DuelLabGameBench 2
Menu

Model results · Other

Space Bunny Alpha

Rank 55 of 66 in Overall Models. All three benchmark settings tested.

Score · relative 0–100
33.4
Rank
55
Status
Complete 3/3
Rank change
0
Players generated
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)36.8
  • Medium (Balanced group, tested and included)35.8
  • Low (Baseline group, tested and included)27.6

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

LowMediumHighXHighMax

Checked on 2026-09-30 · Provider documentation

How settings are grouped

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

Scores by game

  • Go1 of 3 failed37.7
  • Chess1 of 3 failed27.9
  • Shogi1 of 3 failed27.3
  • Xiangqi41.2
  • Hex34.1
  • International Draughts1 of 3 failed32.3
  • Game of the Amazons45.5
  • Tumbleweed1 of 3 failed21.4

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 (36.8).

Across included settings, the highest game score is Game of the Amazons (45.5); the lowest is Tumbleweed (21.4). 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
stealth/space-bunny-alpha
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
262144 (42 of 42 indexed attempts)

Generation evidence

  • Low: 6 contributing player programs across 6 games
  • Medium: 7 contributing player programs across 7 games
  • XHigh: 6 contributing player programs across 6 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 attempt63.81604.3241 / 154 / 121
GoBalanced1 working of 1 attempt49.41463.1197 / 94 / 225
ChessBalanced1 working of 1 attempt42.71415.38 / 378 / 94
ChessBaseline1 working of 1 attempt40.91401.33 / 371 / 106
ShogiBalanced1 working of 1 attempt45.81390.8156 / 102 / 236
ShogiBaseline1 working of 1 attempt36.01305.4102 / 117 / 275
XiangqiIntensive1 working of 1 attempt38.61386.639 / 291 / 168
XiangqiBalanced1 working of 1 attempt41.21406.731 / 332 / 135
XiangqiBaseline1 working of 1 attempt43.71426.645 / 329 / 124
HexIntensive1 working of 1 attempt45.71383.8234 / 0 / 296
HexBalanced1 working of 1 attempt13.2871.965 / 0 / 465
HexBaseline1 working of 1 attempt43.61357.2223 / 0 / 307
International DraughtsIntensive1 working of 1 attempt38.81249.6170 / 5 / 327
International DraughtsBalanced1 working of 1 attempt58.21549.5269 / 6 / 227
Game of the AmazonsIntensive1 working of 1 attempt74.41788.9389 / 0 / 141
Game of the AmazonsBalanced1 working of 1 attempt36.01271.9177 / 0 / 353
Game of the AmazonsBaseline1 working of 1 attempt26.21138.6126 / 0 / 404
TumbleweedIntensive1 working of 1 attempt33.41207.5120 / 92 / 326
TumbleweedBaseline1 working of 1 attempt30.71178.690 / 125 / 323

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

5 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: 13% / 62% / 25% · n 8Medium: 63% / 25% / 12% · n 8Low: 13% / 62% / 25% · n 8 All three benchmark settings testedMany programs needed repairMany programs failed

Generation cost

$0.00average estimated cost per game and reasoning setting

Median
$0.00
Range
$0.00–$0.00
Provider-reported total
$0.00
Cost data
24 combinations · 24 runs
Price source
Provider-reported
Price list
boardgame-list-prices-2026-09-08
Average output
14k tokens
Output range
2.3k–39k 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