DuelLabGameBench 2
Menu

Model results · xAI

Grok 4.6

Rank 16 of 66 in Overall Models. All three benchmark settings tested.

Score · relative 0–100
61.1
Rank
16
Status
Complete 3/3
Rank change
0
Players generated
2026-09-03
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)66.4
  • Medium (Balanced group, tested and included)71.4
  • Low (Baseline group, tested and included)45.4

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

LowMediumHighXHigh

Checked on 2026-09-03 · Provider documentation

How settings are grouped

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

Scores by game

  • Go59.9
  • Chess60.6
  • Shogi54.6
  • Xiangqi56.2
  • Hex73.0
  • International Draughts53.3
  • Game of the Amazons70.1
  • Tumbleweed60.6

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 (71.4).

Across included settings, the highest game score is Hex (73.0); the lowest is International Draughts (53.3). 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
x-ai/grok-4.6
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
Not retained (0 of 27 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 attempt50.61474.3124 / 252 / 140
GoBalanced1 working of 1 attempt62.51591.4246 / 131 / 139
GoBaseline1 working of 1 attempt66.81635.9303 / 61 / 152
ChessIntensive1 working of 1 attempt83.31801.2361 / 67 / 51
ChessBalanced1 working of 1 attempt54.61507.4103 / 301 / 76
ChessBaseline1 working of 1 attempt44.11426.014 / 379 / 87
ShogiIntensive1 working of 1 attempt51.71443.1185 / 102 / 207
ShogiBalanced1 working of 1 attempt67.41596.3268 / 94 / 132
ShogiBaseline1 working of 1 attempt44.71381.85 / 394 / 95
XiangqiIntensive1 working of 1 attempt60.21556.2155 / 272 / 71
XiangqiBalanced1 working of 1 attempt65.41600.5193 / 248 / 57
XiangqiBaseline1 working of 1 attempt42.91420.348 / 315 / 135
HexIntensive1 working of 1 attempt85.02059.6445 / 0 / 85
HexBalanced1 working of 1 attempt82.71989.7432 / 0 / 98
HexBaseline1 working of 1 attempt51.31453.0263 / 0 / 267
International DraughtsIntensive1 working of 1 attempt66.31687.7301 / 30 / 171
International DraughtsBalanced1 working of 1 attempt79.71938.7383 / 13 / 106
International DraughtsBaseline1 working of 1 attempt13.7848.454 / 7 / 441
Game of the AmazonsIntensive1 working of 1 attempt76.21819.1399 / 0 / 131
Game of the AmazonsBalanced1 working of 1 attempt76.51825.4401 / 0 / 129
Game of the AmazonsBaseline1 working of 1 attempt57.61544.9294 / 0 / 236
TumbleweedIntensive1 working of 1 attempt57.61487.2236 / 109 / 193
TumbleweedBalanced1 working of 1 attempt82.71955.5434 / 0 / 104
TumbleweedBaseline1 working of 1 attempt41.71296.4101 / 214 / 223

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: 88% / 12% / 0% · n 8Medium: 75% / 25% / 0% · n 8Low: 100% / 0% / 0% · n 8 All three benchmark settings tested

Generation cost

$0.13average estimated cost per game and reasoning setting

Median
$0.12
Range
$0.03–$0.28
Provider-reported total
$3.15
Cost data
24 combinations · 24 runs
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
19k tokens
Output range
1.9k–44k 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