DuelLabGameBench 2
Menu

Model results · OpenAI

GPT-6 Astra

Rank 1 of 66 in Overall Models. All three benchmark settings tested.

Score · relative 0–100
89.7
Rank
1
Status
Complete 3/3
Rank change
0
Players generated
2026-09-05
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)94.4
  • Medium (Balanced group, tested and included)89.6
  • Low (Baseline group, tested and included)85.1

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

LowMediumHighXHighMax

Checked on 2026-09-05 · Provider documentation

How settings are grouped

  • Baseline: Low — tested and included
  • Balanced: Medium — tested and included
  • Intensive: XHigh — tested and included

Scores by game

  • Go89.1
  • Chess83.0
  • Shogi89.3
  • Xiangqi89.1
  • Hex95.4
  • International Draughts86.9
  • Game of the Amazons96.4
  • Tumbleweed88.7

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 (94.4).

Across included settings, the highest game score is Game of the Amazons (96.4); the lowest is Chess (83.0). 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-astra
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
Not retained (0 of 24 indexed attempts)

Generation evidence

  • Low: 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 attempt97.32279.0501 / 0 / 15
GoBalanced1 working of 1 attempt76.91755.5368 / 37 / 111
GoBaseline1 working of 1 attempt93.22076.1464 / 24 / 28
ChessIntensive1 working of 1 attempt95.32104.4445 / 25 / 10
ChessBalanced1 working of 1 attempt81.01767.5304 / 159 / 17
ChessBaseline1 working of 1 attempt72.61667.4231 / 221 / 28
ShogiIntensive1 working of 1 attempt97.72409.5479 / 9 / 6
ShogiBalanced1 working of 1 attempt94.82197.0464 / 5 / 25
ShogiBaseline1 working of 1 attempt75.51696.8277 / 161 / 56
XiangqiIntensive1 working of 1 attempt92.61988.4443 / 33 / 22
XiangqiBalanced1 working of 1 attempt91.41955.6431 / 44 / 23
XiangqiBaseline1 working of 1 attempt83.41801.3368 / 84 / 46
HexIntensive1 working of 1 attempt98.92940.5527 / 0 / 3
HexBalanced1 working of 1 attempt93.12395.1493 / 0 / 37
HexBaseline1 working of 1 attempt94.32461.9500 / 0 / 30
International DraughtsIntensive1 working of 1 attempt87.02096.3415 / 29 / 58
International DraughtsBalanced1 working of 1 attempt88.62136.9427 / 23 / 52
International DraughtsBaseline1 working of 1 attempt85.02050.0406 / 25 / 71
Game of the AmazonsIntensive1 working of 1 attempt97.82659.0522 / 0 / 8
Game of the AmazonsBalanced1 working of 1 attempt96.72552.9516 / 0 / 14
Game of the AmazonsBaseline1 working of 1 attempt94.62410.4505 / 0 / 25
TumbleweedIntensive1 working of 1 attempt88.92124.3472 / 0 / 66
TumbleweedBalanced1 working of 1 attempt94.72349.0508 / 0 / 30
TumbleweedBaseline1 working of 1 attempt82.51951.5433 / 0 / 105

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: 100% / 0% / 0% · n 8Low: 100% / 0% / 0% · n 8 All three benchmark settings tested

Generation cost

$0.65average estimated cost per game and reasoning setting

Median
$0.41
Range
$0.21–$1.48
Estimated total for recorded runs
$15.61
Cost data
24 combinations · 24 runs
Price source
Standard list-price estimate
Price list
boardgame-list-prices-2026-09-05
Average output
11k tokens
Output range
2.3k–28k 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