Mahal Systems RealHiTBench
Fits assistants that read reports or financial tables with multi-level headers. Borrow the structure taxonomy (hierarchical headers, nested sub-tables, multi-table joins, decorative elements) and the practice of testing the same table in several input formats.
What it asks the agent to do
- answer a question over a table with hierarchical row or column headers
- read a table given as LaTeX, HTML or an image
- reason across nested sub-tables or joined tables
What to borrow from it
case templatetaxonomybaseline
Caveats
Non-commercial data license; the README does not explain the scoring metrics; read-only question answering with no table editing.
Details
| Workloads | data analysis, knowledge qa, documents |
|---|---|
| Interaction | single turn |
| Environment | static |
| End state checked | No |
| Tools | none |
| Grading | programmatic check |
| Size | 3,752 |
| Data | real public |
| Personal data | none |
| License | CC-BY-NC-4.0 |
| Harness | own repo |
| Status | active |