DuelLabGameBench 2
Menu

Model results · MiniMax

Minimax M3

No Overall rank: results for 2 of 3 reasoning settings. Intensive not supported.

Score · relative 0–100
26.7
Rank
—
Status
Provisional
Players generated
2026-07-02
Match evidence updated
2026-10-26
Results published
Compare in charts View player programs Back to leaderboard

Scores by reasoning setting

  • Enabled (Balanced group, tested and included)23.1
  • None (Baseline group, tested and included)30.4

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

Reasoning disabledReasoning enabled

Checked on 2026-07-21 · Provider documentation

How settings are grouped

  • Baseline: Reasoning disabled — tested and included
  • Balanced: Reasoning enabled — tested and included
  • Intensive: Not available for this model

Scores by game

  • Go38.7
  • Chess39.8
  • Shogi1 of 2 failed20.0
  • Xiangqi1 of 2 failed20.2
  • Hex15.4
  • International Draughts1 of 2 failed8.6
  • Game of the Amazons33.0
  • Tumbleweed38.4

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: Reasoning disabled (30.4).

Across included settings, the highest game score is Chess (39.8); the lowest is International Draughts (8.6). 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
minimax/minimax-m3
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 30 indexed attempts)

Generation evidence

  • Reasoning disabled: 6 contributing player programs across 6 games
  • Reasoning enabled: 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)
GoBalanced1 working of 1 attempt18.61132.278 / 22 / 416
GoBaseline1 working of 1 attempt58.71553.4251 / 82 / 183
ChessBalanced1 working of 1 attempt39.81393.01 / 365 / 114
ChessBaseline1 working of 1 attempt39.71392.23 / 360 / 117
ShogiBaseline1 working of 1 attempt39.91340.0127 / 104 / 263
XiangqiBalanced1 working of 1 attempt40.41400.332 / 322 / 144
HexBalanced1 working of 1 attempt2.2441.58 / 0 / 522
HexBaseline1 working of 1 attempt28.71154.6146 / 0 / 384
International DraughtsBalanced1 working of 1 attempt17.1912.171 / 3 / 428
Game of the AmazonsBalanced1 working of 1 attempt42.41352.9211 / 0 / 319
Game of the AmazonsBaseline1 working of 1 attempt23.61100.5113 / 0 / 417
TumbleweedBalanced1 working of 1 attempt24.51108.271 / 100 / 367
TumbleweedBaseline1 working of 1 attempt52.31418.0254 / 17 / 267

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

Reasoning enabled: 0% / 88% / 12% · n 8Reasoning disabled: 50% / 25% / 25% · n 8 No Overall rankIntensive not supportedMany programs needed repairMany programs failed

Generation cost

$0.05average estimated cost per game and reasoning setting

Median
$0.05
Range
$0.0064–$0.10
Known cost subtotal (incomplete or unverified charges)
$0.79
Cost data
16 combinations · 16 runs
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
37k tokens
Output range
3.5k–78k tokens
Runs with output-token data
16
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