- Score · relative 0–100
- 40.6
- Rank
- 20
- Status
- Complete 3/3
- Players generated
- 2026-07-02 – 2026-07-03
- 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: Thinking field omitted — tested and included
- Balanced: Medium — tested and included
- Intensive: XHigh — tested and included
Scores by game
What this result shows
Strongest included setting: XHigh (54.1).
Across included settings, the highest game score is International Draughts (67.8); the lowest is Xiangqi (19.0). 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
- claude-opus-4-8
- Provider route (catalog)
- anthropic
- 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 31 indexed attempts)
Generation evidence
- Thinking field omitted: 7 contributing player programs across 7 games
- Medium: 8 contributing player programs across 8 games
- XHigh: 7 contributing player programs across 7 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 | medium | 1 | 1 | 8.5–8.5 |
| Chess | none | 1 | 1 | 6.3–6.3 |
| Chess | xhigh | 1 | 1 | 51.2–51.2 |
| Game of the Amazons | medium | 1 | 1 | 59.1–59.1 |
| Game of the Amazons | none | 1 | 1 | 46.9–46.9 |
| Game of the Amazons | xhigh | 1 | 1 | 65.2–65.2 |
| Go | medium | 1 | 1 | 38.7–38.7 |
| Go | none | 1 | 1 | 46.8–46.8 |
| Go | xhigh | 1 | 1 | 56.2–56.2 |
| Hex | medium | 1 | 1 | 44.8–44.8 |
| Hex | none | 1 | 1 | 27.9–27.9 |
| Hex | xhigh | 1 | 1 | 43.8–43.8 |
| International Draughts | medium | 1 | 1 | 76.8–76.8 |
| International Draughts | none | 1 | 1 | 48.0–48.0 |
| International Draughts | xhigh | 1 | 1 | 78.6–78.6 |
| Shogi | medium | 1 | 1 | 14.0–14.0 |
| Tumbleweed | medium | 1 | 1 | 17.9–17.9 |
| Tumbleweed | none | 1 | 1 | 58.6–58.6 |
| Tumbleweed | xhigh | 1 | 1 | 60.1–60.1 |
| Xiangqi | medium | 1 | 1 | 10.7–10.7 |
| Xiangqi | none | 1 | 1 | 9.8–9.8 |
| Xiangqi | xhigh | 1 | 1 | 36.4–36.4 |
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; 6 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: 75% / 13% / 12% · n 8Medium: 100% / 0% / 0% · n 8Thinking field omitted: 88% / 0% / 12% · n 8 All three benchmark settings testedGeneration cost
$0.44average estimated cost per game and reasoning setting
- Median
- $0.20
- Range
- $0.13–$1.39
- Known cost subtotal (incomplete or unverified charges)
- $10.46
- Cost data
- 24 combinations · 24 runs
- Price source
- Standard list-price estimate
- Price list
- boardgame-list-prices-2026-08-08
- Average output
- 15k tokens
- Output range
- 2.9k–52k 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