LlamaIndex Extract v2.5 hits 93–96% on dense table extraction benchmarks
Original titleone of the most challenging tasks for frontier models is being able to extract thousands of values from extremely dense tables in documents.
AISummary
LlamaIndex released Extract v2.5, a set of document extraction agents that it says reach 93%–96%+ accuracy on long-list extraction, including records spanning pages.
The post claims the agents outperform frontier VLMs, which it says stop early, miss repeated records, and struggle to attribute values to sources, while LlamaIndex attributes every extracted value to its source. The agents are available through LlamaParse.
Source: Jerry Liu · x.comPublished · added here