- Score · relative 0–100
- 53.7
- Rank
- 28
- Status
- Complete 3/3
- Rank change
- +1
- Players generated
- 2026-08-13 – 2026-10-09
- Match evidence updated
- 2026-10-26
- Results published
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-08-08 · Provider documentation
How settings are grouped
- Baseline: Minimal — tested and included
- Balanced: Medium — tested and included
- Intensive: XHigh — tested and included
Scores by game
What this result shows
Strongest included setting: XHigh (59.7).
Across included settings, the highest game score is Go (67.9); the lowest is International Draughts (23.4). 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
- meta/muse-spark-1.2
- 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
- 943718 (9 of 27 indexed attempts)
Generation evidence
- Minimal: 8 contributing player programs across 8 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.
| Game | Reasoning group | Programs | Working-program strength | Raw rating | Combined record (W / D / L) |
|---|---|---|---|---|---|
| Go | Intensive | 1 working of 1 attempt | 80.6 | 1806.9 | 405 / 2 / 109 |
| Go | Balanced | 1 working of 1 attempt | 85.8 | 1894.5 | 423 / 23 / 70 |
| Go | Baseline | 1 working of 1 attempt | 37.3 | 1346.5 | 99 / 167 / 250 |
| Chess | Intensive | 1 working of 1 attempt | 48.4 | 1459.3 | 40 / 368 / 72 |
| Chess | Balanced | 1 working of 1 attempt | 46.8 | 1447.1 | 36 / 361 / 83 |
| Chess | Baseline | 1 working of 1 attempt | 42.0 | 1409.6 | 20 / 347 / 113 |
| Shogi | Intensive | 1 working of 1 attempt | 61.1 | 1530.0 | 273 / 19 / 202 |
| Shogi | Balanced | 1 working of 1 attempt | 52.3 | 1447.6 | 186 / 105 / 203 |
| Shogi | Baseline | 1 working of 1 attempt | 46.3 | 1395.3 | 175 / 69 / 250 |
| Xiangqi | Intensive | 1 working of 1 attempt | 49.5 | 1471.4 | 103 / 270 / 125 |
| Xiangqi | Balanced | 1 working of 1 attempt | 45.9 | 1443.1 | 85 / 270 / 143 |
| Xiangqi | Baseline | 1 working of 1 attempt | 47.8 | 1458.0 | 53 / 353 / 92 |
| Hex | Intensive | 1 working of 1 attempt | 61.5 | 1585.9 | 317 / 0 / 213 |
| Hex | Balanced | 1 working of 1 attempt | 49.9 | 1436.3 | 256 / 0 / 274 |
| Hex | Baseline | 1 working of 1 attempt | 51.6 | 1457.8 | 265 / 0 / 265 |
| International Draughts | Intensive | 1 working of 1 attempt | 27.1 | 1072.6 | 107 / 20 / 375 |
| International Draughts | Baseline | 1 working of 1 attempt | 19.7 | 956.6 | 83 / 2 / 417 |
| Game of the Amazons | Intensive | 1 working of 1 attempt | 74.8 | 1794.8 | 391 / 0 / 139 |
| Game of the Amazons | Balanced | 1 working of 1 attempt | 64.3 | 1633.9 | 331 / 0 / 199 |
| Game of the Amazons | Baseline | 1 working of 1 attempt | 34.6 | 1254.7 | 170 / 0 / 360 |
| Tumbleweed | Intensive | 1 working of 1 attempt | 74.4 | 1772.7 | 380 / 10 / 148 |
| Tumbleweed | Balanced | 1 working of 1 attempt | 70.4 | 1693.6 | 351 / 21 / 166 |
| Tumbleweed | Baseline | 1 working of 1 attempt | 56.5 | 1473.1 | 284 / 2 / 252 |
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 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: 100% / 0% / 0% · n 8Medium: 100% / 0% / 0% · n 7Minimal: 88% / 12% / 0% · n 8 All three benchmark settings testedGeneration cost
$0.07average estimated cost per game and reasoning setting
- Median
- $0.05
- Range
- $0.02–$0.22
- Provider-reported total
- $1.71
- Cost data
- 24 combinations · 24 runs
- Price source
- Provider-reported
- Price list
- boardgame-list-prices-2026-08-08 + boardgame-list-prices-2026-10-09
- Average output
- 14k tokens
- Output range
- 2.6k–46k 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