DuelLabGameBench 2
Menu

Model results · xAI

Grok 4.7

Rank 13 of 66 in Overall Models. All three benchmark settings tested.

Score · relative 0–100
65.0
Rank
13
Status
Complete 3/3
Rank change
0
Players generated
2026-09-23 – 2026-09-30
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)73.2
  • Medium (Balanced group, tested and included)73.4
  • Low (Baseline group, tested and included)48.4

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

LowMediumHighXHigh

Checked on 2026-09-22 · Provider documentation

How settings are grouped

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

Scores by game

  • Go55.6
  • Chess74.4
  • Shogi1 of 3 failed53.6
  • Xiangqi1 of 3 failed45.2
  • Hex76.4
  • International Draughts1 of 3 failed57.7
  • Game of the Amazons70.1
  • Tumbleweed87.0

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: Medium (73.4).

Across included settings, the highest game score is Tumbleweed (87.0); the lowest is Xiangqi (45.2). 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
x-ai/grok-4.7
Provider route (catalog)
openrouter
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
450000 (29 of 29 indexed attempts)

Generation evidence

  • Low: 7 contributing player programs across 7 games
  • Medium: 7 contributing player programs across 7 games
  • XHigh: 7 contributing player programs across 7 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 attempt59.41560.2289 / 13 / 214
GoBalanced1 working of 1 attempt80.01798.6386 / 34 / 96
GoBaseline1 working of 1 attempt27.51244.356 / 155 / 305
ChessIntensive1 working of 1 attempt89.11908.1400 / 50 / 30
ChessBalanced1 working of 1 attempt81.21770.2331 / 107 / 42
ChessBaseline1 working of 1 attempt52.91494.379 / 333 / 68
ShogiIntensive1 working of 1 attempt88.01937.3385 / 84 / 25
ShogiBalanced1 working of 1 attempt72.71659.0328 / 29 / 137
XiangqiBalanced1 working of 1 attempt92.31980.5436 / 44 / 18
XiangqiBaseline1 working of 1 attempt43.21422.6141 / 132 / 225
HexIntensive1 working of 1 attempt93.42413.3495 / 0 / 35
HexBalanced1 working of 1 attempt93.12395.1493 / 0 / 37
HexBaseline1 working of 1 attempt42.61345.0218 / 0 / 312
International DraughtsIntensive1 working of 1 attempt90.22181.0441 / 13 / 48
International DraughtsBaseline1 working of 1 attempt82.82002.4388 / 37 / 77
Game of the AmazonsIntensive1 working of 1 attempt78.41861.0412 / 0 / 118
Game of the AmazonsBalanced1 working of 1 attempt76.31822.2400 / 0 / 130
Game of the AmazonsBaseline1 working of 1 attempt55.51516.9282 / 0 / 248
TumbleweedIntensive1 working of 1 attempt86.92066.9460 / 0 / 78
TumbleweedBalanced1 working of 1 attempt91.22199.2486 / 0 / 52
TumbleweedBaseline1 working of 1 attempt83.01963.6436 / 0 / 102

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

3 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: 75% / 13% / 12% · n 8Medium: 88% / 0% / 12% · n 8Low: 75% / 13% / 12% · n 8 All three benchmark settings tested

Generation cost

$0.42average estimated cost per game and reasoning setting

Median
$0.38
Range
$0.05–$1.22
Provider-reported total
$10.09
Cost data
24 combinations · 24 runs
Price source
Provider-reported
Price list
boardgame-list-prices-2026-09-08
Average output
68k tokens
Output range
8.4k–195k 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