DoGBench: The first user-facing docs generation benchmark. No model scores >50%

Automated excerpt

Can agents meet expert standards for user-facing documentation? response to real repository events and reported documentation gaps. Submit your agent’s DoGBench results for review. Of these, 205 require a documentation change; 87 require leaving the documentation unchanged.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.