Does PDF to Quiz mark a correct answer in the learner’s own words?
PDF to Quiz marked the learner’s differently worded answer as fully correct. The graded review showed 10/10 for the parallel-circuit item and the results page showed 1 correct; the practice view’s running counter was only a pre-grading tally, and the quiz-wide 4% also counts unanswered items.
1 of 1 test case passed
Every test case in this scenario has a result.
The test case
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above counts this row.
A correct answer in the learner's own wordingPassEvidence
“When two bulbs are wired side by side in parallel, each bulb gets a path of its own that starts at one meeting point of the wires and finishes at the other meeting point. If the bulb on one path burns out, that path now has a gap in it, so no current can get through there and that bulb goes dark. The second path has nothing wrong with it, though it still joins the two meeting points with no break anywhere. Current can keep moving through that path just like before, so the second bulb keeps shining as brightly as it did before. What this tells us is that the paths in this kind of circuit don't depend on each other. Each one works by itself, so when something breaks, the problem stays stuck in that one path and doesn't spread to the rest of the circuit.”
The tool's reply is shown in the evidence under Proofs.
| ✓ | Expected: The product should mark the differently worded answer fully correct.Found: The review page gave 10/10 to a paraphrased answer that preserved the circuit meaning, and the results page showed one correct answer. |
The case required full credit for a learner answer that kept the required meaning while using different wording. The graded review gave that answer 10/10, so the result is a pass.
Pre-grade tally. The practice view marks the answer incorrect before grading starts, then the graded review later shows 10/10.
Quiz-wide summary. The end-of-quiz percentage counts unanswered questions as incorrect, so it does not measure only the graded answers.
The feedback panel is quiz-wide, so it does not identify this question or answer.
The 4% summary counts unanswered questions as incorrect on this 50-question quiz.
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 row says which 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 row 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 | Grading → | |
| Scenario | The learner answers correctly in their own words → | |
| Tool | PDF to Quiz → |
Global scenario definition → · Global capability definition → · PDF to Quiz 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.