Score · relative 0–100: 48.9
Rank: 38
Status: Complete 3/3
Rank change: +1
Players generated: 2026-07-02 – 2026-07-21
Match evidence updated: 2026-10-26
Results published: 2026-10-26

Compare in charts View player programs Back to leaderboard

Scores by reasoning setting

High (Intensive group, tested and included)50.0
Budgetednot included (Intensive group, tested, not included)50.0
Medium (Balanced group, tested and included)48.8
Budgetednot included (Balanced group, tested, not included)48.8
None (Baseline group, tested and included)47.9
Historicalnot included (Not grouped group, tested, not included)44.3

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

Available settings and grouping

Available settings

Thinking field omittedLow effort + 8,000 thinking tokensMedium effort + 16,000 thinking tokensHigh effort + 32,000 thinking tokens

Checked on 2026-07-21 · Provider documentation

How settings are grouped

Baseline: Thinking field omitted — tested and included
Balanced: Medium effort + 16,000 thinking tokens — tested and included
Intensive: High effort + 32,000 thinking tokens — tested and included

Scores by game

Go47.3
Chess44.0
Shogi47.4
Xiangqi43.7
Hex46.6
International Draughts48.8
Game of the Amazons45.7
Tumbleweed67.7

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

Strongest included setting: High effort + 32,000 thinking tokens (50.0).

Across included settings, the highest game score is Tumbleweed (67.7); the lowest is Xiangqi (43.7). 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: claude-opus-4-5
Provider route (catalog): anthropic
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: 64000 (16 of 24 indexed attempts)

Generation evidence

Thinking field omitted: 8 contributing player programs across 8 games
Medium effort + 16,000 thinking tokens: 8 contributing player programs across 8 games
High effort + 32,000 thinking tokens: 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.

Game	Reasoning group	Programs	Working-program strength	Raw rating	Combined record (W / D / L)
Go	Intensive	2 working of 2 attempts	49.9 program scores 72.1 · 27.6	1470.8 program range 1245–1696	381 / 229 / 422
Go	Balanced	2 working of 2 attempts	47.4 program scores 57.9 · 37.0	1444.2 program range 1344–1545	283 / 371 / 378
Go	Baseline	1 working of 1 attempt	44.6	1417.4	102 / 235 / 179
Chess	Intensive	2 working of 2 attempts	43.5 program scores 43.9 · 43.2	1421.9 program range 1419–1424	23 / 758 / 179
Chess	Balanced	2 working of 2 attempts	44.1 program scores 44.3 · 44.0	1426.4 program range 1425–1428	31 / 753 / 176
Chess	Baseline	1 working of 1 attempt	44.4	1428.4	20 / 370 / 90
Shogi	Intensive	1 working of 1 attempt	50.4	1431.3	192 / 75 / 227
Shogi	Balanced	2 working of 2 attempts	49.3 program scores 51.5 · 47.0	1421.5 program range 1402–1441	330 / 236 / 422
Shogi	Baseline	1 working of 1 attempt	42.3	1361.0	105 / 171 / 218
Xiangqi	Intensive	2 working of 2 attempts	41.1 program scores 41.7 · 40.5	1405.9 program range 1401–1411	100 / 586 / 310
Xiangqi	Balanced	2 working of 2 attempts	41.3 program scores 43.8 · 38.8	1407.8 program range 1388–1427	59 / 673 / 264
Xiangqi	Baseline	1 working of 1 attempt	48.6	1464.3	71 / 325 / 102
Hex	Intensive	2 working of 2 attempts	47.4 program scores 51.3 · 43.6	1405.1 program range 1357–1453	486 / 0 / 574
Hex	Balanced	2 working of 2 attempts	45.2 program scores 46.8 · 43.6	1377.7 program range 1357–1398	463 / 0 / 597
Hex	Baseline	1 working of 1 attempt	47.0	1400.5	241 / 0 / 289
International Draughts	Intensive	2 working of 2 attempts	52.8 program scores 56.4 · 49.3	1464.3 program range 1408–1521	470 / 35 / 499
International Draughts	Balanced	2 working of 2 attempts	47.8 program scores 51.9 · 43.8	1386.3 program range 1324–1448	417 / 37 / 550
International Draughts	Baseline	1 working of 1 attempt	45.6	1352.7	201 / 11 / 290
Game of the Amazons	Intensive	2 working of 2 attempts	55.4 program scores 60.7 · 50.2	1517.6 program range 1450–1585	564 / 0 / 496
Game of the Amazons	Balanced	2 working of 2 attempts	49.4 program scores 52.2 · 46.5	1439.5 program range 1404–1475	497 / 0 / 563
Game of the Amazons	Baseline	1 working of 1 attempt	32.3	1224.5	158 / 0 / 372
Tumbleweed	Intensive	2 working of 2 attempts	59.1 program scores 77.6 · 40.6	1561.7 program range 1285–1839	508 / 196 / 372
Tumbleweed	Balanced	2 working of 2 attempts	65.8 program scores 76.8 · 54.8	1636.5 program range 1451–1822	585 / 180 / 311
Tumbleweed	Baseline	1 working of 1 attempt	78.2	1851.5	390 / 34 / 114

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

0 model-code generation failures; 0 provider/infrastructure failures excluded from the generation denominator. Runtime player faults are separate: 1 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

High effort + 32,000 thinking tokens: 100% / 0% / 0% · n 8Medium effort + 16,000 thinking tokens: 100% / 0% / 0% · n 8Thinking field omitted: 100% / 0% / 0% · n 8 All three benchmark settings tested

Generation cost

$0.25average estimated cost per game and reasoning setting

Median: $0.21
Range: $0.10–$0.51
Known cost subtotal (incomplete or unverified charges): $11.20
Cost data: 24 combinations · 40 runs
Price source: Standard list-price estimate
Price list: boardgame-list-prices-2026-07-12 + boardgame-list-prices-2026-10-09
Average output: 10.0k tokens
Output range: 2.1k–28k 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

Claude Opus 4.5