Scenario in benchmark · Quiz Generation · Version 1

The learner's answer is partly correct

A learner response is partly correct when it includes one required idea, leaves out another, and does not contradict the correct part.

Capability: Grading, Answer Feedback2 pinned test cases per toolNeutral global definition →

What we check

  1. Whether the response is treated as partially correct rather than fully correct or fully incorrect.
  2. Whether the system preserves the learner's correct idea while identifying the missing required idea.
  3. Whether feedback explains what is present, what is absent, and what must be added or corrected.
  4. Whether the same underlying response can support both a grading judgement and explanatory feedback without changing the scenario.

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 · 3
Edcafe AIFailed1 of 2 test cases passed · 1 failedRecognised the learner’s answer as partly correct, but its personalised feedback did not explain the missing idea.View Result →

It credited the series-circuit explanation and identified the omitted parallel case; the explanation of that case appeared in a stored model answer, not in the personalised feedback.

1 Pass · 1 Fail · 0 Not gradable · 2 of 2 assessed · 2 of 2 gradable

QuizgeckoFailed1 of 2 test cases passed · 1 failedGave useful feedback for the partly correct answer, but its scored result treated that same answer as fully correct.View Result →

The explanation named what the learner got right and what idea was missing, while the score card still showed Correct and +15 XP with no partial-credit mark.

1 Pass · 1 Fail · 0 Not gradable · 2 of 2 assessed · 2 of 2 gradable

StudyglenFailed1 of 2 test cases passed · 1 failedExplained the learner's partial understanding, but graded the answer as incorrect without partial credit.View Result →

It showed 55% similarity versus 0% for a response expressing no understanding; its feedback identified the correct brightness comparison and the missing voltage and battery-life ideas.

1 Pass · 1 Fail · 0 Not gradable · 2 of 2 assessed · 2 of 2 gradable

Passed · 1
QuestionWellPassed2 of 2 test cases passedHandles partly correct open-ended answers as partial rather than fully correct or wrong.View Result →

It named the correct idea, named the missing idea, and told the learner what to add; it also showed a distinct partial-correct judgment and a 1.5/3 total in the same session.

2 Pass · 0 Fail · 0 Not gradable · 2 of 2 assessed · 2 of 2 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, PDF to Quiz, Quizizz, QuizRise.

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

Test design

Pinned test cases
2
Disclosure
0 public · 2 withheld
Capabilities exercised here
Grading, Answer Feedback

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's answer is partly correct in Quiz Generation | AI Demos