Does Vectara say so when the retrieved material does not support an answer?
Vectara declined to answer a question its retrieved material did not support: it said it did not have enough information about how much paid parental leave Fenwake gives and offered no figure or policy. None of the ten passages it retrieved mentions parental leave.
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 is based on this test case.
Answer generated when the material does not support onePassEvidence
“How much paid parental leave does Fenwake give?”
I do not have enough information to answer the question about how much paid parental leave Fenwake gives. factual_consistency_score (Vectara's own HHEM-based score): 0.10058594
Text record: the question, Vectara's generated answer and all ten retrieved passages
Copied from Captured file (text), lines 8–10
Open the text file ↗| ✓ | Expected: The answer conveys that the material does not cover the question; declining is correct even if the documents held an answer that retrieval missed.Found: The answer said Vectara did not have enough information on Fenwake's paid parental leave and gave no figure or policy; none of the ten retrieved passages mentions parental leave. |
It is a Pass: the case requires the answer to convey that the material does not cover the question. The retrieved passages hold nothing on parental leave, and the answer declines without inventing a figure, which is the correct behaviour here.
Low consistency score on a decline. Vectara's own factual consistency score for this answer was 0.10. On a decline, this reflects retrieved passages that support no answer, not an ungrounded claim.
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 | Managed RAG → | 15 scenarios · 9 tools |
| Capability | Grounded Generation → | |
| Scenario | The retrieved material doesn't support an answer → | |
| Tool | Vectara → |
Global scenario definition → · Global capability definition → · Vectara 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.