DuelLabGameBench 2
Menu

Model results · OpenAI

GPT-6 Sol

Rank 8 of 66 in Overall Models. All three benchmark settings tested.

Score · relative 0–100
74.7
Rank
8
Status
Complete 3/3
Rank change
0
Players generated
2026-09-22
Match evidence updated
2026-10-26
Results published
Compare in charts View player programs Back to leaderboard

Scores by reasoning setting

  • XHigh (Intensive group, tested and included)80.6
  • Medium (Balanced group, tested and included)76.4
  • None (Baseline group, tested and included)67.0

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

NoneMediumXHigh

Checked on 2026-09-22 · Provider documentation

How settings are grouped

  • Baseline: None — tested and included
  • Balanced: Medium — tested and included
  • Intensive: XHigh — tested and included

Scores by game

  • Go37.3
  • Chess68.7
  • Shogi83.9
  • Xiangqi68.6
  • Hex87.7
  • International Draughts81.8
  • Game of the Amazons82.0
  • Tumbleweed87.1

Each game counts every generation attempt, a failed one as 0 (“1 of 2 failed” marks games with failed attempts). Scores are relative within each game, across the included settings; they do not compare game difficulty.

What this result shows

Strongest included setting: XHigh (80.6).

Across included settings, the highest game score is Hex (87.7); the lowest is Go (37.3). Each game counts every generation attempt, a failed one as 0. These are relative scores within each game, not direct comparisons of difficulty.

Match evidence measures these retained programs. It does not establish how a fresh generation will perform. Independent-generation variation is not estimated in this release.

Test protocol and evidence limits
Model identifier
gpt-6-sol
Provider route (catalog)
openai
Prompt identity / profile
Not retained in this result set / Not retained in this result set
Prompt version
Not retained in this result set
Generation policy
Generation-quality admission policy (see methodology)
Requested output-token limits
65536 (25 of 25 indexed attempts)

Generation evidence

  • None: 8 contributing player programs across 8 games
  • Medium: 8 contributing player programs across 8 games
  • XHigh: 8 contributing player programs across 8 games

Counts describe contributing programs, not independent replications: repairs and resends are not new independent samples. Independent-generation lineage is not retained.

GameReasoning groupProgramsWorking-program strengthRaw ratingCombined record (W / D / L)
GoIntensive1 working of 1 attempt10.4990.034 / 29 / 453
GoBalanced1 working of 1 attempt39.81371.8114 / 163 / 239
GoBaseline1 working of 1 attempt61.81584.5300 / 16 / 200
ChessIntensive1 working of 1 attempt83.61806.7333 / 128 / 19
ChessBalanced1 working of 1 attempt69.51635.9217 / 218 / 45
ChessBaseline1 working of 1 attempt52.91494.397 / 297 / 86
ShogiIntensive1 working of 1 attempt94.42174.1462 / 4 / 28
ShogiBalanced1 working of 1 attempt75.11691.6336 / 39 / 119
ShogiBaseline1 working of 1 attempt82.31807.0378 / 33 / 83
XiangqiIntensive1 working of 1 attempt88.31884.8409 / 54 / 35
XiangqiBalanced1 working of 1 attempt73.61679.9279 / 160 / 59
XiangqiBaseline1 working of 1 attempt43.91428.256 / 309 / 133
HexIntensive1 working of 1 attempt93.82432.2497 / 0 / 33
HexBalanced1 working of 1 attempt91.62319.4484 / 0 / 46
HexBaseline1 working of 1 attempt77.91865.8405 / 0 / 125
International DraughtsIntensive1 working of 1 attempt90.22181.0435 / 25 / 42
International DraughtsBalanced1 working of 1 attempt81.51975.8381 / 37 / 84
International DraughtsBaseline1 working of 1 attempt73.51819.0334 / 43 / 125
Game of the AmazonsIntensive1 working of 1 attempt94.42399.3504 / 0 / 26
Game of the AmazonsBalanced1 working of 1 attempt94.02377.8502 / 0 / 28
Game of the AmazonsBaseline1 working of 1 attempt57.61544.9294 / 0 / 236
TumbleweedIntensive1 working of 1 attempt89.62144.7476 / 0 / 62
TumbleweedBalanced1 working of 1 attempt85.72033.2448 / 9 / 81
TumbleweedBaseline1 working of 1 attempt86.12044.3451 / 8 / 79

Each row covers all the model's programs in one game and setting. Strength and raw rating are attempt-weighted means; under them, each program's score and the lowest and highest rating describe the programs (not a confidence interval). The combined record adds up their matches: evidence volume, not strength.

Failures and budgets

0 model-code generation failures; 0 provider/infrastructure failures excluded from the generation denominator. Runtime player faults are separate: 0 recorded one-sided faults across contributing program rows. A crash or illegal move pinned on one program also counts as that program's loss in its match record; other faults, such as timeouts, are left out of rating evidence.

Repair/resend outcomes and available costs are included. Exact retry ceilings and execution budgets are not retained in this result set; see the methodology for the public policy. Do not infer a measured setting from a current provider catalog.

Player program results

XHigh: 100% / 0% / 0% · n 8Medium: 88% / 12% / 0% · n 8None: 100% / 0% / 0% · n 8 All three benchmark settings tested

Generation cost

$0.11average estimated cost per game and reasoning setting

Median
$0.08
Range
$0.03–$0.23
Estimated total for recorded runs
$2.63
Cost data
24 combinations · 24 runs
Price source
Standard list-price estimate
Price list
boardgame-list-prices-2026-09-08
Average output
8.9k tokens
Output range
1.5k–21k tokens
Runs with output-token data
24
How cost is measured

Comparison cost gives equal weight to each model, game, and reasoning-setting combination. Recorded generation attempts include repairs and resends when cost evidence is available; runtime compute and service operation are excluded. Cost and output-token counts use separate telemetry denominators. A list-price estimate is not actual expenditure; mixed evidence is not a uniform standard-price comparison.

Test protocol

  • Combines this model's tested reasoning settings
  • Player-program generation; retained protocol details are under “Test protocol and evidence limits” above