MINES BENCHMARK · REASONING MEDIUM

GPT-6 Luna

Openai · released 2026-09-22 · route gpt-6-luna · Model profile · Chess results · Sudoku results · FreeCell results · Nations Royale results · Hustle Sim results · Elemental Armory results · Micro Mouse results

Results

Score
095%: 0 to 27 · 4 of 24 base boards so far
Boards won
0 of 4
Safe cells cleared beyond the opening
0.8%
Won / hit a mine / unfinished / unreadable
0 / 2 / 1 / 1
Ended for changing nothing five turns running
1
Reached the turn cap
0
Flags left on safe cells
1 in 1 boards
Illegal actions
0 of 20 (0.0%)
Wasted actions (already open or flagged)
10 of 20 (50.0%)
Unreadable replies
5
Turns per board
2.8
Requests per board
3.8
API-equivalent cost per win
n/a
Tokens per board (in / out)
44,282 / 3,201
Reasoning tokens per board
3,116
API-equivalent cost per board
$0.0042
Seconds per board
38.8
Replies cut off at the length limit
0.0%
Aborted on our side (not counted)
0

By tier

TierBoard, minesWonClearedTurnsOutput tokensSeconds
Beginner9×9, 100 of 13%3.04,15546.2
Intermediate16×16, 400 of 10%1.02,65626.3
Expert30×16, 990 of 10%5.03,98652.2
Master30×24, 2000 of 10%2.02,00730.3

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.

TechniqueCellsOpened
Cascade from an empty cell4580.0%
One number5690.4%
Two numbers together680.0%
The mine count40.0%

Every board