Does QuestionWell handle partly correct answers in grading and feedback?
QuestionWell handles partly correct open-ended answers as partial rather than fully correct or wrong. 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 of 2 test cases passed
Every test case in this scenario has a result.
The 2 test cases
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on these test cases.
A partly correct answer, explainedPassEvidence
“The current is the same at every point in a series circuit.”
You are correct that the current is the same at every point in a series circuit. Nice job! However, the question also asks about the relationship between current and voltage. What can you say about how the voltage is distributed among the components in a series circuit? Think about what happens to the voltage as it passes through each part of the circuit.
Transcribed from Proof 2 · Screenshot
| ✓ | Expected: The feedback should say what was right, what idea is missing, and what to add for a complete answer.Found: It praised the correct current idea, named the missing voltage idea, and told the learner to think about how voltage changes through the circuit. |
It passes because the feedback names the correct idea, names the missing voltage idea, and tells the learner what to add for a complete answer.
Missing idea asked. The feedback asked for the missing voltage idea instead of stating it outright.
A partly correct answer, scoredPassEvidence
“The current is the same at every point in a series circuit.”
Judgement ⚠️ Partially Correct! Feedback You are correct that the current is the same at every point in a series circuit. Nice job! However, the question also asks about the relationship between current and voltage. What can you say about how the voltage is distributed among the components in a series circuit? Think about what happens to the voltage as it passes through each part of the circuit.
Transcribed from Proof 2 · Screenshot
| ✓ | Expected: The product should show partial credit or judgment for an answer with one required idea but not the other.Found: It showed an amber partial-correct screen and a 1.5/3 total, separate from the correct and wrong judgments in the session. |
It passes because QuestionWell marked the one-idea answer as partially correct, separate from the full-correct and wrong-answer judgments in the same session.
No per-question mark. The screen showed the partial judgment, but no question-by-question mark.
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 | Grading → | |
| Capability | Answer Feedback → | |
| Scenario | The learner's answer is partly correct → | |
| Tool | QuestionWell → |
Global scenario definition → · Global capability definition: Grading → · Global capability definition: Answer Feedback → · 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.