Can QuestionWell make valid quiz questions from both text and a diagram?
QuestionWell wrote 30 questions from the food-web chapter, including items on animals that appear only in its diagram, but some keys disagree with the chapter. The one question on the diagram keys the stickleback as getting food from kingfishers, the reverse of the figure, and a question on energy keys new leaves where the chapter says energy leaves the chain as heat.
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
On QuestionWell's Generate New Quiz form we requested 30 multiple-choice questions on food webs and energy flow, in English at an 8th Grade reading level, and attached the Chapter 9 PDF as the source.
The rest of what the tool returned is shown in the evidence under Proofs.
Question 12, on Figure 9.2, and its key
12. In the food web of Figure 9.2, what does 'stickleback' depend on most directly? A Eating water snails and dragonflies. | B Getting food from kingfisher birds. (keyed, filled purple B, bold)
Question 7 and its key
7. If you drew an arrow from grasshopper to grass, what would it incorrectly mean? A The grasshopper eats grass. (keyed, filled purple A, bold)
Show the reply as returned (Markdown)
Question 12, on Figure 9.2, and its key 12. In the food web of Figure 9.2, what does 'stickleback' depend on most directly? A Eating water snails and dragonflies. | B Getting food from kingfisher birds. (keyed, filled purple B, bold) Question 7 and its key 7. If you drew an arrow from grasshopper to grass, what would it incorrectly mean? A The grasshopper eats grass. (keyed, filled purple A, bold)
Transcribed from Proof 1 · Screenshot
Transcribed from Proof 3 · Screenshot
| ✗ | Expected: Valid questions on the core ideas of both the text and the diagram, with answers that agree with the chapter.Found: Question 12 keys the stickleback getting food from kingfishers, reversing Figure 9.2; questions 7 and 14 key answers that contradict the chapter's own rules on arrows and energy loss. |
Text and diagram questions had to be keyed as the chapter teaches. It is a Fail: question 12's key says the stickleback gets food from kingfishers, but in Figure 9.2 the feeding goes the other way; question 14 keys new leaves where the chapter says energy leaves as heat.
A question outside the chapter. Question 29 asks about the main cause of unusual weather patterns, a topic outside the chapter's five listed sections.
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 | QuestionWell → |
Global scenario definition → · Global capability definition → · QuestionWell 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.