- Score · relative 0–100
- 50.4
- Rank
- 36
- Status
- Complete 3/3
- Rank change
- 0
- Players generated
- 2026-08-08 – 2026-08-18
- 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 (51.9).
Across included settings, the highest game score is Hex (68.7); the lowest is Go (33.9). 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
- 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 (1 of 30 indexed attempts)
Generation evidence
- Minimal: 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 | 32.6 | 1299.2 | 111 / 96 / 309 |
| Go | Balanced | 1 working of 1 attempt | 42.4 | 1396.6 | 125 / 167 / 224 |
| Go | Baseline | 1 working of 1 attempt | 26.8 | 1236.3 | 71 / 118 / 327 |
| Chess | Intensive | 1 working of 2 attempts | 51.9 | 1486.1 | 69 / 343 / 68 |
| Chess | Balanced | 1 working of 1 attempt | 42.9 | 1417.0 | 8 / 380 / 92 |
| Chess | Baseline | 1 working of 1 attempt | 40.5 | 1398.0 | 11 / 351 / 118 |
| Shogi | Intensive | 1 working of 1 attempt | 57.3 | 1493.7 | 245 / 37 / 212 |
| Shogi | Balanced | 1 working of 1 attempt | 56.7 | 1488.1 | 211 / 99 / 184 |
| Shogi | Baseline | 1 working of 1 attempt | 39.1 | 1332.6 | 92 / 166 / 236 |
| Xiangqi | Intensive | 1 working of 1 attempt | 66.8 | 1612.9 | 224 / 200 / 74 |
| Xiangqi | Balanced | 1 working of 1 attempt | 37.9 | 1380.9 | 18 / 326 / 154 |
| Xiangqi | Baseline | 1 working of 1 attempt | 41.5 | 1409.1 | 43 / 311 / 144 |
| Hex | Intensive | 1 working of 1 attempt | 47.4 | 1405.3 | 243 / 0 / 287 |
| Hex | Balanced | 1 working of 1 attempt | 68.1 | 1682.4 | 352 / 0 / 178 |
| Hex | Baseline | 1 working of 1 attempt | 90.6 | 2273.4 | 478 / 0 / 52 |
| International Draughts | Intensive | 1 working of 1 attempt | 52.1 | 1452.8 | 220 / 40 / 242 |
| International Draughts | Balanced | 1 working of 1 attempt | 49.7 | 1415.5 | 216 / 23 / 263 |
| International Draughts | Baseline | 1 working of 1 attempt | 22.8 | 1005.7 | 89 / 17 / 396 |
| Game of the Amazons | Intensive | 1 working of 1 attempt | 78.1 | 1854.3 | 410 / 0 / 120 |
| Game of the Amazons | Balanced | 1 working of 1 attempt | 39.8 | 1320.0 | 197 / 0 / 333 |
| Game of the Amazons | Baseline | 1 working of 1 attempt | 72.0 | 1748.8 | 375 / 0 / 155 |
| Tumbleweed | Intensive | 1 working of 1 attempt | 55.2 | 1455.6 | 224 / 108 / 206 |
| Tumbleweed | Balanced | 1 working of 1 attempt | 67.8 | 1645.9 | 311 / 71 / 156 |
| Tumbleweed | Baseline | 1 working of 1 attempt | 55.5 | 1459.3 | 185 / 189 / 164 |
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
1 model-code generation failures; 3 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: 89% / 0% / 11% · n 9Medium: 100% / 0% / 0% · n 8Minimal: 100% / 0% / 0% · n 8 All three benchmark settings testedGeneration cost
$0.19average estimated cost per game and reasoning setting
- Median
- $0.14
- Range
- $0.07–$0.41
- Provider-reported total
- $6.45
- Cost data
- 24 combinations · 29 runs
- Price source
- Provider-reported
- Price list
- boardgame-list-prices-2026-08-08
- Average output
- 34k tokens
- Output range
- 8.5k–76k tokens
- Runs with output-token data
- 29
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