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

Identified Albert Schweitzer in 17 counted questions.

Back to all Albert Schweitzer rounds
Questions
17
Outcome
Solved
Format errors
Errors found View one example
Duration
5m 37s
Round cost
$0.2350 All 18 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
94.4%
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 currently alive?

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

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

2 · Answer check returns No
Q2
1 · Guesser asks

Is the person primarily known for political leadership, such as being a head of state or prominent government official?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for political leadership, such as being a head of state or prominent government official?"}}
Oracle evidence2 model-reported sources

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

2 · Answer check returns No
Q3
1 · Guesser asks

Is the person primarily known for contributions to the sciences (including natural sciences, engineering, or mathematics)?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for contributions to the sciences (including natural sciences, engineering, or mathematics)?"}}
Oracle evidence2 model-reported sources

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

2 · Answer check returns No
Q4
1 · Guesser asks

Is the person primarily known for contributions to the arts (including visual arts, literature, music, or performing arts)?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for contributions to the arts (including visual arts, literature, music, or performing arts)?"}}
Oracle evidence2 model-reported sources

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

2 · Answer check returns No
Q5
1 · Guesser asks

Is the person primarily known for achievements in sports?

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

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

2 · Answer check returns No
Q6
1 · Guesser asks

Is the person primarily known as a religious or spiritual leader?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known as a religious or spiritual leader?"}}
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 primarily known for business or entrepreneurship, such as founding a company or being a corporate leader?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for business or entrepreneurship, such as founding a company or being a corporate leader?"}}
Oracle evidence2 model-reported sources

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

2 · Answer check returns No
Q8
1 · Guesser asks

Is the person primarily known for contributions to philosophy?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for contributions to philosophy?"}}
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 military leadership or involvement in wars?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for military leadership or involvement in wars?"}}
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 activism, humanitarian work, or campaigning for social or civil causes?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for activism, humanitarian work, or campaigning for social or civil causes?"}}
Oracle evidence1 model-reported source

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

2 · Answer check returns Yes
Q11
1 · Guesser asks

Did the person receive the Nobel Peace Prize?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person receive the Nobel Peace Prize?"}}
Oracle evidence1 model-reported source

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

2 · Answer check returns Yes
Q12
1 · Guesser asks

Is the person primarily known for civil rights activism?

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

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

2 · Answer check returns No
Q13
1 · Guesser asks

Did the person found the International Red Cross?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person found the International Red Cross?"}}
Oracle evidence1 model-reported source

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

2 · Answer check returns No
Q14
1 · Guesser asks

Was the person female?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Was the person female?"}}
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 asks

Did the person serve as Secretary-General of the United Nations?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person serve as Secretary-General of the United Nations?"}}
Oracle evidence2 model-reported sources

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

2 · Answer check returns No
Q16
1 · Guesser reply rejectedTurn counted

Reply in the wrong format.

Output limit exceeded · fixed format reminder sent

Why this reply was rejectedOutput limit exceeded · turn 16

The reply hit the output length limit before it was complete.

Recorded type
output_limit_exceeded
Turn
16
Counted
Yes · question 16
Feedback
FORMAT_ERROR
What the model returnedExact text from the provider

The provider returned no text.

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
Q17
1 · Guesser asks

Is the person a medical doctor (physician)?

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

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

2 · Answer check returns Yes
G
1 · Guesser guessesNot counted

Albert Schweitzer

Swiss physician, humanitarian, and Nobel Peace Prize laureate known for his medical missionary work in Africa

Validator rationale The proposed identity names Albert Schweitzer, matching the trusted subject exactly; the differing nationality wording does not change the identification.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Swiss physician, humanitarian, and Nobel Peace Prize laureate known for his medical missionary work in Africa","name":"Albert Schweitzer","question":null}}
2 · Validator returns Yes