Score · relative 0–100
73.0
Rank
13
Status
Complete 3/3
Rank change
-2
Players generated
2026-09-22
Match evidence updated
2026-11-14

Reasoning settings compared

  1. XHighIntensive

    79.2 · rank 16 on the Intensive leaderboard

    Cost per program
    $0.207 · list-price estimate
    Working programs
    8 of 8
    API time
    Not recorded

    4.3 points above Medium, at 2.6× the cost

    • Higher score for $0.207 or less: Pareto 26.10 (no Overall rank) Reasoning controls unavailable · Baseline: 89.9 for $0.0296 (provider-reported)
    • Cheapest scoring at least as high: GPT-6.1 Terra None · Baseline: 79.3 for $0.0270 (list-price estimate) (one of 9 such settings)
  2. MediumBalanced

    74.9 · rank 12 on the Balanced leaderboard

    Cost per program
    $0.0783 · list-price estimate
    Working programs
    8 of 8
    API time
    Not recorded

    10.2 points above None, at 1.8× the cost

    • Higher score for $0.0783 or less: Pareto 26.10 (no Overall rank) Reasoning controls unavailable · Baseline: 89.9 for $0.0296 (provider-reported)
    • Cheapest scoring at least as high: GPT-6.1 Terra None · Baseline: 79.3 for $0.0270 (list-price estimate) (one of 7 such settings)
  3. NoneBaseline

    64.7 · rank 15 on the Baseline leaderboard

    Cost per program
    $0.0432 · list-price estimate
    Working programs
    8 of 8
    API time
    Not recorded
    • Higher score for $0.0432 or less: Pareto 26.10 (no Overall rank) Reasoning controls unavailable · Baseline: 89.9 for $0.0296 (provider-reported)
    • Cheapest scoring at least as high: Particle-1 Max · Intensive: 71.7 for $0.0256 (provider-reported) (one of 6 such settings)

Score and cost of every ranked setting

The chart needs JavaScript. The setting cards hold this model's results, and Charts compares every model.

Each setting is placed by its published score and its generation cost per player program, the mean over the game cells including repairs and failed attempts. Higher is better; further left costs less (logarithmic axis, with recorded $0 in its own lane). Filled marks are compared; hollow marks are not (the reason is in the table). The line marks the best value across ranked reasoning settings: no ranked setting with complete cost evidence scores at least as high for the same or less. It includes models without an Overall rank, so it can differ from the line on Charts. Costs mix provider-reported charges and list-price estimates; differences in score points are not tested for significance.
Show the numbers

The table needs JavaScript.

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

  • Go35.8
  • Chess67.1
  • Shogi82.0
  • Xiangqi66.9
  • Hex85.6
  • International Draughts79.2
  • Game of the Amazons80.6
  • Tumbleweed86.5

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 (79.2).

Across included settings, the highest game score is Tumbleweed (86.5); the lowest is Go (35.8). 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 attempt10.2979.139 / 32 / 529
GoBalanced1 working of 1 attempt39.11360.2137 / 173 / 290
GoBaseline1 working of 1 attempt58.01543.4327 / 17 / 256
ChessIntensive1 working of 1 attempt82.01774.1367 / 165 / 30
ChessBalanced1 working of 1 attempt68.11615.3239 / 260 / 63
ChessBaseline1 working of 1 attempt51.21472.0102 / 344 / 116
ShogiIntensive1 working of 1 attempt93.22130.2523 / 6 / 43
ShogiBalanced1 working of 1 attempt72.91656.5370 / 49 / 153
ShogiBaseline1 working of 1 attempt80.01765.3420 / 35 / 117
XiangqiIntensive1 working of 1 attempt87.21861.4466 / 59 / 53
XiangqiBalanced1 working of 1 attempt71.61654.7310 / 182 / 86
XiangqiBaseline1 working of 1 attempt41.71401.059 / 339 / 180
HexIntensive1 working of 1 attempt92.82396.3560 / 0 / 52
HexBalanced1 working of 1 attempt89.72260.0539 / 0 / 73
HexBaseline1 working of 1 attempt74.41789.1437 / 0 / 175
International DraughtsIntensive1 working of 1 attempt88.32146.1495 / 26 / 63
International DraughtsBalanced1 working of 1 attempt78.21923.4425 / 38 / 121
International DraughtsBaseline1 working of 1 attempt71.11788.5385 / 29 / 170
Game of the AmazonsIntensive1 working of 1 attempt92.92336.7564 / 0 / 46
Game of the AmazonsBalanced1 working of 1 attempt93.12352.4566 / 0 / 44
Game of the AmazonsBaseline1 working of 1 attempt55.81491.7317 / 0 / 293
TumbleweedIntensive1 working of 1 attempt87.32192.1527 / 0 / 87
TumbleweedBalanced1 working of 1 attempt86.62175.2523 / 0 / 91
TumbleweedBaseline1 working of 1 attempt85.62146.5516 / 0 / 98

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, an illegal move, or a timeout repeated by a later quiet replay, pinned on one program, also counts as that program's loss in its match record; other faults 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, all settings combined

$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