- Score · relative 0–100
- 82.9
- Rank
- 6
- Status
- Partial 3/3
- Players generated
- 2026-10-24
- Match evidence updated
- 2026-10-24
- Results published
Why this result is partial: fixed opponent-and-seat coverage is incomplete. The rank uses the available reasoning-setting results.
Scores by reasoning setting
Available settings and grouping
Available settings
Checked on 2026-10-23 · Provider documentation
How settings are grouped
- Baseline: Low — tested and included
- Balanced: High — tested and included
- Intensive: Max — tested and included
Scores by game
What this result shows
Strongest included setting: Max (85.7).
Across included settings, the highest game score is Tumbleweed (92.9); the lowest is Go (66.0). Each game counts every generation attempt, a failed one as 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
- moonshotai/kimi-k3.1-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
- 943718 (24 of 24 indexed attempts)
Generation evidence
- Low: 8 contributing player programs across 8 games
- High: 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 | highest | 1 | 1 | 79.7–79.7 |
| Chess | medium | 1 | 1 | 76.0–76.0 |
| Chess | none | 1 | 1 | 82.6–82.6 |
| Game of the Amazons | highest | 1 | 1 | 74.6–74.6 |
| Game of the Amazons | medium | 1 | 1 | 85.1–85.1 |
| Game of the Amazons | none | 1 | 1 | 80.0–80.0 |
| Go | highest | 1 | 1 | 93.2–93.2 |
| Go | medium | 1 | 1 | 61.3–61.3 |
| Go | none | 1 | 1 | 43.5–43.5 |
| Hex | highest | 1 | 1 | 90.4–90.4 |
| Hex | medium | 1 | 1 | 81.0–81.0 |
| Hex | none | 1 | 1 | 84.7–84.7 |
| International Draughts | highest | 1 | 1 | 85.4–85.4 |
| International Draughts | medium | 1 | 1 | 92.1–92.1 |
| International Draughts | none | 1 | 1 | 92.1–92.1 |
| Shogi | highest | 1 | 1 | 87.3–87.3 |
| Shogi | medium | 1 | 1 | 88.7–88.7 |
| Shogi | none | 1 | 1 | 88.8–88.8 |
| Tumbleweed | highest | 1 | 1 | 91.4–91.4 |
| Tumbleweed | medium | 1 | 1 | 91.7–91.7 |
| Tumbleweed | none | 1 | 1 | 95.6–95.6 |
| Xiangqi | highest | 1 | 1 | 83.8–83.8 |
| Xiangqi | medium | 1 | 1 | 82.2–82.2 |
| Xiangqi | none | 1 | 1 | 78.9–78.9 |
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: 30 recorded one-sided faults across contributing program rows. A crash or illegal move pinned on one program also counts as that program's loss in its match record; other faults, such as timeouts, are left out of 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: 100% / 0% / 0% · n 8High: 100% / 0% / 0% · n 8Low: 100% / 0% / 0% · n 8 All three benchmark settings testedGeneration cost
$0.28average estimated cost per game and reasoning setting
- Median
- $0.23
- Range
- $0.09–$0.52
- Provider-reported total
- $6.68
- Cost data
- 24 combinations · 24 runs
- Price source
- Provider-reported
- Price list
- boardgame-list-prices-2026-10-09
- Average output
- 26k tokens
- Output range
- 7.9k–50k 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