AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 12 November 2026

Does QuestionWell target each learner's weaker topic based on past performance?

QuestionWell did not personalize practice from learners' stored performance histories. Its Teaching Assistant first asked for results to be shared, then said it could not access the assignment or class results.

1 of 1 test case failed

Every test case in this scenario has a result.

Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed 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 test case below: what we sent, what we checked, what the tool returned, and the proof.

The test case

Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.

Practice follows the weaker topicFailEvidence
What we sent

Input 1 · General per-learner review request: “Create a separate review for each student based on that student's own results.”

Input 2 · Assignment-specific review request: “Use the Electric Circuits: Series and Parallel assignment I gave to CLASS A and create a review for each learner”

What the tool returned

Request for student results

Please share the student results you want me to use.

Assignment access response

I can create the individual reviews, but I can't access the Electric Circuits: Series and Parallel assignment or CLASS A's results right now.

Transcribed from Proof 2 · Screenshot

Every message the tool sent, in order (2)
  1. Request for student results

    Printed above.

  2. Assignment access response

    The final response, printed above.

Expected vs. Found
✗Expected: Each learner receives practice directed at their weaker topic, rather than the same topic focus regardless of performance history.Found: No practice targeted a learner's weaker topic using the results already held in QuestionWell.
Supporting proof
Proof 1Screenshot
Chat screenshot: the initial request for learner reviews and the assistant's request for results
Open original ↗
Proof 2Screenshot
Chat screenshot: the assignment-specific request and the assistant's stated inability to access class results
Open original ↗
Proof 3Screenshot
Assignment history screenshot: the class assignment with five submissions
Open original ↗
Proof 4Screenshot
Section screenshot: the eighth-grade science class and its three-learner roster
Open original ↗
Proof 5Screenshot
Chat screenshot: the electric-circuits results table pasted into the composer
Open original ↗
Proof 6Screen recording
Screen recording: differentiated learner reviews generated after results were pasted
Key moments
Open original ↗
Why this result

Practice had to adapt from performance stored across sessions. The relevant section was active and QuestionWell held the results. Both requests received replies, but the assistant could not use that history for practice; having the teacher re-enter results does not meet the requirement.

Also observed in this test case

Reviews from pasted results. After the teacher pasted the electric-circuits results table, the Teaching Assistant created separate reviews with different topic targets for three learners.

Tested by Anshika Gupta · evidence dated 21 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
QuestionWell
Build or version
Not exposed by the hosted product
Plan or tier
Premium
Surface
Web app
Set up before the run
For the class's assignment on series and parallel electric circuits, comparable learner histories had to cover the same topics with opposite strengths and weaknesses. Practice was requested without pasted results, following an earlier attempt with a manually supplied results table.
Active section
CLASS A (8th Grade, science)
Tested
21 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
CapabilityPersonalized Practice →
ScenarioOne topic is weaker than the others →
ToolQuestionWell →

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
13 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/questionwell/one-topic-is-weaker-than-the-others · 0 pass · 1 fail · coverage 1/1 · graded 2026-11-12

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.

Proof 1 · Screenshot ↗image/png · 286 KB
Proof 2 · Screenshot ↗image/png · 330 KB
Proof 3 · Screenshot ↗image/png · 240 KB
Proof 4 · Screenshot ↗image/png · 1.3 MB
Proof 5 · Screenshot ↗image/png · 425 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Proof 1 · Screenshotc5e05b745dc7f72ff892b25da11af7595c205c493111aa45252dbe02b5954243
Proof 2 · Screenshot7438fb62e08453b81973130df935b0f4166d0bf2c76c18a297f4b420b9b61577
Proof 3 · Screenshot8d276f0f4803dfc2542c2a8e4fec42d3c8fee75baa065f9dff9b53e39a835906
Proof 4 · Screenshot606b14f03cd3d2d8e3d22405eee4b4918390a6ef9d74e2650b6b4a985ca4285d
Proof 5 · Screenshotca86f65886783406314be75021a146eff33e2d57bb1ebda1c37f68de228976a1
Proof 6 · Screen recordinga581680425fb156ae7f87b068d3ee3ffa88ef7618148f1695dcde284214f8ca6