Scenario in benchmark · Quiz Generation · Version 1

The learner returns to the material later

A learner returns later and the next practice session uses retained performance history.

Capability: Personalized Practice1 pinned test case per toolNeutral global definition →

What we check

  1. Whether the later session uses retained performance history rather than resetting the learner’s context.
  2. Whether the practice focus changes when earlier strengths and weaknesses differ.
  3. Whether the system avoids the same fixed practice focus regardless of prior performance.

Exact wording, inputs, fixture state, expected output and detailed grading remain at the test-case level and may be withheld while the benchmark version is active. The scenario and its evaluation intent are public.

How the tools performed

One row per tool, from its current published Result for this scenario and benchmark version. Open a row for the full summary and the exact counts.

Failed · 4
Edcafe AIFailed1 of 1 test case failedServed a returning learner the same blank quiz rather than practice tailored to earlier weaknesses.View Result →

It did not refer to the earlier attempt or offer a practice recommendation.

0 Pass · 1 Fail · 0 Not gradable · 1 of 1 assessed · 1 of 1 gradable

PDF to QuizFailed1 of 1 test case failedRetained the learner’s history across sessions but did not use it to target weaker topics.View Result →

Practice restarted the fixed 47-question quiz with a previously answered fuse question from the learner’s stronger area, rather than focusing on parallel circuits.

0 Pass · 1 Fail · 0 Not gradable · 1 of 1 assessed · 1 of 1 gradable

QuestionWellFailed1 of 1 test case failedOffered neither returning learner new personalized practice.View Result →

Its assistant also asked for student results again in a new conversation.

0 Pass · 1 Fail · 0 Not gradable · 1 of 1 assessed · 1 of 1 gradable

StudyglenFailed1 of 1 test case failedResumed broad chapter practice rather than targeting each returning learner’s weaker topic.View Result →

Learner A received 20 learned cards in order, Learner B received a mixed 15-card deck starting with household wiring, and Weak spots named no weak topic for either.

0 Pass · 1 Fail · 0 Not gradable · 1 of 1 assessed · 1 of 1 gradable

Failures first, then A–Z within each group. Not a ranking. Assessed = Pass + Fail + Not gradable; Gradable = Pass + Fail, both out of the Result’s pinned test cases.

No published Result yet (6): DoctoQuiz, GPT-5.6 terra, Knowt, Quizgecko, Quizizz, QuizRise.

No published Result does not tell you whether a tool has been tested.

Test design

Pinned test cases
1
Disclosure
0 public · 1 withheld
Capabilities exercised here
Personalized Practice

How the results are graded

  • Pass the test-case expectations hold.
  • Fail an expectation demonstrably does not hold.
  • Not gradable the evidence cannot establish the outcome.

Version 1 uses test-case expectations; no scenario rubric is pinned. Benchmark methodology →

The learner returns to the material later in Quiz Generation | AI Demos