NONOGRAMS BENCHMARK · REASONING MEDIUM

GPT-6.1 Sol

Openai · released 2026-09-29 · route gpt-6.1-sol · Model profile · Chess results · Sudoku results · Mines results · FreeCell results · Starjar results · Nations Royale results · Wildhaven results · Hustle Sim results · Elemental Armory results · Micro Mouse results

Results

Score
6795%: 45 to 88 · 6 of 36 base puzzles so far
Puzzles solved
4 of 6
Cells that match the solution
78.2%
Rows and columns whose clue it satisfies
65.6%
Wrong cells / left cells unknown / no grid
0 / 2 / 0
Near misses (three cells or fewer wrong)
0
Average stated confidence
80%
Average confidence when it had not solved it
40%
Sure but wrong (90% or more, unsolved)
0
Calibration (Brier, lower is better)
0.107
API-equivalent cost per solved puzzle
$0.184
Tokens per puzzle (in / out)
19,696 / 10,762
Reasoning tokens per puzzle
10,073
Retries for an unreadable reply
0
API-equivalent cost per puzzle
$0.123
Seconds per puzzle
301.0
Replies cut off at the length limit
0.0%
Aborted on our side (not counted)
0

By tier

TierNeedsSolvedOutput tokensSeconds
5 by 5Line logic, a round or two1 of 11465.4
10 by 10Line logic, about 3 rounds1 of 12,34268.5
15 by 15Line logic, about 5 rounds1 of 18,474246.9
20 by 20Line logic, about 8 rounds1 of 117,473497.6
25 by 25Line logic, about 11 rounds0 of 130,687827.4
BeyondLine logic stalls; needs contradiction or search0 of 15,453160.4

Cells by the depth of logic they need

Each cell is tagged with the round of line logic that settles it. Beyond line logic means only contradiction or search does.

DepthCellsRight
First pass40399.0%
Rounds 2-361393.0%
Rounds 4-733278.0%
Round 8 on15913.8%
Beyond line logic931.1%

Every puzzle