alleryStart learning →Approximate context window of Claude 4?
- 20K tokens
- 2M tokens
- 200K tokens
- Unlimited
Show answer and solution
Correct answer: C. 200K tokens
Claude 4 holds roughly 200K tokens (around 150K words) per call.
Claude AI Claudeai Long Context — practice questions
Explore 3 free Claudeai Long Context questions in Claude AI Claudearchitect. Open each question or exercise to read its content, reference answers and available explanation.
Practise Claudeai Long Context with Quill →Claudeai Long Context questions and exercises with answers
Showing questions 1–3 of 3.
Worked practice questions
Where in a long prompt is recall WEAKEST?
- The very start
- The very end
- Length does not matter
- The middle
Show answer and solution
Correct answer: D. The middle
**Lost-in-the-middle:** items at the start and end of a long prompt are recalled best
the middle gets fuzzy.
Put key facts at the ends.
Fix the long prompt claims
Read exercise and reference answers
- Questions
- Statement parts
- Claude
- 4
- holds
- roughly
- 20K
- tokens
- per
- call
- Correction
- 200K
- Incorrect part
- 20K
- Statement parts
- Recall
- is
- weakest
- at
- the
- start
- of
- a
- long
- prompt
- Correction
- middle
- Incorrect part
- start
- Statement parts
- Put
- the
- key
- facts
- in
- the
- middle
- Correction
- at the ends
- Incorrect part
- middle
- Instructions
- Tap the one wrong word in each line about how a long prompt is read, then see the fix.
_Source: Qallery verified question bank, Claude Architect, topic claudeai_long_context_
How to practise
- Choose a Claudeai Long Context question and try to work out your answer.
- Open the question to check the correct answer and read its worked solution.
- Continue in the app for bite-sized lessons, explanations and review with Quill. You can start without creating an account.