GPT-6 Luna
Openai · released 2026-09-22 · route gpt-6-luna · Model profile · Chess results · Sudoku results · Mines results · FreeCell results · Hustle Sim results · Elemental Armory results · Micro Mouse results
Results
- Score
- 10095%: 69 to 100 · 3 of 12 base wars so far
- Wars won
- 3 of 3
- Won / lost / timed out
- 3 / 0 / 0
- Share of the world held at the end, on average
- 73.1%
- Decisions per war
- 62.0
- Orders sent per decision
- 3.58
- Orders the game refused
- 33 of 665 (5.0%)
- Refused orders per decision
- 0.18
- Decisions with no readable orders
- 0.0%
- Retries for a reply with no orders tag
- 0
- Model minutes per war
- 6.6
- Tokens per decision (in / out)
- 12,376 / 373
- Reasoning tokens per decision
- 321
- Game build
- 0.91.0+e426bd2
- API-equivalent cost per war
- $0.040
- Seconds per decision
- 6.4
- Replies cut off at the length limit
- 0.0%
- Aborted on our side (not counted)
- 1
By tier
| Tier | Wars | Score | Won / lost / timed out | Held | Median win | Reference player |
|---|---|---|---|---|---|---|
| Easy | 1 | 100 | 1 / 0 / 0 | 77% | 4:04 | 100 |
| Medium | 1 | 100 | 1 / 0 / 0 | 71% | 5:55 | 0 |
| Hard | 1 | 100 | 1 / 0 / 0 | 71% | 5:29 | 0 |
| Extreme | 0 | n/a | 0 / 0 / 0 | n/a | n/a | n/a |
Against the game's players, war by war
Its war score minus each player's on the same wars, in points out of 100. Better and worse count the wars where it scored higher or lower.
| Player | Wars | Gap | Better / worse |
|---|---|---|---|
| Reference player | 3 | +66.7 | 2 / 0 |
| Reference on the model's clock | 3 | +66.7 | 2 / 0 |
| Sharp persona | 3 | +33.3 | 1 / 0 |
| Median persona | 3 | +65.8 | 2 / 0 |
| Tourist persona | 3 | +98.3 | 3 / 0 |