Score · relative 0–100: 34.6
Rank: 53
Status: Partial 3/3
Players generated: 2026-09-03 – 2026-10-09
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: generation quality is below the publication threshold. The rank uses the available reasoning-setting results.

Scores by reasoning setting

XHigh (Intensive group, tested and included)45.5
Medium (Balanced group, tested and included)40.8
None (Baseline group, tested and included)17.5

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

Reasoning disabledLowMediumXHigh

Checked on 2026-09-03 · Provider documentation

How settings are grouped

Baseline: Reasoning disabled — tested and included
Balanced: Medium — tested and included
Intensive: XHigh — tested and included

Scores by game

Go50.9
Chess1 of 3 failed28.0
Shogi1 of 3 failed30.5
Xiangqi1 of 3 failed37.1
Hex1 of 3 failed39.5
International Draughts40.5
Game of the Amazons1 of 3 failed33.1
Tumbleweed2 of 3 failed17.1

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 (45.5).

Across included settings, the highest game score is Go (50.9); the lowest is Tumbleweed (17.1). 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: qwen/qwen3.8-27b
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: 131072 (27 of 38 indexed attempts)

Generation evidence

Reasoning disabled: 4 contributing player programs across 4 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.

Game	Reasoning group	Programs	Working-program strength	Raw rating	Combined record (W / D / L)
Go	Intensive	1 working of 1 attempt	74.7	1727.5	370 / 10 / 136
Go	Balanced	1 working of 1 attempt	53.1	1498.6	206 / 114 / 196
Go	Baseline	1 working of 1 attempt	24.9	1214.2	50 / 141 / 325
Chess	Balanced	1 working of 1 attempt	42.2	1411.2	4 / 381 / 95
Chess	Baseline	1 working of 1 attempt	42.0	1409.6	5 / 377 / 98
Shogi	Balanced	1 working of 1 attempt	49.0	1418.7	136 / 173 / 185
Shogi	Baseline	1 working of 1 attempt	42.7	1363.7	142 / 100 / 252
Xiangqi	Intensive	1 working of 1 attempt	71.1	1653.9	270 / 152 / 76
Xiangqi	Balanced	1 working of 1 attempt	40.2	1398.7	35 / 314 / 149
Hex	Intensive	1 working of 1 attempt	59.3	1555.2	305 / 0 / 225
Hex	Balanced	1 working of 1 attempt	59.3	1555.2	305 / 0 / 225
International Draughts	Intensive	1 working of 1 attempt	29.0	1102.4	119 / 14 / 369
International Draughts	Balanced	1 working of 1 attempt	61.9	1611.4	280 / 24 / 198
International Draughts	Baseline	1 working of 1 attempt	30.4	1123.6	126 / 13 / 363
Game of the Amazons	Intensive	1 working of 1 attempt	78.2	1857.6	411 / 0 / 119
Game of the Amazons	Balanced	1 working of 1 attempt	21.0	1059.8	100 / 0 / 430
Tumbleweed	Intensive	1 working of 1 attempt	51.3	1406.3	226 / 63 / 249

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

7 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: 63% / 12% / 25% · n 8Medium: 50% / 38% / 12% · n 8Reasoning disabled: 25% / 25% / 50% · n 8 All three benchmark settings testedMany programs failed

Generation cost

$0.09average estimated cost per game and reasoning setting

Median: $0.04
Range: $0.0065–$0.35
Known cost subtotal (incomplete or unverified charges): $2.09
Cost data: 24 combinations · 24 runs
Price source: Provider-reported
Price list: boardgame-list-prices-2026-10-09
Average output: 33k tokens
Output range: 2.2k–143k 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

Qwen3.8 27B