Model summary · Edition 1.1

GPT-6 LunaHigh

These results come from one run: 10 fixed subjects, 3 rounds each, a 40-question limit, and reasoning setting high. They do not predict results on other subjects or settings.

This page always shows the model’s newest ranked run.

See all 30 rounds → All models

Every question, answer, guess, and source.

Rank: Rank 16of 20 models
Question score: 21.17 Lower is better. 95% confidence interval 18.18 to 24.15.
Rounds solved: 24 of 30 0 format errors
Guesser cost per round: $0.0031 Model time 1m 11s.

See how GPT-6 Luna (high) played. All 30 rounds, with every question, answer, guess, and source.

Observations

What stood out in this run.

Counts and ranks from this run only. A subject rank compares this model’s average on that subject with every other model in this edition. Each item links to its rounds.

Best ranks vs other models

Moon: 6th of 20 models, average 9.33 questions. round 1, round 2, round 3
Albert Einstein: 6th of 20 models, average 10.00 questions. round 1, round 2, round 3

Lowest ranks vs other models

Eyebrow: 18th of 20 models, average 31.33 questions. round 1, round 2, round 3
Bike pump: 17th of 20 models, average 41.00 questions. round 1, round 2, round 3

Single rounds

Fewest questions in a solved round: 8, on Albert Einstein. round 3
Most questions in a solved round: 39, on Eyebrow. round 1
Largest spread between rounds: Eyebrow, from 14 to 41 questions. round 1, round 2, round 3
9 wrong guesses in 30 rounds, up to 2 in one round on Eyebrow. round 1

Failed rounds and format errors

Not solved: Albert Schweitzer. Question limit reached after 40 questions; scored as 41. round 3
Not solved: Bike pump. Question limit reached after 40 questions; scored as 41. round 1
Not solved: Bike pump. Question limit reached after 40 questions; scored as 41. round 2
Not solved: Bike pump. Question limit reached after 40 questions; scored as 41. round 3
Not solved: Eyebrow. Question limit reached after 40 questions; scored as 41. round 2
Not solved: Door handle. Question limit reached after 40 questions; scored as 41. round 1

Subjects

Results by subject.

Failed rounds count as 41 questions. Rank compares this subject's average with the other models in edition 1.1. Select a subject or a round to see the game.

Subject	Average questions	Subject rank	Solved	Rounds
Albert Einstein	10.00	6 of 20	3 of 3	11, 11, 8
Albert Schweitzer	30.67	16 of 20	2 of 3	21, 30, not solved
Garfield	14.33	15 of 20	3 of 3	20, 10, 13
Achilles	10.00	15 of 20	3 of 3	9, 12, 9
Genghis Khan	15.00	16 of 20	3 of 3	13, 15, 17
Bike pump	41.00	17 of 20	0 of 3	not solved, not solved, not solved
Spider web	17.67	7 of 20	3 of 3	16, 22, 15
Eyebrow	31.33	18 of 20	2 of 3	39, not solved, 14
Moon	9.33	6 of 20	3 of 3	8, 11, 9
Door handle	32.33	16 of 20	2 of 3	not solved, 31, 25

Runs

Runs of this model.

Each edition ranks only the newest complete run of a model. Earlier runs are not ranked and their details are not published.

Current run in edition 1.1: BX-20260926-B-0003-official-M0028-001, completed 26 Sep 2026.