Scores by reasoning setting

XHigh (Intensive group, tested and included)56.0
Medium (Balanced group, tested and included)38.4
Low (Baseline group, tested and included)40.7

Every tested setting is included in the overall score.

Available settings and grouping

Available settings

LowMediumHighXHighMax

Checked on 2026-10-20 · Provider documentation

How settings are grouped

Baseline: Low — tested and included
Balanced: Medium — tested and included
Intensive: XHigh — tested and included

Scores by game

Go1 of 3 failed23.5
Chess42.9
Shogi52.9
Xiangqi46.6
Hex53.1
International Draughts1 of 3 failed43.2
Game of the Amazons29.5
Tumbleweed68.6

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 (56.0).

Across included settings, the highest game score is Tumbleweed (68.6); the lowest is Go (23.5). 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: reflection/beam-1.0-501b-a23b
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 (36 of 36 indexed attempts)

Generation evidence

Low: 7 contributing player programs across 7 games
Medium: 7 contributing player programs across 7 games
XHigh: 8 contributing player programs across 8 games

Counts describe contributing programs, not independent replications: repairs and resends are not new independent samples. Independent-generation lineage is not retained; the per-game counts below keep unique code identities separate from admitted generation runs.

Game	Setting	Unique programs	Admitted generation runs	Program score range
Chess	highest	1	1	49.2–49.2
Chess	medium	1	1	33.7–33.7
Chess	none	1	1	45.7–45.7
Game of the Amazons	highest	1	1	42.8–42.8
Game of the Amazons	medium	1	1	35.3–35.3
Game of the Amazons	none	1	1	10.6–10.6
Go	highest	1	1	25.2–25.2
Go	none	1	1	45.4–45.4
Hex	highest	1	1	55.6–55.6
Hex	medium	1	1	41.6–41.6
Hex	none	1	1	62.1–62.1
International Draughts	highest	1	1	74.4–74.4
International Draughts	medium	1	1	55.2–55.2
Shogi	highest	1	1	79.2–79.2
Shogi	medium	1	1	38.6–38.6
Shogi	none	1	1	40.8–40.8
Tumbleweed	highest	1	1	61.7–61.7
Tumbleweed	medium	1	1	61.6–61.6
Tumbleweed	none	1	1	82.6–82.6
Xiangqi	highest	1	1	59.9–59.9
Xiangqi	medium	1	1	41.0–41.0
Xiangqi	none	1	1	38.7–38.7

Program ranges describe the retained competitors on this release scale, not a statistical estimate of a fresh generation.

Failures and budgets

2 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% / 37% / 0% · n 8Medium: 63% / 25% / 12% · n 8Low: 38% / 50% / 12% · n 8 All three benchmark settings testedMany programs needed repair

Generation cost

$0.02average estimated cost per game and reasoning setting

Median: $0.01
Range: $0.0041–$0.05
Provider-reported total: $0.38
Cost data: 24 combinations · 24 runs
Price source: Provider-reported
Price list: boardgame-list-prices-2026-10-09
Average output: 13k tokens
Output range: 2.2k–44k 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

Beam 1.0 501B A23B