Can PDF to Quiz cover both text and diagram when both matter?
PDF to Quiz generated 17 questions covering text-based ideas but left the diagram-only food web unassessed. The questions addressed energy transfer, decomposers and other prose-based topics, with answers that agreed with the chapter.
1 of 1 test case failed
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 is based on this test case.
A core idea carried only by a diagramFailEvidence
The tool's response has no text to quote: it is what the evidence under Proofs shows.
Proof 1 · Screen recording · ▶ 2:00–2:04; ▶ 2:00–2:42
| ✗ | Expected: Valid questions must assess core information from both text and diagram, with answers or evaluation guidance that agree with the source.Found: The 17 questions covered text-based ideas with source-aligned answers; none assessed the Fenmoor Ditch food web taught only in the diagram. |
A usable quiz was generated from the whole chapter, diagram included, with supplementary questions off. It still omitted a required core idea, so this is a coverage failure rather than a generation error. The conclusion is limited to the free plan’s default model, not Pro.
Arrow mismatch. Question 14 follows conflicting wording on page 2 of the chapter: it points arrows from an organism to its food, reversing the diagram and the introductory explanation.
Contradictory arrow directions. Question 6 correctly describes energy flowing from prey to predator, contradicting question 14.
Repeated layout question. Questions 7 and 13 ask almost the same thing: which feeding connections stay unchanged when the food-web boxes are rearranged.
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 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.
| Level | Name | Scope |
|---|---|---|
| Benchmark | Quiz Generation → | 15 scenarios · 10 tools |
| Capability | Quiz Generation → | |
| Scenario | Important information appears in both text and a diagram → | |
| 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.