Model summary · Edition 1.0

gpt-oss-120BHigh

These results come from one run: 7 fixed subjects, 5 rounds each, a 50-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 35 rounds → All models

Every question, answer, guess, and source.

Rank: Rank 6of 18 models
Question score: 13.63 Lower is better. 95% confidence interval 9.79 to 17.46.
Rounds solved: 33 of 35 46 format errors
Guesser cost per round: $0.0363 Model time 1m 32s.

See how gpt-oss-120B (high) played. All 35 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

Mario: best of 18 models, average 2.80 questions. round 1, round 2, round 3, round 4, round 5
Albert Einstein: 2nd of 18 models, average 5.40 questions. round 1, round 2, round 3, round 4, round 5

Lowest ranks vs other models

Genghis Khan: 15th of 18 models, average 17.20 questions. round 1, round 2, round 3, round 4, round 5
Achilles: 15th of 18 models, average 11.40 questions. round 1, round 2, round 3, round 4, round 5

Single rounds

Fewest questions in a solved round: 2, on Mario. round 2
Most questions in a solved round: 38, on Albert Schweitzer. round 2
Largest spread between rounds: Garfield, from 6 to 51 questions. round 1, round 2, round 3, round 4, round 5
7 wrong guesses in 35 rounds, up to 2 in one round on Garfield. round 2

Failed rounds and format errors

Not solved: Albert Schweitzer. Too many format errors after 50 questions; scored as 51. round 4
Not solved: Garfield. Too many format errors after 31 questions; scored as 51. round 4
46 format errors in 7 rounds. Each one before the question limit used a counted turn. Albert Schweitzer round 1, Albert Schweitzer round 2, Albert Schweitzer round 3, Albert Schweitzer round 4, Garfield round 4, Achilles round 4, Genghis Khan round 2

Subjects

Results by subject.

Failed rounds count as 51 questions. Rank compares this subject's average with the other models in edition 1.0. Select a subject or a round to see the game.

Subject	Average questions	Subject rank	Solved	Rounds
Albert Einstein	5.40	2 of 18	5 of 5	5, 6, 4, 6, 6
Albert Schweitzer	26.80	8 of 18	4 of 5	17, 38, 17, not solved, 11
Stephen King	12.00	3 of 18	5 of 5	10, 12, 12, 15, 11
Garfield	19.80	14 of 18	4 of 5	8, 19, 6, not solved, 15
Achilles	11.40	15 of 18	5 of 5	6, 8, 7, 28, 8
Genghis Khan	17.20	15 of 18	5 of 5	13, 24, 11, 22, 16
Mario	2.80	1 of 18	5 of 5	3, 2, 4, 2, 3

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 1.0: BX-20260728-official-M0002-011, completed 28 Jul 2026.
Edition 1.1: rank 18 of 20, question score 22.23. Different rules and subjects, so scores are not comparable across editions.