Text Fidelity
Ordinary digital textual content survives completely and correctly — the floor everything downstream stands on; its failure mode reads fine and is invisible
What this capability means
Text Fidelity means a tool preserves ordinary digital text completely and correctly. The text should come through with no missing, garbled, reordered, or invented content, so the words remain faithful to the source rather than silently altered or dropped.
Boundary: This does not judge layout, reading order, headings, tables, or other document structure.
Scenarios that test this capability
A scenario is a real-world situation used to test a capability.
Benchmarks that include this capability
A capability has global identity and may be used by more than one benchmark.
Converting a complex PDF into clean Markdown with an open-source library
Also evaluates this capability.
Converting a complex PDF into clean Markdown with a hosted API
Which hosted API converts a complex, real-world PDF into faithful, usable Markdown?