DuelLabGameBench 2
Menu

Model results · Meta

Muse Glimmer 30B

Rank 58 of 66 in Overall Models. All three benchmark settings tested.

Score · relative 0–100
30.3
Rank
58
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)35.9
  • Medium (Balanced group, tested and included)31.4
  • Low (Baseline group, tested and included)23.7

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

  • Go30.0
  • Chess1 of 3 failed28.8
  • Shogi40.7
  • Xiangqi46.1
  • Hex23.0
  • International Draughts2 of 3 failed5.7
  • Game of the Amazons37.5
  • Tumbleweed30.7

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 (35.9).

Across included settings, the highest game score is Xiangqi (46.1); the lowest is International Draughts (5.7). 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
meta/muse-glimmer-30b
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 34 indexed attempts)

Generation evidence

  • Low: 6 contributing player programs across 6 games
  • Medium: 8 contributing player programs across 8 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 attempt31.71289.987 / 135 / 293
GoBalanced1 working of 1 attempt22.01178.361 / 90 / 365
GoBaseline1 working of 1 attempt36.31336.7130 / 95 / 291
ChessIntensive1 working of 1 attempt43.01417.85 / 387 / 88
ChessBalanced1 working of 1 attempt43.41421.11 / 399 / 80
ShogiIntensive1 working of 1 attempt37.41317.789 / 156 / 249
ShogiBalanced1 working of 1 attempt39.91340.0114 / 130 / 250
ShogiBaseline1 working of 1 attempt44.61380.9119 / 165 / 210
XiangqiIntensive1 working of 1 attempt49.21469.093 / 287 / 118
XiangqiBalanced1 working of 1 attempt45.31438.446 / 342 / 110
XiangqiBaseline1 working of 1 attempt43.71426.632 / 355 / 111
HexIntensive1 working of 1 attempt45.91386.2235 / 0 / 295
HexBalanced1 working of 1 attempt15.5922.077 / 0 / 453
HexBaseline1 working of 1 attempt7.8727.937 / 0 / 493
International DraughtsBalanced1 working of 1 attempt17.1912.172 / 1 / 429
Game of the AmazonsIntensive1 working of 1 attempt47.81420.0240 / 0 / 290
Game of the AmazonsBalanced1 working of 1 attempt37.51291.4185 / 0 / 345
Game of the AmazonsBaseline1 working of 1 attempt27.11152.7131 / 0 / 399
TumbleweedIntensive1 working of 1 attempt32.01192.646 / 226 / 266
TumbleweedBalanced1 working of 1 attempt30.11172.141 / 217 / 280
TumbleweedBaseline1 working of 1 attempt29.91168.959 / 178 / 301

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: 1 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: 63% / 25% / 12% · n 8Medium: 75% / 25% / 0% · n 8Low: 38% / 37% / 25% · n 8 All three benchmark settings testedMany programs failed

Generation cost

$0.01average estimated cost per game and reasoning setting

Median
$0.0085
Range
$0.0040–$0.02
Provider-reported total
$0.28
Cost data
24 combinations · 24 runs
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
6.4k tokens
Output range
1.7k–17k 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