Quiz generator from LLM output
Whether you are building e-learning content, onboarding material, or an evaluation dataset, turning a passage into good comprehension questions by hand is slow. This tool sends your LLM-generated content to your own OpenAI key and returns ready-to-use multiple-choice or short-answer questions, each grounded in the text you provide.
When to use this tool
Three scenarios where this saves meaningful time:
E-learning and training content. When an LLM drafts a course module or onboarding guide, you need comprehension questions to pair with the material. Generating them manually from a freshly written passage repeats the work. This tool reads the passage and produces questions grounded in exactly what was written, not general knowledge about the topic.
Spaced repetition review sets. Generate a larger bank of questions from a single passage — ten or fifteen — then present them across multiple sessions. Because questions are grounded in the same text, they test retention of the specific content rather than background knowledge.
Evaluation datasets. Short-answer mode produces question-answer pairs you can use as a starting eval dataset for other LLMs or RAG retrieval pipelines. Testing whether a different model can answer questions about the same source document is a meaningful quality signal.
How it works
On run, the tool makes a single request to
https://api.openai.com/v1/chat/completions. It instructs the model to read
your content and produce exactly the number and type of questions you asked for,
returning them in a clean, copyable format. For multiple-choice it includes four
options and marks the correct one; for short-answer it includes a model answer.
Everything happens directly between your browser and OpenAI — there is no Gera
backend in the loop, and your key is never stored.
Multiple choice vs short answer
| Format | Best for | Typical use |
|---|---|---|
| Multiple choice | Assessments, quizzes with automatic scoring | LMS, onboarding tests |
| Short answer | Eval datasets, discussion questions, study prompts | QA pipelines, study guides |
Multiple-choice questions include four options where one is marked correct. Short-answer questions include a model answer you can use as a rubric or ground truth.
Tips and notes
- Quiz one section at a time. Tight, focused passages produce sharper questions than a long mixed document.
- Review before publishing. Skim the generated answers; occasionally a distractor option is too close to correct, and you may want to tweak it.
- Use short-answer for eval sets. The question-answer pairs make a quick starting dataset for testing other models or RAG retrieval against the same source.
- Increase count for spaced practice. More questions per passage gives you a bank you can rotate through across multiple review sessions.
- Keep inputs under a few thousand words. Very long passages cost more tokens and may cause the model to produce generic questions about the topic rather than specific questions about the passage — chunking avoids this.