Model summary · Edition 1.1

GPT-6 SolHigh

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 10of 20 models
Question score: 18.03 Lower is better. 95% confidence interval 16.29 to 19.77.
Rounds solved: 30 of 30 0 format errors
Guesser cost per round: $0.0398 Model time 1m 4s.

See how GPT-6 Sol (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: 2nd of 20 models, average 8.33 questions. round 1, round 2, round 3
Eyebrow: 5th of 20 models, average 13.33 questions. round 1, round 2, round 3

Lowest ranks vs other models

Albert Schweitzer: 17th of 20 models, average 31.33 questions. round 1, round 2, round 3
Albert Einstein: 15th of 20 models, average 11.33 questions. round 1, round 2, round 3

Single rounds

Fewest questions in a solved round: 7, on Moon. round 2
Most questions in a solved round: 40, on Door handle. round 2
Largest spread between rounds: Door handle, from 22 to 40 questions. round 1, round 2, round 3
1 wrong guess in 30 rounds, on Eyebrow. round 3

Failed rounds and format errors

Every round was solved, and every reply used the required format.

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	11.33	15 of 20	3 of 3	10, 11, 13
Albert Schweitzer	31.33	17 of 20	3 of 3	30, 28, 36
Garfield	13.00	11 of 20	3 of 3	13, 13, 13
Achilles	9.00	13 of 20	3 of 3	9, 9, 9
Genghis Khan	12.67	11 of 20	3 of 3	11, 14, 13
Bike pump	34.00	10 of 20	3 of 3	34, 38, 30
Spider web	17.00	6 of 20	3 of 3	16, 19, 16
Eyebrow	13.33	5 of 20	3 of 3	13, 16, 11
Moon	8.33	2 of 20	3 of 3	9, 7, 9
Door handle	30.33	13 of 20	3 of 3	22, 40, 29

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-M0029-001, completed 26 Sep 2026.