FREECELL BENCHMARK · REASONING MEDIUM

GPT-6.1 Sol

Openai · released 2026-09-29 · route gpt-6.1-sol · Model profile · Chess results · Sudoku results · Elemental Armory results

Results

Score
2095%: 0 to 44 · 5 of 30 base games so far
Deals won
1 of 5
Cards home at the end (of 52)
14.0
How the games ended
won 1, stalled 1, resigned 3
Refused moves per game
3.60
Refused moves of moves sent
3.8%
Moves not in the notation
0
Moves played per game
53.2
Moves per won game
121.0
Replies per game
8.0
Moves sent per reply
11.9
Retries for a reply with no moves tag
0
Plan: won in one reply
0 of 1
Plan: cards home / moves played
0.0 / 0.0
API-equivalent cost per win
$1.50
Requests per game
6.8
Tokens per game (in / out)
146,976 / 13,974
Reasoning tokens per game
12,583
API-equivalent cost per game
$0.267
Seconds per game
523.5
Replies cut off at the length limit
0.0%
Aborted on our side (not counted)
2

By tier

TierFree cellsWonCards homeOutput tokensSecondsCost
Easy40 of 110.029,2971,110.5$0.561
Four cells41 of 152.037,3591,460.5$0.709
Three cells30 of 13.01,77179.2$0.040
Two cells20 of 14.03,542129.8$0.092
Beyond10 of 11.03,855137.9$0.095

Every game