- Score · relative 0–100
- 21.7
- Rank
- 68
- Status
- Complete 3/3
- Players generated
- 2026-08-09 – 2026-08-18
- Match evidence updated
- 2026-10-06
- Results published
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-08-08 · Provider documentation
How settings are grouped
- Baseline: None — tested and included
- Balanced: Medium — tested and included
- Intensive: Max — tested and included
Scores by game
What this result shows
Strongest included setting: Max (25.0).
Across included settings, the highest game score is International Draughts (36.6); the lowest is Chess (8.2). 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
- thinkingmachines/inkling-small
- 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 43 indexed attempts)
Generation evidence
- None: 8 contributing player programs across 8 games
- Medium: 8 contributing player programs across 8 games
- Max: 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 | max | 1 | 1 | 8.3–8.3 |
| Chess | medium | 1 | 1 | 7.8–7.8 |
| Chess | none | 1 | 1 | 8.4–8.4 |
| Game of the Amazons | max | 1 | 1 | 24.5–24.5 |
| Game of the Amazons | medium | 1 | 1 | 50.0–50.0 |
| Game of the Amazons | none | 1 | 1 | 34.3–34.3 |
| Go | max | 1 | 1 | 31.1–31.1 |
| Go | medium | 1 | 1 | 9.6–9.6 |
| Go | none | 1 | 1 | 24.3–24.3 |
| Hex | max | 1 | 1 | 38.8–38.8 |
| Hex | medium | 1 | 1 | 14.2–14.2 |
| Hex | none | 1 | 1 | 5.4–5.4 |
| International Draughts | max | 1 | 1 | 52.6–52.6 |
| International Draughts | medium | 1 | 1 | 28.4–28.4 |
| International Draughts | none | 1 | 1 | 28.6–28.6 |
| Shogi | max | 1 | 1 | 25.7–25.7 |
| Shogi | medium | 1 | 1 | 20.7–20.7 |
| Shogi | none | 1 | 1 | 29.6–29.6 |
| Tumbleweed | max | 1 | 1 | 18.0–18.0 |
| Tumbleweed | medium | 1 | 1 | 19.2–19.2 |
| Tumbleweed | none | 1 | 1 | 18.1–18.1 |
| Xiangqi | max | 1 | 1 | 12.8–12.8 |
| Xiangqi | medium | 1 | 1 | 15.6–15.6 |
| Xiangqi | none | 1 | 1 | 16.2–16.2 |
Program ranges describe the retained competitors on this release scale, not a statistical estimate of a fresh generation.
Failures and budgets
4 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
Max: 60% / 20% / 20% · n 10Medium: 45% / 44% / 11% · n 9None: 56% / 33% / 11% · n 9 All three benchmark settings testedGeneration cost
$0.02average estimated cost per game and reasoning setting
- Median
- $0.01
- Range
- $0.0043–$0.07
- Known cost subtotal (incomplete or unverified charges)
- $0.54
- Cost data
- 24 combinations · 28 runs
- Price source
- Provider-reported
- Price list
- boardgame-list-prices-2026-08-08
- Average output
- 12k tokens
- Output range
- 894–49k tokens
- Runs with output-token data
- 28
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