- Score · relative 0–100
- 23.5
- Rank
- 62
- Status
- Partial 3/3
- Players generated
- 2026-07-02 – 2026-07-21
- Match evidence updated
- 2026-10-06
- Results published
Why this result is partial: generation quality is below the publication threshold. The rank uses the available reasoning-setting results.
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-07-21 · Provider documentation
How settings are grouped
- Baseline: Low — tested and included
- Balanced: Medium — tested and included
- Intensive: High — tested and included
Scores by game
What this result shows
Strongest included setting: Low (26.9).
Across included settings, the highest game score is Hex (38.9); the lowest is International Draughts (36.8). 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
- stepfun/step-3.7-flash
- 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 59 indexed attempts)
Generation evidence
- Low: 4 contributing player programs across 4 games
- Medium: 4 contributing player programs across 4 games
- High: 5 contributing player programs across 5 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 | 9.7–9.7 |
| Game of the Amazons | high | 1 | 1 | 29.6–29.6 |
| Game of the Amazons | low | 1 | 1 | 33.5–33.5 |
| Go | high | 1 | 1 | 9.8–9.8 |
| Hex | high | 1 | 1 | 40.0–40.0 |
| Hex | low | 1 | 1 | 33.5–33.5 |
| Hex | medium | 1 | 1 | 43.1–43.1 |
| International Draughts | high | 1 | 1 | 36.0–36.0 |
| International Draughts | low | 1 | 1 | 46.6–46.6 |
| International Draughts | medium | 1 | 1 | 27.8–27.8 |
| Tumbleweed | high | 1 | 1 | 18.7–18.7 |
| Tumbleweed | low | 1 | 1 | 14.3–14.3 |
| Xiangqi | medium | 1 | 1 | 13.8–13.8 |
Program ranges describe the retained competitors on this release scale, not a statistical estimate of a fresh generation.
Failures and budgets
11 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
High: 0% / 63% / 37% · n 8Medium: 0% / 50% / 50% · n 8Low: 38% / 12% / 50% · n 8 All three benchmark settings testedMany programs needed repairMany programs failedGeneration cost
$0.04average estimated cost per game and reasoning setting
- Median
- $0.03
- Range
- $0.0098–$0.11
- Known cost subtotal (incomplete or unverified charges)
- $1.00
- Cost data
- 24 combinations · 24 runs
- Price source
- Provider-reported
- Price list
- Not recorded for this older data
- Average output
- 33k tokens
- Output range
- 6.7k–93k 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