Score · relative 0–100: 38.1
Rank: 50
Status: Partial 3/3
Players generated: 2026-10-20
Match evidence updated: 2026-10-24
Results published: 2026-10-26

Compare in charts View player programs Back to leaderboard

Why this result is partial: the provider capability record is unavailable. The rank uses the available reasoning-setting results.

Scores by reasoning setting

XHighnot included (Intensive group, tested, not included)40.0
Mediumnot included (Balanced group, tested, not included)42.7
Lownot included (Baseline group, tested, not included)31.5

Settings marked “not included” were tested but are left out of the overall score.

Scores by game

Go38.0
Chess1 of 3 failed27.6
Shogi34.8
Xiangqi39.7
Hex48.9
International Draughts51.2
Game of the Amazons54.6
Tumbleweed2 of 3 failed9.7

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

No qualified setting comparison is retained.

Across included settings, the highest game score is Game of the Amazons (54.6); the lowest is Tumbleweed (9.7). 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: minimax/minimax-m3.1-flash
Provider route (catalog): Not retained in this result set
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: 524288 (35 of 35 indexed attempts)

Generation evidence

Counts describe contributing programs, not independent replications: repairs and resends are not new independent samples. Independent-generation lineage is not retained.

Game	Reasoning group	Programs	Working-program strength	Raw rating	Combined record (W / D / L)
Go	Intensive	1 working of 1 attempt	14.9	1076.4	58 / 26 / 432
Go	Balanced	1 working of 1 attempt	68.1	1650.5	300 / 81 / 135
Go	Baseline	1 working of 1 attempt	30.9	1281.4	136 / 29 / 351
Chess	Intensive	1 working of 1 attempt	41.1	1403.0	15 / 349 / 116
Chess	Baseline	1 working of 1 attempt	41.7	1407.9	4 / 377 / 99
Shogi	Intensive	1 working of 1 attempt	49.1	1420.1	176 / 94 / 223
Shogi	Balanced	1 working of 1 attempt	31.8	1267.4	85 / 112 / 297
Shogi	Baseline	1 working of 1 attempt	23.5	1183.9	12 / 181 / 301
Xiangqi	Intensive	1 working of 1 attempt	39.7	1394.7	32 / 315 / 151
Xiangqi	Balanced	1 working of 1 attempt	38.7	1387.4	37 / 296 / 165
Xiangqi	Baseline	1 working of 1 attempt	40.7	1402.7	27 / 335 / 136
Hex	Intensive	1 working of 1 attempt	72.8	1761.4	377 / 0 / 153
Hex	Balanced	1 working of 1 attempt	50.5	1443.5	259 / 0 / 271
Hex	Baseline	1 working of 1 attempt	23.5	1071.7	119 / 0 / 411
International Draughts	Intensive	1 working of 1 attempt	32.2	1149.7	137 / 6 / 358
International Draughts	Balanced	1 working of 1 attempt	51.7	1445.4	232 / 11 / 259
International Draughts	Baseline	1 working of 1 attempt	69.7	1748.3	334 / 1 / 167
Game of the Amazons	Intensive	1 working of 1 attempt	70.2	1721.4	365 / 0 / 165
Game of the Amazons	Balanced	1 working of 1 attempt	71.5	1740.4	372 / 0 / 158
Game of the Amazons	Baseline	1 working of 1 attempt	22.2	1079.0	106 / 0 / 424
Tumbleweed	Balanced	1 working of 1 attempt	29.1	1160.1	144 / 0 / 394

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: 36 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: 50% / 38% / 12% · n 8Medium: 63% / 25% / 12% · n 8Low: 63% / 25% / 12% · n 8 All three benchmark settings tested

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-2026-10-09
Average output: 17k tokens
Output range: 1.4k–73k 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

Minimax M3.1 Flash