Wasted actions (already open or flagged)
- 53 of 453 (11.7%)
- Unreadable replies
- 0
- Turns per board
- 8.3
- Requests per board
- 8.3
- API-equivalent cost per win
- $0.387
- Tokens per board (in / out)
- 159,035 / 11,980
- Reasoning tokens per board
- 8,177
- API-equivalent cost per board
- $0.258
- Seconds per board
- 255.9
- Replies cut off at the length limit
- 0.0%
- Aborted on our side (not counted)
- 0
By tier
| Tier | Board, mines | Won | Cleared | Turns | Output tokens | Seconds |
|---|---|---|---|---|---|---|
| Beginner | 9×9, 10 | 1 of 1 | 100% | 6.0 | 2,359 | 74.0 |
| Intermediate | 16×16, 40 | 0 of 1 | 67% | 4.0 | 7,245 | 147.6 |
| Expert | 30×16, 99 | 1 of 1 | 100% | 15.0 | 26,336 | 546.0 |
| Master | 30×24, 200 | 0 of 0 | n/a | n/a | n/a | n/a |
Cells by the technique that proves them
Each safe cell covered at the start is tagged with the simplest deduction that first proves it safe, given everything a perfect player could open before it.
| Technique | Cells | Opened |
|---|---|---|
| Cascade from an empty cell | 295 | 91.5% |
| One number | 273 | 88.6% |
| Two numbers together | 16 | 93.8% |
| The mine count | 4 | 100.0% |