openbenchmarks-labs/document-processing
Open, independent benchmark on document parsing APIs and frontier VLMs for AI agents and RAG: does a struck-out clause in a redlined contract PDF survive the parse? Open source code + open data. LlamaParse, Reducto, Datalab, Extend, Pulse, Mistral OCR, GPT-6 Astra, Claude Fable 5.1.
GitHub repository with 6 stars and 0 forks.
Language: Python
Topics: ai-agents, benchmark, contracts, document-parsing, document-processing, evaluation-framework, independent-benchmark, leaderboard, legal-tech, llamaparse