- Score · relative 0–100
- 33.1
- Rank
- 36
- Status
- Complete 3/3
- Players generated
- 2026-08-09
- 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 disabled — tested and included
- Balanced: Medium — tested and included
- Intensive: XHigh — tested and included
Scores by game
What this result shows
Strongest included setting: XHigh (40.1).
Across included settings, the highest game score is Game of the Amazons (47.2); the lowest is Chess (9.0). 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-sonnet-5
- 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
- 128000 (24 of 24 indexed attempts)
Generation evidence
- Thinking disabled: 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; 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 | 10.1–10.1 |
| Chess | none | 1 | 1 | 8.7–8.7 |
| Chess | xhigh | 1 | 1 | 8.3–8.3 |
| Game of the Amazons | medium | 1 | 1 | 46.5–46.5 |
| Game of the Amazons | none | 1 | 1 | 37.3–37.3 |
| Game of the Amazons | xhigh | 1 | 1 | 57.9–57.9 |
| Go | medium | 1 | 1 | 41.7–41.7 |
| Go | none | 1 | 1 | 40.3–40.3 |
| Go | xhigh | 1 | 1 | 51.3–51.3 |
| Hex | medium | 1 | 1 | 42.1–42.1 |
| Hex | none | 1 | 1 | 28.4–28.4 |
| Hex | xhigh | 1 | 1 | 49.8–49.8 |
| International Draughts | medium | 1 | 1 | 42.0–42.0 |
| International Draughts | none | 1 | 1 | 46.9–46.9 |
| International Draughts | xhigh | 1 | 1 | 34.9–34.9 |
| Shogi | medium | 1 | 1 | 22.5–22.5 |
| Shogi | none | 1 | 1 | 28.9–28.9 |
| Shogi | xhigh | 1 | 1 | 32.6–32.6 |
| Tumbleweed | medium | 1 | 1 | 21.9–21.9 |
| Tumbleweed | none | 1 | 1 | 28.6–28.6 |
| Tumbleweed | xhigh | 1 | 1 | 58.5–58.5 |
| Xiangqi | medium | 1 | 1 | 14.8–14.8 |
| Xiangqi | none | 1 | 1 | 12.8–12.8 |
| Xiangqi | xhigh | 1 | 1 | 27.1–27.1 |
Program ranges describe the retained competitors on this release scale, not a statistical estimate of a fresh generation.
Failures and budgets
0 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: 100% / 0% / 0% · n 8Medium: 100% / 0% / 0% · n 8Thinking disabled: 100% / 0% / 0% · n 8 All three benchmark settings testedGeneration cost
$0.16average estimated cost per game and reasoning setting
- Median
- $0.07
- Range
- $0.05–$0.50
- Known cost subtotal (incomplete or unverified charges)
- $3.83
- Cost data
- 24 combinations · 24 runs
- Price source
- Standard list-price estimate
- Price list
- boardgame-list-prices-2026-08-08
- Average output
- 13k tokens
- Output range
- 2.6k–48k 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