Deep20Bench
v1.0Previous

Benchmark edition

Edition 1.0 settings

7 subjects5 rounds per subject50 question limit
Question answersYesNoUnknown
What changed
Source
Menu
Round

Round 1

Round 1

Did not identify Stephen King after 50 counted questions.

Back to all Stephen King rounds
Questions
50 Scored as 51
Outcome
Too many format errors
Format errors
Errors found View one example
Duration
14m 53s
Round cost
$0.6229 All 51 turns

Format warning

The model sent replies in the wrong format.

The Guesser sent 1 invalid reply. Each one before the question limit used up a counted turn. The model was only reminded of the required format; it was never told whether its question or guess was correct.

Valid format
98.0%
Format errors
1
Turns used by format errors
1

Transcript

Questions and answers.

Turns are shown in the order they happened. Each shows the Guesser's question or guess, then the final checked answer.

Exact Guesser setupSystem message and BEGIN event

The Guesser received these messages at the start of the round. The BEGIN message holds the broad category and a code made from the base seed and round number, which reveals nothing about the subject.

System message
You are the Guesser being evaluated in a Twenty Questions benchmark.

One subject is hidden. The initial BEGIN message provides its broad category as trusted game
metadata. Identify the subject using as few counted questions as possible. ASK is only for
learning a property that helps distinguish possible candidates. Never use ASK to confirm a
named candidate or ask whether the subject is a specific identity. When you are ready to name
a candidate, use GUESS immediately. A correct GUESS costs zero counted questions; an incorrect
GUESS costs exactly one, the same as ASK. A GUESS must provide both a name and a short
identifying description. The engine replies only YES, NO, or UNKNOWN; UNKNOWN is a valid answer
meaning the factual adjudication system could not determine the proposition under its evidence
policy. Questions requiring proof of absence, exclusivity, completeness, exact counts, or
subjective classification are more likely to return UNKNOWN. Prefer direct, positively
verifiable properties when possible.

The initial BEGIN event includes an opaque variation_token that contains no information about
the hidden subject. Do not interpret, repeat, mention, or derive meaning from it. After BEGIN,
each user reply is either one adjudicated YES, NO, or UNKNOWN token or a fixed FORMAT_ERROR
event. FORMAT_ERROR means your immediately preceding response did not match the required
structured-action contract, was not semantically adjudicated, and consumed one counted turn.
Use the formats in that event and try again. Never infer that the attempted question or
guess was right or wrong.

At most 50 questions or rejected guesses are counted. After that limit you receive
one final guess-only opportunity. Format errors also consume counted turns. The provider wire
response is an object with exactly one `result` action. On the final opportunity ASK is
forbidden. Return only the required structured response. Do not include analysis, hidden
reasoning, or additional fields.
BEGIN event
{"category":"person","event":"BEGIN","variation_token":"EAQCORIU"}

Valid replies are shown in the required format. Rejected replies are shown separately, without provider or call IDs.

Q1
1 · Guesser asks

Is the person male?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person male?"}}
Oracle evidence1 model-reported source

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q2
1 · Guesser asks

Is the person a historical figure?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person a historical figure?"}}
2 · Answer check returns Unknown
Q3
1 · Guesser asks

Is the person still alive?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person still alive?"}}
Oracle evidence1 model-reported source

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q4
1 · Guesser asks

Is the person a politician?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person a politician?"}}
Oracle evidence1 model-reported source

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q5
1 · Guesser asks

Is the person an actor or entertainer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person an actor or entertainer?"}}
Oracle evidence1 model-reported source

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q6
1 · Guesser asks

Is the person primarily known for acting in films?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for acting in films?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q7
1 · Guesser asks

Is the person a musician or singer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person a musician or singer?"}}
2 · Answer check returns Unknown
Q8
1 · Guesser asks

Is the person a comedian?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person a comedian?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q9
1 · Guesser asks

Is the person primarily known for work in television?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for work in television?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q10
1 · Guesser asks

Is the person primarily known for sports or athletics?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for sports or athletics?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q11
1 · Guesser asks

Is the person known for performing music?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person known for performing music?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q12
1 · Guesser asks

Is the person a singer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person a singer?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q13
1 · Guesser asks

Is the person primarily known as a pop singer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a pop singer?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q14
1 · Guesser asks

Is the person primarily known as a rock musician or rock singer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a rock musician or rock singer?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q15
1 · Guesser reply rejectedTurn counted

Reply in the wrong format.

Invalid JSON · fixed format reminder sent

Why this reply was rejectedInvalid JSON · turn 15

The reply was not one complete, valid JSON object.

Recorded type
invalid_json
Turn
15
Counted
Yes · question 15
Feedback
FORMAT_ERROR
What the model returnedExact text from the provider
Attempt 1 · finish stop
{"result":{"action":"ASK","question":"Is the person known for hip-hop or rap music?","name":null,"description":null}}{"result":{"action":"ASK","question":"Is the person known for hip-hop or rap music?","name":null,"description":null}}
What a valid reply looks likeThe same formats shown to the Guesser
ASK
{"result":{"action":"ASK","description":null,"name":null,"question":"<non-empty yes-or-no property question>"}}
GUESS
{"result":{"action":"GUESS","description":"<non-empty identifying description>","name":"<non-empty candidate name>","question":null}}

A reply must match one of these formats exactly. Text fields in use must not be empty; unused fields must be JSON null.

2 · System responseFORMAT
Q16
1 · Guesser asks

Is the person primarily known as a country music singer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a country music singer?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q17
1 · Guesser asks

Is the person primarily known as a rapper or hip-hop artist?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a rapper or hip-hop artist?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q18
1 · Guesser asks

Is the person primarily known as an R&B singer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as an R&B singer?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q19
1 · Guesser asks

Is the person known for classical music or opera?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person known for classical music or opera?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q20
1 · Guesser asks

Is the person primarily known as a jazz musician or singer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a jazz musician or singer?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q21
1 · Guesser asks

Is the person a member of a famous band or musical group?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person a member of a famous band or musical group?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q22
1 · Guesser asks

Is the person associated with heavy metal or hard rock music?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with heavy metal or hard rock music?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q23
1 · Guesser asks

Is the person the lead singer of the band?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person the lead singer of the band?"}}
2 · Answer check returns Unknown
Q24
1 · Guesser asks

Is the person primarily known as a guitarist?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a guitarist?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q25
1 · Guesser asks

Is the person primarily known as a drummer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a drummer?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q26
1 · Guesser asks

Is the person American?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person American?"}}
Oracle evidence1 model-reported source

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q27
1 · Guesser asks

Is the person primarily known as a bassist?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a bassist?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q28
1 · Guesser asks

Is the person associated with thrash metal?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with thrash metal?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q29
1 · Guesser asks

Is the person associated with the band Metallica?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with the band Metallica?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q30
1 · Guesser guesses

James Hetfield

Lead vocalist and rhythm guitarist of the thrash metal band Metallica

Validator rationale The proposal identifies James Hetfield of Metallica, whereas the trusted subject is author Stephen King.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Lead vocalist and rhythm guitarist of the thrash metal band Metallica","name":"James Hetfield","question":null}}
2 · Validator returns No
Q31
1 · Guesser asks

Was the person ever a member of Metallica?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Was the person ever a member of Metallica?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

Source 01
In recap, the band members of Metallica since 1981 are: James Hetfield, Lars Ulrich, Dave Mustaine, Ron McGovney, Cliff Burton, Kirk Hammett, Jason Newsted, Robert Trujillo, and Bob Rock.
Open metalshout.com
2 · Answer check returns No
Q32
1 · Guesser asks

Is the person associated with the band Megadeth?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with the band Megadeth?"}}
Oracle evidence1 model-reported source

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q33
1 · Guesser asks

Is the person associated with the band Slayer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with the band Slayer?"}}
2 · Answer check returns Unknown
Q34
1 · Guesser asks

Is the person associated with the band Anthrax?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with the band Anthrax?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns Yes
Q35
1 · Guesser guesses

Joey Belladonna

Lead singer of the thrash metal band Anthrax

Validator rationale The proposed identity is Joey Belladonna, Anthrax's lead singer, which is a different person from Stephen King.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Lead singer of the thrash metal band Anthrax","name":"Joey Belladonna","question":null}}
2 · Validator returns No
Q36
1 · Guesser asks

Is the person a current or former member of Anthrax?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person a current or former member of Anthrax?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q37
1 · Guesser asks

Is the person primarily known as a vocalist?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a vocalist?"}}
Oracle evidence1 model-reported source

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q38
1 · Guesser asks

Is the person known for producing thrash metal music or related work rather than performing as a band member?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person known for producing thrash metal music or related work rather than performing as a band member?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q39
1 · Guesser asks

Is the person known for working as a music producer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person known for working as a music producer?"}}
2 · Answer check returns Unknown
Q40
1 · Guesser asks

Is the person primarily known as a songwriter or composer for thrash metal?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a songwriter or composer for thrash metal?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q41
1 · Guesser asks

Did the person play keyboards or another non-traditional thrash instrument?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person play keyboards or another non-traditional thrash instrument?"}}
2 · Answer check returns Unknown
Q42
1 · Guesser asks

Did the person become famous in the 1980s?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person become famous in the 1980s?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

2 · Answer check returns No
Q43
1 · Guesser asks

Is the person associated with the thrash metal scene as a journalist, author, or documentarian?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with the thrash metal scene as a journalist, author, or documentarian?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

Source 01
Anthrax’s album Among The Living was heavily inspired by Stephen King’s The Stand, and another track was inspired by his novella Apt Pupil.
Open nme.com
2 · Answer check returns No
Q44
1 · Guesser asks

Is the person associated with Metallica in a non-performing capacity such as manager, producer, orエンド engineer?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with Metallica in a non-performing capacity such as manager, producer, orエンド engineer?"}}
2 · Answer check returns Unknown
Q45
1 · Guesser asks

Is the person associated with the band Testament?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with the band Testament?"}}
2 · Answer check returns Unknown
Q46
1 · Guesser asks

Has the person performed as a guest or collaborator with Metallica?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Has the person performed as a guest or collaborator with Metallica?"}}
2 · Answer check returns Unknown
Q47
1 · Guesser asks

Is the person a member of a thrash metal band?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person a member of a thrash metal band?"}}
2 · Answer check returns Unknown
Q48
1 · Guesser asks

Did the person become famous in the 1990s or later?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person become famous in the 1990s or later?"}}
Oracle evidence2 model-reported sources

The Oracle reported these excerpts and URLs. They are not independently checked.

Source 02
On April 5, 1974... Carrie... becomes a bestseller... For King, Carrie kicks off a phenomenal writing career, one in which he would come to be known worldwide as the Master of Horror.
Open history.com
2 · Answer check returns No
Q49
1 · Guesser asks

Is the person known for being a DJ or for mixing metal music?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person known for being a DJ or for mixing metal music?"}}
2 · Answer check returns Unknown
Q50
1 · Guesser asks

Is the person associated with the band Exodus?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person associated with the band Exodus?"}}
2 · Answer check returns Unknown