Score · relative 0–100: 58.1
Rank: 21
Status: Complete 3/3
Rank change: 0
Players generated: 2026-11-03
Match evidence updated: 2026-11-10

Compare in charts View player programs Back to leaderboard

MaxIntensive
71.7 · rank 18 on the Intensive leaderboard
Cost per program
$0.0256 · provider-reported
Working programs
8 of 8
API time
5.7 min (observed mean, descriptive)
9.0 points above High, at 2.0× the cost
On the best-value line across ranked settings.
- No ranked setting scores higher for $0.0256 or less.
- No ranked setting scores at least as high for less.
HighBalanced
62.7 · rank 21 on the Balanced leaderboard
Cost per program
$0.0130 · provider-reported
Working programs
8 of 8
API time
2.8 min (observed mean, descriptive)
22.9 points above None, at 5.9× the cost
On the best-value line across ranked settings.
- No ranked setting scores higher for $0.0130 or less.
- No ranked setting scores at least as high for less.
NoneBaseline
39.8 · rank 47 on the Baseline leaderboard
Cost per program
$0.00221 · provider-reported
Working programs
8 of 8
API time
22 s (observed mean, descriptive)
- Higher score for $0.00221 or less: none offered; Ox Alpha High · Balanced: 46.1 for $0 (provider-reported) scores higher, but a $0 record is not a price.
- Cheapest scoring at least as high: none offered; Ox Alpha High · Balanced: 46.1 for $0 (provider-reported) does, but a $0 record is not a price.

Score and cost of every ranked setting

The chart needs JavaScript. The setting cards hold this model's results, and Charts compares every model.

Each setting is placed by its published score and its generation cost per player program, the mean over the game cells including repairs and failed attempts. Higher is better; further left costs less (logarithmic axis, with recorded $0 in its own lane). Filled marks are compared; hollow marks are not (the reason is in the table). The line marks the best value across ranked reasoning settings: no ranked setting with complete cost evidence scores at least as high for the same or less. It includes models without an Overall rank, so it can differ from the line on Charts. Costs mix provider-reported charges and list-price estimates; differences in score points are not tested for significance.

Show the numbers

The table needs JavaScript.

Available settings and grouping

Available settings

NoneLowHighMax

Checked on 2026-11-03 · Provider documentation

How settings are grouped

Baseline: None — tested and included
Balanced: High — tested and included
Intensive: Max — tested and included

Scores by game

Go60.0
Chess53.3
Shogi62.1
Xiangqi61.0
Hex55.3
International Draughts60.6
Game of the Amazons71.7
Tumbleweed40.5

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: Max (71.7).

Across included settings, the highest game score is Game of the Amazons (71.7); the lowest is Tumbleweed (40.5). 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: particle-ai/particle-1
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 (28 of 28 indexed attempts)

Generation evidence

None: 8 contributing player programs across 8 games
High: 8 contributing player programs across 8 games
Max: 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	1 working of 1 attempt	91.3	2039.3	503 / 19 / 42
Go	Balanced	1 working of 1 attempt	51.8	1498.0	276 / 24 / 264
Go	Baseline	1 working of 1 attempt	36.7	1351.2	194 / 17 / 353
Chess	Intensive	1 working of 1 attempt	55.3	1512.2	115 / 340 / 77
Chess	Balanced	1 working of 1 attempt	65.7	1599.8	212 / 257 / 63
Chess	Baseline	1 working of 1 attempt	38.9	1383.2	10 / 377 / 145
Shogi	Intensive	1 working of 1 attempt	78.8	1759.8	381 / 75 / 92
Shogi	Balanced	1 working of 1 attempt	51.0	1438.2	184 / 151 / 213
Shogi	Baseline	1 working of 1 attempt	56.4	1488.1	263 / 52 / 233
Xiangqi	Intensive	1 working of 1 attempt	77.6	1725.6	325 / 177 / 42
Xiangqi	Balanced	1 working of 1 attempt	67.2	1615.2	240 / 231 / 73
Xiangqi	Baseline	1 working of 1 attempt	38.2	1376.3	43 / 312 / 189
Hex	Intensive	1 working of 1 attempt	80.1	1948.1	457 / 0 / 125
Hex	Balanced	1 working of 1 attempt	61.3	1573.8	345 / 0 / 237
Hex	Baseline	1 working of 1 attempt	24.7	1067.3	137 / 0 / 445
International Draughts	Intensive	1 working of 1 attempt	80.2	1984.1	429 / 19 / 106
International Draughts	Balanced	1 working of 1 attempt	68.0	1748.1	364 / 4 / 186
International Draughts	Baseline	1 working of 1 attempt	33.6	1172.4	166 / 3 / 385
Game of the Amazons	Intensive	1 working of 1 attempt	80.9	1920.5	464 / 0 / 114
Game of the Amazons	Balanced	1 working of 1 attempt	71.1	1732.3	403 / 0 / 175
Game of the Amazons	Baseline	1 working of 1 attempt	63.1	1610.0	353 / 0 / 225
Tumbleweed	Intensive	1 working of 1 attempt	29.2	1077.9	159 / 0 / 423
Tumbleweed	Balanced	1 working of 1 attempt	65.8	1699.6	370 / 0 / 212
Tumbleweed	Baseline	1 working of 1 attempt	26.6	1041.9	145 / 0 / 437

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: 0 recorded one-sided faults across contributing program rows. A crash, an illegal move, or a timeout repeated by a later quiet replay, pinned on one program, also counts as that program's loss in its match record; other faults 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

Max: 75% / 25% / 0% · n 8High: 100% / 0% / 0% · n 8None: 75% / 25% / 0% · n 8 All three benchmark settings tested

Generation cost, all settings combined

$0.01average estimated cost per game and reasoning setting

Median: $0.01
Range: $0.0015–$0.04
Provider-reported total: $0.33
Cost data: 24 combinations · 24 runs
Price source: Provider-reported
Price list: boardgame-list-prices-2026-10-09
Average output: 26k tokens
Output range: 2.2k–84k 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

Particle-1

Reasoning settings compared