Can Anomaly AI answer questions when a user's wording differs from stored values?
Anomaly AI interpreted gift vouchers as gift-card payments and returned the matching orders. It listed 14 orders against a reference count of 14, including two cancelled orders.
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.
Category asked by the user's synonymPassEvidence
“Show me all orders paid with a gift voucher.”
Found 14 orders paid with a gift voucher, recorded as gift-card payments. The full list is shown newest first and includes cancelled orders. Data is current as of October 30, 2026, 11:21 AM your local time.
Transcribed from Proof 1 · Screen recording at 0:21
Every message the tool sent, in order (2)
- Generated SQL · not part of the answer
SELECT COUNT(DISTINCT o."id") AS "value" FROM "orders" o WHERE o."payment_method" = 'gift_card'
- Answer
The final response, printed above.
| ✓ | Expected: Return the 14 matching gift-card orders when asked for gift-voucher orders, rather than an empty answer.Found: It returned 14 orders; the reference count was 14 gift-card orders. The table showed order numbers, local dates, statuses, amounts and gift-card payments throughout the visible rows. |
The request required matching orders, not an empty answer. With no synonym mapping supplied, Anomaly AI identified the stored category, explained its interpretation and returned an order list rather than just a count.
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 | AI Database Agents → | 28 scenarios · 11 tools |
| Capability | Question Answering → | |
| Scenario | The user's wording doesn't match how the values are stored → | |
| Tool | Anomaly AI → |
Global scenario definition → · Global capability definition → · Anomaly AI 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.