Model results
GPT-6 Luna
OpenAI · Overall Models
- Score · relative 0–100
- 32.4
- Rank
- 42
- Status
- Partial 3/3
- Rank change
- Baseline
- Players generated
- 2026-09-22 – 2026-09-22
- Match evidence updated
- 2026-09-26
- Results published
- 2026-09-26T08:55:16Z
- Settings tested
- All three benchmark settings tested
Why this result is partial: the official generation cohort is incomplete. The rank uses the available reasoning-setting results.
What this result shows
Strongest included setting: XHigh (44.0).
Across included settings, the highest game score is Hex (48.6); the lowest is Chess (19.4). 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
- gpt-6-luna
- Provider route (catalog)
- openai
- 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
- 65536 (24 of 24 indexed attempts)
Generation evidence
- None: 7 contributing player programs across 7 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 | 11.6–11.6 |
| Chess | none | 1 | 1 | 11.9–11.9 |
| Chess | xhigh | 1 | 1 | 34.6–34.6 |
| Game of the Amazons | medium | 1 | 1 | 41.9–41.9 |
| Game of the Amazons | xhigh | 1 | 1 | 34.8–34.8 |
| Go | medium | 1 | 1 | 35.2–35.2 |
| Go | none | 1 | 1 | 21.6–21.6 |
| Go | xhigh | 1 | 1 | 30.3–30.3 |
| Hex | medium | 1 | 1 | 47.0–47.0 |
| Hex | none | 1 | 1 | 45.8–45.8 |
| Hex | xhigh | 1 | 1 | 52.8–52.8 |
| International Draughts | medium | 1 | 1 | 33.9–33.9 |
| International Draughts | none | 1 | 1 | 26.4–26.4 |
| International Draughts | xhigh | 1 | 1 | 78.8–78.8 |
| Shogi | medium | 1 | 1 | 30.6–30.6 |
| Shogi | none | 1 | 1 | 27.5–27.5 |
| Shogi | xhigh | 1 | 1 | 31.4–31.4 |
| Tumbleweed | medium | 1 | 1 | 17.4–17.4 |
| Tumbleweed | none | 1 | 1 | 21.3–21.3 |
| Tumbleweed | xhigh | 1 | 1 | 53.1–53.1 |
| Xiangqi | medium | 1 | 1 | 18.3–18.3 |
| Xiangqi | none | 1 | 1 | 11.2–11.2 |
| Xiangqi | xhigh | 1 | 1 | 36.0–36.0 |
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; 1 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.
Scores by reasoning setting
| Tested setting | Score | Result status | Display group |
|---|---|---|---|
| None | 23.7 | Tested and included | Baseline |
| Medium | 29.5 | Tested and included | Balanced |
| XHigh | 44.0 | Tested and included | Intensive |
Available settings and grouping
Available settings
Checked on 2026-09-22 · Provider documentation
How settings are grouped
- Baseline: None — tested and included
- Balanced: Medium — tested and included
- Intensive: XHigh — tested and included
Player program results
XHigh: 100% / 0% / 0% · n 8Medium: 100% / 0% / 0% · n 8None: 100% / 0% / 0% · n 7 All three benchmark settings testedGeneration cost
- Average estimated cost
- $0.0061
- Median estimated cost
- $0.0039
- Estimated range
- $0.0016–$0.01
- Cost data
- 23 combinations / 23 recorded runs
- Known cost subtotal (incomplete or unverified charges)
- $0.14
- Price source
- Standard list-price estimate
- Price list
- boardgame-list-prices-2026-09-08
- Average output
- 10k tokens
- Output range
- 1.4k–27k tokens
- Runs with output-token evidence
- 23
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 evidence below