DuelLabGameBench 2
Menu

Model results · Xiaomi

MiMo-V2.5-Pro

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

Score · relative 0–100
38.3
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)46.8
  • None (Baseline group, tested and included)29.8

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

  • Go54.3
  • Chess39.1
  • Shogi34.5
  • Xiangqi1 of 2 failed23.8
  • Hex22.4
  • International Draughts52.8
  • Game of the Amazons45.6
  • Tumbleweed23.9

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 enabled (46.8).

Across included settings, the highest game score is Go (54.3); the lowest is Hex (22.4). 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
xiaomi/mimo-v2.5-pro
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 28 indexed attempts)

Generation evidence

  • Reasoning disabled: 7 contributing player programs across 7 games
  • Reasoning enabled: 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)
GoBalanced1 working of 1 attempt71.41687.3326 / 63 / 127
GoBaseline1 working of 1 attempt37.31346.5119 / 127 / 270
ChessBaseline1 working of 1 attempt39.11387.220 / 320 / 140
ShogiBaseline1 working of 1 attempt34.51292.062 / 183 / 249
XiangqiBalanced1 working of 1 attempt47.61456.5103 / 251 / 144
HexBalanced1 working of 1 attempt25.51103.3129 / 0 / 401
HexBaseline1 working of 1 attempt19.3997.297 / 0 / 433
International DraughtsBalanced1 working of 1 attempt67.21702.3313 / 15 / 174
International DraughtsBaseline1 working of 1 attempt38.41243.5168 / 5 / 329
Game of the AmazonsBalanced1 working of 1 attempt41.81345.9208 / 0 / 322
Game of the AmazonsBaseline1 working of 1 attempt49.31438.4248 / 0 / 282
TumbleweedBalanced1 working of 1 attempt27.31140.211 / 248 / 279
TumbleweedBaseline1 working of 1 attempt20.61060.841 / 121 / 376

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

1 model-code generation failures; 2 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% / 100% / 0% · n 6Reasoning disabled: 50% / 38% / 12% · n 8 No Overall rankIntensive not supportedMany programs needed repair

Generation cost

$0.08average estimated cost per game and reasoning setting

Median
$0.05
Range
$0.0057–$0.30
Known cost subtotal (incomplete or unverified charges)
$1.33
Cost data
16 combinations · 16 runs
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
41k tokens
Output range
2.8k–131k 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