Model summary · Edition 1.1

Claude Haiku 5.5High

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 → Compare this model All models

Every question, answer, guess, and source.

Rank: Rank 15of 21 models
Question score: 20.00 Lower is better. 95% confidence interval 17.10 to 22.90.
Rounds solved: 25 of 30 0 format errors
Guesser cost per round: $0.0046 Model time 1m 19s.

See how Claude Haiku 5.5 (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

Achilles: best of 21 models, average 5.67 questions. round 1, round 2, round 3
Garfield: best of 21 models, average 7.67 questions. round 1, round 2, round 3

Lowest ranks vs other models

Door handle: 19th of 21 models, average 35.67 questions. round 1, round 2, round 3
Genghis Khan: 19th of 21 models, average 18.33 questions. round 1, round 2, round 3

Single rounds

Fewest questions in a solved round: 5, on Garfield. round 1
Most questions in a solved round: 38, on Spider web. round 2
Largest spread between rounds: Albert Schweitzer, from 16 to 41 questions. round 1, round 2, round 3
13 wrong guesses in 30 rounds, up to 3 in one round on Bike pump. round 2

Failed rounds and format errors

Not solved: Albert Schweitzer. Too many format errors after 40 questions; scored as 41. round 2
Not solved: Bike pump. Too many format errors after 40 questions; scored as 41. round 1
Not solved: Bike pump. Too many format errors after 40 questions; scored as 41. round 2
Not solved: Door handle. Question limit reached after 40 questions; scored as 41. round 1
Not solved: Door handle. Too many format errors after 40 questions; scored as 41. round 2

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	8.33	3 of 21	3 of 3	11, 7, 7
Albert Schweitzer	25.33	13 of 21	2 of 3	16, not solved, 19
Garfield	7.67	1 of 21	3 of 3	5, 7, 11
Achilles	5.67	1 of 21	3 of 3	6, 6, 5
Genghis Khan	18.33	19 of 21	3 of 3	15, 15, 25
Bike pump	37.67	14 of 21	1 of 3	not solved, not solved, 31
Spider web	29.67	18 of 21	3 of 3	30, 38, 21
Eyebrow	23.00	17 of 21	3 of 3	32, 20, 17
Moon	8.67	4 of 21	3 of 3	8, 11, 7
Door handle	35.67	19 of 21	1 of 3	not solved, not solved, 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-20261023-B-0003-official-M0035-001, completed 23 Oct 2026.