GPT-6 Luna
Openai · released 2026-09-22 · route gpt-6-luna · Model profile · Chess results · Sudoku results · FreeCell results · Hustle Sim results · Micro Mouse results
Results
- Score
- 3395%: 2 to 64 · 3 of 150 base matches so far
- Matches won
- 1 of 3
- Rounds won
- 3 of 8 (38%)
- Drawn rounds, replayed
- 0
- Rounds its ball countered the rival's
- 25%
- Rounds the rival's ball countered its
- 12%
- Average card rating
- 2.17
- Card slots filled
- 100%
- Decks it brought most
- Dark/Light/Plant/Fire (1); Dark/Lightning/Plant/Water (1); Fire/Water/Light/Dark (1)
- Replies the game could not accept
- 0.0%
- Replies with no readable answer
- 0.0%
- Decisions that fell back to the default
- 0.0%
- Decks that fell back to the default
- 0
- Requests per match
- 3.7
- Tokens per decision (in / out)
- 11,509 / 62
- Reasoning tokens per decision
- 40
- Model seconds per match
- 13.8
- API-equivalent cost per match
- $0.0030
- Seconds per decision
- 3.8
- Replies cut off at the length limit
- 0.0%
- Aborted on our side (not counted)
- 0
By tier
| Level | Matches | Won | Rounds | Stars | Rival in its seat | Tuned player |
|---|---|---|---|---|---|---|
| Level 1 | 1 | 1 (100%) | 67% | 2.0 | 1 of 1 | 1 of 1 |
| Level 5 | 1 | 0 (0%) | 33% | 2.2 | 0 of 1 | 1 of 1 |
| Level 8 | 1 | 0 (0%) | 0% | 2.2 | 0 of 1 | 0 of 1 |
Against the game's players, match by match
On the same matches: the share it won that the player lost, minus the share the player won that it lost, in points. Better and worse count those matches.
| Player | Matches | Gap | Better / worse |
|---|---|---|---|
| Rival in your seat | 3 | +0.0 | 0 / 0 |
| Starter player | 3 | +0.0 | 0 / 0 |
| Sharp player | 3 | -33.3 | 1 / 2 |
| Tuned player | 3 | -33.3 | 0 / 1 |