AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 19 November 2026

Can Studyglen turn study material into a quiz covering its core ideas?

Studyglen generated 20-question multiple-choice quizzes from both chapters, but neither met the quality requirements. The English quiz included a contradictory question, a second defensible option and a coverage gap; the Hindi quiz stayed in Hindi but keyed 0.35 A after a new branch was added, although 0.35 A was the total before it.

2 of 2 test cases failed

Every test case in this scenario has a result.

Pass rate0%0 of 2 gradable
Coverage2 of 2test cases with a result
0PassNo test case passed.
2FailMissed at least one thing it was expected to do; the reason and proof are with each test case below.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the 2 test cases below: what we sent, what we checked, what the tool returned, and the proof.

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 quizFailEvidence
What we sent

We uploaded the ten-page English electric-circuits chapter to Studyglen's quiz builder, selected only Multiple Choice, set the count to 20 and the language to English, and generated the quiz.

InputDocument (PDF)
Input PDF: the English electric-circuits chapter, including lamp failure in series and parallel
Open the PDF ↗
What the tool returned

The tool's response has no text to quote: it is what the evidence under Proofs shows.

Proof 5 · Screenshot

Proof 6 · Screenshot

Proof 3 · Screenshot

Proof 2 · Screenshot

Proof 4 · Screenshot

Proof 1 · Screenshot

Expected vs. Found
✗Expected: Multiple-choice questions must be clear, answerable and source-supported, with correct keys, no defensible distractors, and core-idea coverage without omission alongside repetition.Found: Question 9 assigns 1.5 V to an unintroduced component; Question 8 has two defensible answers. Questions 8 and 12 repeat voltage; parallel lamp failure is omitted.
Supporting proof
Proof 1Screenshot
Preview screenshot: the English quiz's title, source, 20-question count and unused regenerations
Open original ↗
Proof 2Screenshot
Screenshot: Question 1's ammeter question, options, marked answer, explanation and source passage
Open original ↗
Proof 3Screenshot
Screenshot: Question 8's household-wiring question, four options and marked answer
Open original ↗
Proof 4Screenshot
Screenshot: Question 9 introduces two components, asks about a third and marks 1.5 V
Open original ↗
Proof 5Screenshot
Screenshot: Question 12's branch-voltage question, options, marked answer and explanation
Open original ↗
Proof 6Screenshot
Screenshot: Question 13 tests lamp failure in series, with options, answer and source passage
Open original ↗
Proof 7Screenshot
Setup screenshot: the English source, language, multiple-choice selection and question count
Open original ↗
Proof 8Screen recording
Screen recording: quiz setup, generation and scrolling through the English quiz
Key moments
Open original ↗
Why this result

Producing the requested 20-question format was not enough: the quiz also needed clear questions, unambiguous choices and core-idea coverage. Question 9 asks about an unintroduced component, Question 8 permits another defensible answer, and branch voltage repeats while parallel lamp failure is omitted.

Also observed in this test case

Marked answers versus question quality. The English quiz's examined keys were correct against the chapter. Its defects concern question framing and topic coverage, not the answers marked right.

Tested by Anshika Gupta · evidence dated 22 October 2026
Same-language quiz from same-language materialFailEvidence
What we sent

We uploaded the Hindi edition of the electric-circuits chapter, explicitly selected Hindi in the quiz-language dropdown, selected only Multiple Choice, set the maximum to 20 and generated the quiz.

InputDocument (PDF)
Input PDF: the Hindi electric-circuits chapter and its rules for series and parallel circuits
Open the PDF ↗
What the tool returned

Hindi quiz: Question 1 श्रेणीक्रम और समांतर क्रम में बैटरी के विभवांतर का वितरण किस प्रकार अलग होता है? A दोनों में घटकों के बीच बाँटा जाता है B श्रेणीक्रम में पूरा मिलता है, समांतर क्रम में बाँटा जाता है C श्रेणीक्रम में बाँटा जाता है, समांतर क्रम में पूरा मिलता है Correct answer D दोनों में घटकों को पूरा मिलता है Hindi quiz: Question 4 समांतर क्रम में एक लैम्प की शाखा टूटने पर दूसरी शाखा के लैम्प पर क्या प्रभाव पड़ेगा? A वह पहले से अधिक चमक से जलेगा B वह पहले जैसी चमक से जलता रहेगा Correct answer C वह बहुत मुश्किल से जलेगा D वह भी बुझ जाएगा Hindi quiz: Question 10 and explanation समांतर परिपथ की दो शाखाएँ 0.22 A और 0.13 A धारा लेती हैं। नई शाखा जोड़ने पर बैटरी की कुल धारा के बारे में क्या होगा? A कुल धारा 0.09 A होगी और नई शाखा पर घटेगी B कुल धारा 0.35 A होगी और नई शाखा पर बढ़ेगी Correct answer C कुल धारा 0.13 A होगी और नई शाखा पर रुक जाएगी D कुल धारा 0.22 A होगी और नई शाखा पर समान रहेगी पहले कुल धारा 0.22 A + 0.13 A = 0.35 A है। नई शाखा अपनी धारा लेती है और पहले की शाखाओं की धारा घटाती नहीं, इसलिए कुल धारा बढ़ती है। Hindi quiz: Question 16 समांतर परिपथ की दो शाखाओं में अमीटर क्रमशः 0.24 A और 0.16 A पढ़ते हैं। संधि के पहले कुल धारा कितनी होगी? A 0.08 A B 0.24 A C 0.16 A D 0.40 A Correct answer

Transcribed from Proof 2 · Screenshot

Transcribed from Proof 3 · Screenshot

Transcribed from Proof 4 · Screenshot

Transcribed from Proof 5 · Screenshot

Expected vs. Found
✗Expected: Quiz content must stay in the specified language, with clear, answerable, supported multiple-choice questions, correct keys, unambiguous alternatives and core-idea coverage without omission alongside repetition.Found: The quiz content is Hindi. Question 10 keys 0.35 A after adding a branch; its explanation identifies 0.35 A as the total before addition and says it increases.
Supporting proof
Proof 1Screenshot
Preview screenshot: the Hindi quiz title, source, 20-question count and unused regenerations
Open original ↗
Proof 2Screenshot
Screenshot: Hindi Question 1's voltage-distribution question, four options, marked answer and explanation
Open original ↗
Proof 3Screenshot
Screenshot: Hindi Question 4's parallel lamp-failure question, options, marked answer and explanation
Open original ↗
Proof 4Screenshot
Screenshot: Hindi Question 10's added-branch question, four options, marked answer and contradictory explanation
Open original ↗
Proof 5Screenshot
Screenshot: Hindi Question 16 adds 0.24 A and 0.16 A, marking 0.40 A
Open original ↗
Proof 6Screen recording
Screen recording: Hindi quiz generation and Questions 1 through 20 with answers revealed
Key moments
Open original ↗
Proof 7Screenshot
Setup screenshot: Hindi selected and detected, multiple-choice questions and a maximum of 20
Open original ↗
Why this result

Hindi content and the 20-question format met the request; the answer key did not. In Question 10, 0.22 A plus 0.13 A gives 0.35 A before an added branch. The key wrongly gives 0.35 A afterwards while saying the total increases.

Also observed in this test case

Constructed numerical example. Question 10 uses 0.22 A, 0.13 A and 0.35 A, figures absent from either chapter. Studyglen constructed this numerical example rather than taking it from the study material.

Core ideas covered despite repetition. Question 4 covers parallel lamp failure and keys that the other lamp keeps its brightness. No core idea is omitted; Questions 10 and 16 repeat branch-current addition.

Tested by Anshika Gupta · evidence dated 22 October 2026

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.

Software that produced the output
Studyglen
Build or version
Not exposed by the hosted product
Plan or tier
Same-language quiz from same-language material: Free
Surface
Web app
Set up before the run
The ten-page Foundation Science chapter on electric circuits, in English for the first test case and in its Hindi edition for the second, had to teach a small set of core ideas, among them what one failed lamp does in series and in parallel. Studyglen was asked for an ordinary multiple-choice quiz in the material's own language: English for the first test case, Hindi for the second.
Quiz language
Study material to an ordinary multiple-choice quiz: English; Same-language quiz from same-language material: Hindi (explicitly selected; also detected)
Question type
Multiple Choice only
Question count
Study material to an ordinary multiple-choice quiz: 20; Same-language quiz from same-language material: 20 maximum
Source file
Study material to an ordinary multiple-choice quiz: Foundation-Science-8-Ch6-Electric-Circuits (1).pdf; Same-language quiz from same-language material: Foundation-Science-8-Ch6-Electric-Circuits-Hindi.pdf
Regenerations used
Study material to an ordinary multiple-choice quiz: Study material to an ordinary multiple-choice quiz: 0 used; Same-language quiz from same-language material: Same-language quiz from same-language material: 0 used
Tested
22 October 2026 · Anshika Gupta

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

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.

The rules
  • 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.

LevelNameScope
BenchmarkQuiz Generation →15 scenarios · 10 tools
CapabilityQuiz Generation →
ScenarioThe user turns study material into a quiz →
ToolStudyglen →

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.

from the publication record
20 November 2026First publishedQuiz Generation v1

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.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/quiz-generation/results/studyglen/the-user-turns-study-material-into-a-quiz · 0 pass · 2 fail · coverage 2/2 · graded 2026-11-19

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.

Study material to an ordinary multiple-choice quiz · Input · Document (PDF)220bc6e2dc7e6824ee5bb81ff8f24b17c234c2eb1463835468fdc77a602c3dff
Study material to an ordinary multiple-choice quiz · Proof 1 · Screenshot0c4d2a0dd24601367de010755fa728adbb94ced5c101a07d3dfd4a6b0a02680a
Study material to an ordinary multiple-choice quiz · Proof 2 · Screenshot954c20be3129fdf217d678d4fbb6bb6b64568ccf3b2bfa5b43761c824749ae51
Study material to an ordinary multiple-choice quiz · Proof 3 · Screenshot1a7f1009c3856032d3827566d419ec51ccbf728c5b095808a62d2e16c13cd9a4
Study material to an ordinary multiple-choice quiz · Proof 4 · Screenshota9d9ad2d4c245eedc1c36bae425b87a5802e2e73e1826b6e680d055f7513d944
Study material to an ordinary multiple-choice quiz · Proof 5 · Screenshot6731da5ba365d84e84c48cd7f0a60ab446dd0a5eb98dd7ead562b6acd8b98cf4
Study material to an ordinary multiple-choice quiz · Proof 6 · Screenshotd1199e5d414f302ce9d60fcf33517ca01a9c71a59a1e2bc04d03c01428f28ef5
Study material to an ordinary multiple-choice quiz · Proof 7 · Screenshot5a216cb5ebec43107df82f02f994a653a88d5ff17daf8aa0b3e0b92ea3e589d2
Study material to an ordinary multiple-choice quiz · Proof 8 · Screen recording277fe32ff4faab12067f00a6fb7f46df0bfd5a02be82fa3392172e5de65d868b
Same-language quiz from same-language material · Input · Document (PDF)c7d3a89c5f68c64f695380c1c5945a3b075b218586a7147d83bf2a36c4ea8495
Same-language quiz from same-language material · Proof 1 · Screenshot0d55d7891c958d2a1a51406bf80efea4f4dc69139221a72276527b5057e02957
Same-language quiz from same-language material · Proof 2 · Screenshot53336a809f83b85d7f4d75ccc026f58fa1377d2448378e4180c02dbe8d1e1547
Same-language quiz from same-language material · Proof 3 · Screenshota3b054714f206641dafcdb347ff9a511e0b2209bf4ada5f81ce28a65ea81a035
Same-language quiz from same-language material · Proof 4 · Screenshotf8da01dc68cd8a9393bf03b156fec8cc8b358114abe94283e6e1b40b2974de49
Same-language quiz from same-language material · Proof 5 · Screenshote7439da72097b653b966585cf0470532b946ce2ccae1d6ee49a72fcacec68d0f
Same-language quiz from same-language material · Proof 6 · Screen recordingeb6f7a245411fcf9ffce2da73b941919af1a6abedf3e7598bd35d1c7b17b671a
Same-language quiz from same-language material · Proof 7 · Screenshot416914da3dac0628f9171c30f291183b7fc46a1dfa6bfbe0f7f4b5b2f55df55c