- Score · relative 0–100
- 32.7
- Rank
- 39
- Status
- Complete 3/3
- Players generated
- 2026-09-03
- Match evidence updated
- 2026-10-06
- Results published
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-07-21 · Provider documentation
How settings are grouped
- Baseline: Reasoning disabled — tested and included
- Balanced: High — tested and included
- Intensive: XHigh — tested and included
Scores by game
What this result shows
Strongest included setting: High (37.7).
Across included settings, the highest game score is Game of the Amazons (58.0); the lowest is Xiangqi (13.9). 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
- deepseek/deepseek-v4-pro
- 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
- Not retained (0 of 35 indexed attempts)
Generation evidence
- Reasoning disabled: 6 contributing player programs across 6 games
- High: 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; the per-game counts below keep unique code identities separate from admitted generation runs.
| Game | Setting | Unique programs | Admitted generation runs | Program score range |
|---|---|---|---|---|
| Chess | high | 1 | 1 | 6.0–6.0 |
| Chess | xhigh | 1 | 1 | 10.0–10.0 |
| Game of the Amazons | high | 1 | 1 | 61.0–61.0 |
| Game of the Amazons | none | 1 | 1 | 49.6–49.6 |
| Game of the Amazons | xhigh | 1 | 1 | 63.4–63.4 |
| Go | high | 1 | 1 | 50.2–50.2 |
| Go | none | 1 | 1 | 28.8–28.8 |
| Go | xhigh | 1 | 1 | 25.5–25.5 |
| Hex | high | 1 | 1 | 45.1–45.1 |
| Hex | none | 1 | 1 | 37.8–37.8 |
| Hex | xhigh | 1 | 1 | 42.0–42.0 |
| International Draughts | high | 1 | 1 | 50.1–50.1 |
| International Draughts | xhigh | 1 | 1 | 72.9–72.9 |
| Shogi | high | 1 | 1 | 12.6–12.6 |
| Shogi | none | 1 | 1 | 23.5–23.5 |
| Shogi | xhigh | 1 | 1 | 26.9–26.9 |
| Tumbleweed | high | 1 | 1 | 63.3–63.3 |
| Tumbleweed | none | 1 | 1 | 16.4–16.4 |
| Tumbleweed | xhigh | 1 | 1 | 18.0–18.0 |
| Xiangqi | high | 1 | 1 | 13.5–13.5 |
| Xiangqi | none | 1 | 1 | 12.3–12.3 |
| Xiangqi | xhigh | 1 | 1 | 15.8–15.8 |
Program ranges describe the retained competitors on this release scale, not a statistical estimate of a fresh generation.
Failures and budgets
2 model-code generation failures; 0 provider/infrastructure failures excluded from the generation denominator. Runtime player faults are separate: 0 recorded unilateral faults across contributing program rows, excluded from 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: 63% / 37% / 0% · n 8High: 50% / 50% / 0% · n 8Reasoning disabled: 50% / 25% / 25% · n 8 All three benchmark settings testedMany programs needed repairMany programs failedGeneration cost
$0.06average estimated cost per game and reasoning setting
- Median
- $0.05
- Range
- $0.01–$0.18
- Provider-reported total
- $1.49
- Cost data
- 24 combinations · 24 runs
- Price source
- Provider-reported
- Price list
- Not recorded for this older data
- Average output
- 21k tokens
- Output range
- 2.5k–75k 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