Can FutureSmart Document Intelligence keep a simple table’s values under the right headers?
FutureSmart Document Intelligence passes this simple-table scenario in the checked case. The table shows Extended / Out-of-hours callout at 487, and the grounded answer gives the same amount. The captured table also shows the nearby values in the same section.
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 counts this row.
Table value asked by its row and column labelsPassEvidence
“What is the out-of-hours callout charge on an Extended cover contract?”
<table> <tr> <th>Cover level</th> <th>Weekday callout</th> <th>Out-of-hours callout</th> <th>Offshore day rate</th> </tr> <tr> <td>Standard</td> <td>216</td> <td>352</td> <td>1,140</td> </tr> <tr> <td>Extended</td> <td>284</td> <td>487</td> <td>1,265</td> </tr> <tr> <td>Critical</td> <td>331</td> <td>615</td>
Text capture of the retrieval result and grounded chat answer for the same question.
Copied from Captured file (text), lines 35–58
Open the text file ↗answer: The out-of-hours callout charge for an **Extended** cover contract is **£487**, excluding VAT.
Copied from Captured file (text), line 195
| ✓ | Expected: The value must match the correct row and column, not a neighbouring row’s value.Found: The table shows Extended / Out-of-hours callout = 487, and the chat answer gives the same amount. |
The table evidence shows Extended / Out-of-hours callout at 487, and the grounded answer gives the same amount. The nearby values are also visible in the same table section, so the row-and-column match holds.
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 row says which 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 row 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 · 7 tools |
| Capability | Data Ingestion → | |
| Scenario | A simple, clearly formatted table → | |
| Tool | FutureSmart Document Intelligence → |
Global scenario definition → · Global capability definition →
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.