- Score · relative 0–100
- 55.3
- Rank
- 24
- Status
- Complete 3/3
- Rank change
- +1
- Players generated
- 2026-09-18 – 2026-10-09
- Match evidence updated
- 2026-10-26
- Results published
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-09-18 · Provider documentation
How settings are grouped
- Baseline: Low — tested and included
- Balanced: Medium — tested and included
- Intensive: Xhigh — tested and included
Scores by game
What this result shows
Strongest included setting: Xhigh (70.2).
Across included settings, the highest game score is International Draughts (68.4); the lowest is Tumbleweed (45.3). 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-max-0902
- 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 (30 of 30 indexed attempts)
Generation evidence
- Low: 8 contributing player programs across 8 games
- Medium: 8 contributing player programs across 8 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 | 76.6 | 1751.8 | 384 / 2 / 130 |
| Go | Balanced | 1 working of 1 attempt | 26.3 | 1230.6 | 80 / 95 / 341 |
| Go | Baseline | 1 working of 1 attempt | 42.2 | 1394.7 | 103 / 209 / 204 |
| Chess | Intensive | 1 working of 1 attempt | 49.5 | 1468.2 | 64 / 331 / 85 |
| Chess | Balanced | 1 working of 1 attempt | 48.9 | 1463.3 | 51 / 351 / 78 |
| Chess | Baseline | 1 working of 1 attempt | 42.1 | 1410.4 | 15 / 358 / 107 |
| Shogi | Intensive | 1 working of 1 attempt | 71.4 | 1642.3 | 289 / 93 / 112 |
| Shogi | Balanced | 1 working of 1 attempt | 57.0 | 1490.9 | 217 / 90 / 187 |
| Shogi | Baseline | 1 working of 1 attempt | 55.8 | 1479.7 | 210 / 92 / 192 |
| Xiangqi | Intensive | 1 working of 1 attempt | 84.7 | 1821.7 | 373 / 88 / 37 |
| Xiangqi | Balanced | 1 working of 1 attempt | 45.9 | 1443.1 | 63 / 314 / 121 |
| Xiangqi | Baseline | 1 working of 1 attempt | 37.8 | 1380.0 | 32 / 297 / 169 |
| Hex | Intensive | 1 working of 1 attempt | 92.4 | 2360.3 | 489 / 0 / 41 |
| Hex | Balanced | 1 working of 1 attempt | 43.8 | 1359.7 | 224 / 0 / 306 |
| Hex | Baseline | 1 working of 1 attempt | 59.8 | 1562.8 | 308 / 0 / 222 |
| International Draughts | Intensive | 1 working of 1 attempt | 64.4 | 1654.0 | 279 / 53 / 170 |
| International Draughts | Balanced | 1 working of 1 attempt | 59.5 | 1571.0 | 271 / 16 / 215 |
| International Draughts | Baseline | 1 working of 1 attempt | 81.3 | 1970.1 | 383 / 30 / 89 |
| Game of the Amazons | Intensive | 1 working of 1 attempt | 76.3 | 1822.2 | 400 / 0 / 130 |
| Game of the Amazons | Balanced | 1 working of 1 attempt | 36.6 | 1279.2 | 180 / 0 / 350 |
| Game of the Amazons | Baseline | 1 working of 1 attempt | 39.4 | 1315.3 | 195 / 0 / 335 |
| Tumbleweed | Intensive | 1 working of 1 attempt | 46.3 | 1347.3 | 107 / 249 / 182 |
| Tumbleweed | Balanced | 1 working of 1 attempt | 42.2 | 1301.7 | 124 / 173 / 241 |
| Tumbleweed | Baseline | 1 working of 1 attempt | 47.6 | 1361.8 | 158 / 160 / 220 |
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: 88% / 12% / 0% · n 8Medium: 75% / 25% / 0% · n 8Low: 75% / 25% / 0% · n 8 All three benchmark settings testedGeneration cost
$0.21average estimated cost per game and reasoning setting
- Median
- $0.12
- Range
- $0.05–$0.52
- Provider-reported total
- $5.03
- Cost data
- 24 combinations · 24 runs
- Price source
- Provider-reported
- Price list
- boardgame-list-prices-2026-09-08 + boardgame-list-prices-2026-10-09
- Average output
- 31k tokens
- Output range
- 6.3k–79k 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