A document with figures and captions
A document contains a figure with its caption attached.
What this scenario means
This scenario tests whether a converter keeps visual content and its caption together instead of dropping, moving, or separating them. A good result preserves the figure in the document flow at the right point and keeps the caption attached so the image still grounds the nearby text. It is hard because the page can look complete even when the visual element or its caption has been lost or detached.
What we evaluate
- Whether the figure is preserved rather than omitted or replaced by surrounding prose.
- Whether the figure remains positioned in the output at the point where it belongs in the document flow.
- Whether the caption stays attached to the figure and remains associated with it.
Capabilities this scenario exercises
A scenario may exercise one or more capabilities.
Figures & Charts
Information living in visual content: the asset preserved, referenced from the correct position, caption/title attached, and a text-reachable trace
Benchmarks that use this scenario
A scenario has global identity and may be reused across benchmarks.
Converting a complex PDF into clean Markdown with a hosted API
Which hosted API converts a complex, real-world PDF into faithful, usable Markdown?
Converting a complex PDF into clean Markdown with an open-source library
Also uses this scenario.