one of the most challenging tasks for frontier models is being able to extract thousands of values from extremely dense tables in documents.…

one of the most challenging tasks for frontier models is being able to extract thousands of values from extremely dense tables in documents. our new Extract v2.5 agents are able to get 93%-96%+ on long-list extraction, including cells that fall in between pages. in contrast, astra gets ~30% accuracy over this benchmark. in these cases, frontier VLMs can stop early or miss repeated records. they also struggle to attribute each value back to the source. we are able to attribute every single extracted value back to the source. check out the video below, the blog post, and llamaparse! blog: https://www.llamaindex.ai/blog/introducing-extract-v2-5 llamaparse: https://cloud.llamaindex.ai/ Media Today we’re introducing Extract v2.5 - a series of frontier agents tuned for document extraction. The agents (cost-effective, agentic, agentic plus) are tuned for value accuracy and grounding. Our extraction agents outperform Opus 5.5 and GPT-6 Sol while being 30%-4x cheaper. We’…

Related

• Introducing 𝗘𝘅𝘁𝗿𝗮𝗰𝘁𝗕𝗲𝗻𝗰𝗵: the most comprehensive benchmark for information extraction from complex enterprise documents. Our app…
• Introducing ExtractBench, the most comprehensive benchmark for information extraction from complex enterprise documents. The latest models a…
• ExtractBench is now live on @Kaggle. It tests schema-guided document extraction on the documents most likely to break downstream agents and …
• Astra is one of the best models we've tested at parsing complex documents with tables, at 93.2% on ParseBench. So it seems well suited for a…

Source: Jerry Liu (X) | 2026-10-02