Scenario in benchmark
The set is legitimately empty
Its role in Structured Document Extraction.
Read the neutral global definition →Tools on this scenario
3 of 10 tools have a published result. Open a result to see what was tested and its evidence.
| Tool | Published result | Result and evidence |
|---|---|---|
| Datalab | No published result | |
| Docsumo | No published result | |
| Extend AI | 1 of 1 test case passed | Can Extend AI extract a legitimately empty set? → Version 1 · Round 1 · Graded 5 Oct 2026 |
| FutureSmart Document Intelligence | 1 of 1 test case passed | Can FutureSmart Document Intelligence extract an empty set when the document says there's nothing this period? → Version 1 · Round 1 · Graded 19 Sept 2026 |
| Landing AI | 1 of 1 test case passed | Can Landing AI return an empty set when the document says there are none this period? → Version 1 · Round 1 · Graded 8 Oct 2026 |
| LlamaParse | No published result | |
| Nanonets | No published result | |
| Reducto | No published result | |
| Retab | No published result | |
| Unstract | No published result | |
How this benchmark uses it
- Role
- context
- Pinned test cases
- 1
- Disclosure
- 0 public · 1 withheld