Datalab releases OmniExtractBench for document extraction
For users needing to extract structured data from documents, this benchmark provides a standardized way to evaluate and compare different models' performance.
#LlamaExtract
5 stories · 0 in 7 days · 0 in 30 days
Stories, products and papers tagged "LlamaExtract", newest first.
Sep 19
Aug 18
Chinese contentExtractBench：多数文档提取API无法溯源，词级F1不足50%
想用文档提取API？先看ExtractBench的溯源评测。多数工具给不出出处，LlamaExtract Agentic Plus在长文档上还挺得住。
Aug 17
Chinese contentLlamaExtract推出Agentic Plus，长文档提取准确率达94%以上
LlamaIndex给LlamaParse加了新模式，专门抽长文档里的海量字段，准确率比Claude Code和Codex高10-20%，每个字段还带出处。
Aug 13
Chinese contentLlamaIndex发布LlamaExtract Agentic Plus，文档抽取准确率95.6%
批量解析复杂企业文档？LlamaExtract比Claude Code便宜一半还更准，去LlamaParse体验。
Aug 3
Papers11:19
Chinese contentExtractBench：面向企业文档模式引导提取的新基准Llamaindex出的ExtractBench基准测文档提取。商业VLM长文档会截断，LlamaExtract Agentic Plus更准还更便宜。