Code Extraction
Preformatted code, whose whitespace and line structure ARE meaning; a fenced code block, not LaTeX — code reflowed into prose is broken for every downstream use
What this capability means
A tool has this capability when it keeps code as code: the block stays preformatted or fenced, and its whitespace, indentation, and line structure remain intact. The output may be Markdown or another supported format, but the code must not be reflowed into prose or otherwise flattened, because that changes the meaning of the content.
Boundary: This does not judge non-code content or general Markdown styling. It is only about preserving code blocks as code, not about tables, headings, equations, or other document content.
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?