Deep20Bench
v1.0Previous

Benchmark edition

Edition 1.0 settings

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

Round 5

Round 5

Did not identify Genghis Khan after 50 counted questions.

Back to all Genghis Khan rounds
Questions
50 Scored as 51
Outcome
Question limit reached
Format errors
No errors
Duration
4m 5s
Round cost
$0.1235 All 51 turns

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":"XSZW5TRZ"}

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 primarily known for their work in the entertainment industry?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Is the person primarily known for their work in the entertainment industry?"}}
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 a historical figure?

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

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

2 · Answer check returns Yes
Q4
1 · Guesser asks

Did the person hold significant political power or office?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person hold significant political power or office?"}}
Oracle evidence2 model-reported sources

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

2 · Answer check returns Yes
Q5
1 · Guesser asks

Was the person a head of state?

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

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

2 · Answer check returns Yes
Q6
1 · Guesser asks

Was the person from the United States of America?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Was the person from the United States of America?"}}
Oracle evidence1 model-reported source

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

2 · Answer check returns No
Q7
1 · Guesser asks

Did the person rule in or before the 20th century?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person rule in or before the 20th century?"}}
Oracle evidence1 model-reported source

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

2 · Answer check returns Yes
Q8
1 · Guesser asks

Was the person a monarch or emperor?

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

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

2 · Answer check returns Yes
Q9
1 · Guesser guesses

Napoleon Bonaparte

French military leader and emperor

Validator rationale The proposal identifies Napoleon Bonaparte, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"French military leader and emperor","name":"Napoleon Bonaparte","question":null}}
2 · Validator returns No
Q10
1 · Guesser asks

Did the person have a significant impact on European history?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Did the person have a significant impact on European history?"}}
Oracle evidence2 model-reported sources

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

Source 01
The Mongol invasion of Europe in 1241–1242 was a series of military campaigns led by the Mongol Empire... This event is considered a turning point, likely saving much of Europe from permanent Mongol dominion.
Open britannica.com
2 · Answer check returns Yes
Q11
1 · Guesser guesses

Charlemagne

King of the Franks and Emperor of the Romans

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Charlemagne, a different historical person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of the Franks and Emperor of the Romans","name":"Charlemagne","question":null}}
2 · Validator returns No
Q12
1 · Guesser asks

Was the person known by a regnal name or number?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Was the person known by a regnal name or number?"}}
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 guesses

Louis XIV

King of France

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Louis XIV, a different historical person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of France","name":"Louis XIV","question":null}}
2 · Validator returns No
Q14
1 · Guesser asks

Was the person Russian?

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

Was the person British?

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

Was the person's reign marked by significant military conquests or reforms?

Recorded Guesser outputRequired JSON format
{"result":{"action":"ASK","description":null,"name":null,"question":"Was the person's reign marked by significant military conquests or reforms?"}}
Oracle evidence1 model-reported source

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

2 · Answer check returns Yes
Q17
1 · Guesser guesses

Peter the Great

Russian Tsar known for modernizing Russia

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Peter the Great.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Russian Tsar known for modernizing Russia","name":"Peter the Great","question":null}}
2 · Validator returns No
Q18
1 · Guesser guesses

Charles V, Holy Roman Emperor

Holy Roman Emperor and ruler of the Habsburg lands

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Charles V, Holy Roman Emperor; they are different historical figures.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Holy Roman Emperor and ruler of the Habsburg lands","name":"Charles V, Holy Roman Emperor","question":null}}
2 · Validator returns No
Q19
1 · Guesser guesses

Philip II of Spain

King of Spain and ruler of the Spanish Empire

Validator rationale The proposal identifies Philip II of Spain, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of Spain and ruler of the Spanish Empire","name":"Philip II of Spain","question":null}}
2 · Validator returns No
Q20
1 · Guesser guesses

Francis II, Holy Roman Emperor

Last Holy Roman Emperor

Validator rationale The proposal identifies Francis II, the last Holy Roman Emperor, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Last Holy Roman Emperor","name":"Francis II, Holy Roman Emperor","question":null}}
2 · Validator returns No
Q21
1 · Guesser guesses

Otto von Bismarck

Prime Minister of Prussia and Chancellor of Germany

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Otto von Bismarck.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Prime Minister of Prussia and Chancellor of Germany","name":"Otto von Bismarck","question":null}}
2 · Validator returns No
Q22
1 · Guesser guesses

Philip II of Macedon

King of Macedon and father of Alexander the Great

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Philip II of Macedon.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of Macedon and father of Alexander the Great","name":"Philip II of Macedon","question":null}}
2 · Validator returns No
Q23
1 · Guesser guesses

Ashoka

Indian emperor

Validator rationale The proposal identifies Ashoka, an Indian emperor, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Indian emperor","name":"Ashoka","question":null}}
2 · Validator returns No
Q24
1 · Guesser guesses

Francis II

Holy Roman Emperor

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Francis II, Holy Roman Emperor.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Holy Roman Emperor","name":"Francis II","question":null}}
2 · Validator returns No
Q25
1 · Guesser guesses

Napoleon III

French emperor and nephew of Napoleon Bonaparte

Validator rationale The proposal identifies Napoleon III, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"French emperor and nephew of Napoleon Bonaparte","name":"Napoleon III","question":null}}
2 · Validator returns No
Q26
1 · Guesser guesses

William the Conqueror

Duke of Normandy and King of England

Validator rationale The proposal identifies William the Conqueror, whereas the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Duke of Normandy and King of England","name":"William the Conqueror","question":null}}
2 · Validator returns No
Q27
1 · Guesser guesses

Joseph Stalin

Soviet leader

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Joseph Stalin, a different person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Soviet leader","name":"Joseph Stalin","question":null}}
2 · Validator returns No
Q28
1 · Guesser guesses

Otto I the Great

Holy Roman Emperor

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Otto I the Great, a different historical person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Holy Roman Emperor","name":"Otto I the Great","question":null}}
2 · Validator returns No
Q29
1 · Guesser guesses

Henry VIII

King of England known for having six wives

Validator rationale The trusted subject is Genghis Khan, while the proposed identity is Henry VIII, a different historical person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of England known for having six wives","name":"Henry VIII","question":null}}
2 · Validator returns No
Q30
1 · Guesser guesses

Alexander the Great

King of Macedon and conqueror

Validator rationale The trusted subject is Genghis Khan (Temüjin), while the proposal names Alexander the Great, a different historical person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of Macedon and conqueror","name":"Alexander the Great","question":null}}
2 · Validator returns No
Q31
1 · Guesser guesses

Joseph II, Holy Roman Emperor

Holy Roman Emperor known for reforms

Validator rationale The proposal identifies Joseph II, Holy Roman Emperor, not Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Holy Roman Emperor known for reforms","name":"Joseph II, Holy Roman Emperor","question":null}}
2 · Validator returns No
Q32
1 · Guesser guesses

Frederick the Great

King of Prussia

Validator rationale The trusted subject is Genghis Khan (Temüjin), while the proposal identifies Frederick the Great, King of Prussia.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of Prussia","name":"Frederick the Great","question":null}}
2 · Validator returns No
Q33
1 · Guesser guesses

Charles I of England

King of England, Scotland, and Ireland

Validator rationale The trusted subject is Genghis Khan (Temüjin), while the proposal identifies Charles I of England, a different person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of England, Scotland, and Ireland","name":"Charles I of England","question":null}}
2 · Validator returns No
Q34
1 · Guesser guesses

George Washington

First President of the United States was not correct, but a prominent historical figure; guessing another prominent historical figure.

Validator rationale The proposal identifies George Washington, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"First President of the United States was not correct, but a prominent historical figure; guessing another prominent historical figure.","name":"George Washington","question":null}}
2 · Validator returns No
Q35
1 · Guesser guesses

Adolf Hitler

Leader of Nazi Germany

Validator rationale The trusted subject is Genghis Khan, while the proposed identity is Adolf Hitler; they are different people.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Leader of Nazi Germany","name":"Adolf Hitler","question":null}}
2 · Validator returns No
Q36
1 · Guesser guesses

Julius Caesar

Roman general and statesman

Validator rationale The trusted subject is Genghis Khan (Temüjin), while the proposal identifies Julius Caesar, a different historical person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Roman general and statesman","name":"Julius Caesar","question":null}}
2 · Validator returns No
Q37
1 · Guesser guesses

Napoleon III

French emperor

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Napoleon III, a different person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"French emperor","name":"Napoleon III","question":null}}
2 · Validator returns No
Q38
1 · Guesser guesses

Philip II of Spain

King of Spain and ruler of the Spanish Empire

Validator rationale The trusted subject is Genghis Khan (Temüjin), while the proposed identity is Philip II of Spain; they are different people.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of Spain and ruler of the Spanish Empire","name":"Philip II of Spain","question":null}}
2 · Validator returns No
Q39
1 · Guesser guesses

Charles V

Holy Roman Emperor

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Charles V, Holy Roman Emperor, a different person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Holy Roman Emperor","name":"Charles V","question":null}}
2 · Validator returns No
Q40
1 · Guesser guesses

Catherine the Great

Russian empress

Validator rationale The proposal identifies Catherine the Great, a different person from Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Russian empress","name":"Catherine the Great","question":null}}
2 · Validator returns No
Q41
1 · Guesser guesses

Louis XVI

King of France executed during the French Revolution

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Louis XVI, a different person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of France executed during the French Revolution","name":"Louis XVI","question":null}}
2 · Validator returns No
Q42
1 · Guesser guesses

Francis I, Holy Roman Emperor

Holy Roman Emperor and Habsburg ruler

Validator rationale The proposal identifies Francis I, Holy Roman Emperor, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Holy Roman Emperor and Habsburg ruler","name":"Francis I, Holy Roman Emperor","question":null}}
2 · Validator returns No
Q43
1 · Guesser guesses

Otto von Bismarck

Prime Minister of Prussia and Chancellor of Germany

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Otto von Bismarck.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Prime Minister of Prussia and Chancellor of Germany","name":"Otto von Bismarck","question":null}}
2 · Validator returns No
Q44
1 · Guesser guesses

Gustav II Adolf

King of Sweden during the Thirty Years' War

Validator rationale The proposal identifies Gustav II Adolf, a Swedish king, while the trusted subject is Genghis Khan, founder of the Mongol Empire.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of Sweden during the Thirty Years' War","name":"Gustav II Adolf","question":null}}
2 · Validator returns No
Q45
1 · Guesser guesses

Francis II, Holy Roman Emperor

Last Holy Roman Emperor

Validator rationale The proposal identifies Francis II, the last Holy Roman Emperor, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Last Holy Roman Emperor","name":"Francis II, Holy Roman Emperor","question":null}}
2 · Validator returns No
Q46
1 · Guesser guesses

Peter the Great

Russian Tsar known for modernizing Russia

Validator rationale The trusted subject is Genghis Khan, while the proposed identity is Peter the Great, a different historical person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Russian Tsar known for modernizing Russia","name":"Peter the Great","question":null}}
2 · Validator returns No
Q47
1 · Guesser guesses

Charles I of England

King of England, Scotland, and Ireland

Validator rationale The trusted subject is Genghis Khan, while the proposal identifies Charles I of England, a different person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of England, Scotland, and Ireland","name":"Charles I of England","question":null}}
2 · Validator returns No
Q48
1 · Guesser guesses

Napoleon Bonaparte

French military leader and emperor

Validator rationale The proposal identifies Napoleon Bonaparte, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"French military leader and emperor","name":"Napoleon Bonaparte","question":null}}
2 · Validator returns No
Q49
1 · Guesser guesses

Joseph Stalin

Soviet leader

Validator rationale The trusted subject is Genghis Khan, while the proposed identity is Joseph Stalin, a different person.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Soviet leader","name":"Joseph Stalin","question":null}}
2 · Validator returns No
Q50
1 · Guesser guesses

William the Conqueror

Duke of Normandy and King of England

Validator rationale The proposal identifies William the Conqueror, whereas the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"Duke of Normandy and King of England","name":"William the Conqueror","question":null}}
2 · Validator returns No
G
1 · Guesser guessesNot counted

Philip II of Macedon

King of Macedon and father of Alexander the Great

Validator rationale The proposal identifies Philip II of Macedon, while the trusted subject is Genghis Khan.

Recorded Guesser outputRequired JSON format
{"result":{"action":"GUESS","description":"King of Macedon and father of Alexander the Great","name":"Philip II of Macedon","question":null}}
2 · Validator returns No