Capability in benchmark · Version 1

Code Extraction

Code survives as a preformatted fenced block with its whitespace and line structure intact.

1 scenario · 2 current published Results · 2 tools with published Results

How the tools performed

Explore current published Results across this capability’s scenarios. Open a scenario to compare its tools, or a Result to inspect the evidence.

Each cell reports its own published test set. There is no combined capability score or claim that different Results used identical tests.

Scenarios in this capability
Tools with published Results appear first, alphabetically. Remaining participants stay visible below.
Participating toolA document containing a code block →
Adobe PDF Extract APIA document containing a code block →
1 Fail
1/1 assessed1/1 gradableView Result →
ReductoA document containing a code block →
1 Fail
1/1 assessed1/1 gradableView Result →
Extend AINo published result across these scenarios
FirecrawlNo published result across these scenarios
GPT-5.6 terraNo published result across these scenarios
Landing AINo published result across these scenarios
LlamaParseNo published result across these scenarios
Mistral AINo published result across these scenarios
Nutrient.ioNo published result across these scenarios
PDF VectorNo published result across these scenarios
TensorlakeNo published result across these scenarios
UnstructuredNo published result across these scenarios
Upstage AINo published result across these scenarios

Reading the comparison

Publication availability and test coverage describe different things.

Published evidence

Publication is not testing progress

“No published result” says only that there is no current public Result. It does not indicate whether a tool has been tested, passed, failed or is applicable.

Test coverage

Read each Result’s test set

Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Each fraction uses the pinned tests in that same published Result.

Go deeper

Choose the view you need

A scenario compares tools on one situation. A tool page follows one tool across this benchmark. A Result explains the outcome and shows the evidence.

Code Extraction in Converting a complex PDF into clean Markdown with a hosted API | AI Demos