Does Quizgecko turn study material into a quiz?
Quizgecko generated English and Hindi multiple-choice quizzes covering all six core ideas, with correct keys and clearly incorrect alternatives. Both displayed formatting code around numbers, and the Hindi content stayed in Hindi. Repetition involved one confirmed pair and two further reported pairs in English, and one pair in Hindi.
2 of 2 test cases passed
Every test case in this scenario has a result.
The 2 test cases
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on these test cases.
Study material to an ordinary multiple-choice quizPassEvidence
We uploaded the English Electric Circuits chapter from Foundation Science 8 in Generate, selected multiple-choice questions in Configure, and generated the course.
The tool's response has no text to quote: it is what the evidence under Proofs shows.
Proof 1 · Screen recording · ▶ 1:35–1:36; ▶ 1:24–1:30; ▶ 2:12–4:44
| ✓ | Expected: Clear, answerable, source-supported multiple-choice questions with correct keys, unambiguously incorrect alternatives, and no core idea omitted through redundant coverage.Found: The 53 four-option questions covered all six ideas. Questions were chapter-supported and answerable; the answers shown were correct, with clearly incorrect alternatives and explanations. |
The required question form, answer quality and chapter coverage held. Repetition did not leave a core idea uncovered, and formatting code left the numbers legible and the keys correct.
Formatting code in English answers. In the three-lamp ammeter question, the options and explanation show formatting code around 0.18 A; the question itself displays the number normally.
Repeated English questions. Questions 47 and 51 both test placing a safety device in series to interrupt the circuit. Two further pairs were reported as repetitive: questions 12 and 14, and questions 13 and 18.
Same-language quiz from same-language materialPassEvidence
We uploaded the Hindi Electric Circuits chapter from Foundation Science 8 and selected multiple-choice questions. We chose Hindi explicitly and added an instruction forbidding English mixing or translation before generating the course.
The tool's response has no text to quote: it is what the evidence under Proofs shows.
Proof 2 · Screen recording · ▶ 1:40–1:55; ▶ 2:50–3:44
| ✓ | Expected: Hindi-only multiple-choice content without meaning changes: clear, answerable, source-supported questions, correct keys, unambiguously incorrect alternatives, and core-idea coverage without repetition displacing an idea.Found: The 33 four-option questions used Hindi throughout, including options and explanations. Questions were chapter-supported and answerable, with correct answers shown, clearly incorrect alternatives and all six ideas covered. |
The Hindi quiz met the language and question-quality requirements while covering all six ideas. Its repeated fact was isolated, not a case of replacing another core idea.
Repeated Hindi questions. Questions 15 and 30 of the Hindi quiz both restate the fact that an extra lamp in series lowers the current.
Dollar signs in Hindi answers. In the Hindi quiz’s parallel-current questions 22 and 23, numeric options and explanations retain dollar-sign formatting while the question text displays the numbers normally.
Hindi question cap exceeded. The Hindi quiz contains 33 questions despite the selected maximum of 30.
Configuration and setup
How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.
- Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
- Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
- Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.
Where this sits in the benchmark
This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.
| Level | Name | Scope |
|---|---|---|
| Benchmark | Quiz Generation → | 15 scenarios · 10 tools |
| Capability | Quiz Generation → | |
| Scenario | The user turns study material into a quiz → | |
| Tool | Quizgecko → |
Global scenario definition → · Global capability definition → · Quizgecko product page →
History of this result
What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.
Act on this result
Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.
You run the same kind of test against your own setup and get the same behaviour.
Agree →Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Something here is wrong — a reference value, a transcription, a grade.
Report an issue →Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.
Verify the proof files
These files support this result. Open a file to inspect the original evidence.
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.