This week we launched the world's most accurate document extraction agent over real-world documents....

TL;DR · AI 摘要
LlamaExtract Agentic Plus是首个在真实企业文档中实现高精度文档提取的模型,价格仅为Claude Code/Codex的25-50%。
核心要点
- LlamaExtract Agentic Plus在ExtractBench基准测试中表现最优,支持复杂文档结构解析
- 文档提取价格效率达竞品的25-50%,适合企业级应用
- ExtractBench包含旋转文本、手写体等12类真实企业文档测试场景
结构提纲
按章节快速跳转。
- §产品发布
宣布推出LlamaExtract Agentic Plus文档提取模型
- ·技术特性
支持复杂文档类型/长度/结构的结构化输出转换
- ›基准测试
在ExtractBench基准中覆盖12类真实企业文档测试场景
- ·性能对比
准确率超越竞品且价格仅为Claude Code/Codex的25-50%
思维导图
用一张图看清主题之间的关系。
查看大纲文本(无障碍 / 无 JS 友好)
- LlamaExtract Agentic Plus
- 技术能力
- 复杂文档解析
- 多模态支持
- 测试验证
- ExtractBench基准
- 12类企业文档测试
- 商业优势
- 价格效率
- 竞品对比
金句 / Highlights
值得收藏与分享的关键句。
LlamaExtract Agentic Plus可处理旋转文本、跨页表格等复杂文档结构
ExtractBench基准包含短/中/长文档、密集文档等6种任务类型
文档提取成本较Claude Code/Codex降低50%-75%仍保持更高准确率
Jerry Liu on X: "This week we launched the world's most accurate document extraction agent over real-world documents. Introducing LlamaExtract Agentic Plus 💫 . It is a complete document extraction model+harness engine that can convert even the most complex document types/lengths/schemas into" / X
@jerryjliu0
This week we launched the world's most accurate document extraction agent over real-world documents. Introducing LlamaExtract Agentic Plus 💫 . It is a complete document extraction model+harness engine that can convert even the most complex document types/lengths/schemas into clean, grounded, structured output. We benchmarked it over ExtractBench - a comprehensive set of real-world enterprise documents. It is measured over various dimensions: document length (short/medium/long), task (long-list, needle in haystack, dense docs), perception (rotated, scanned, handwriting), table structured (merged headers, cross-page tables, table within cells), and business domains. We compared it against a variety of coding agent harness to document extraction solutions. LlamaExtract Agentic Plus is not only highly accurate, it is quite price efficient relative to its capabilities (25-50% the price of Claude Code/Codex). You can see the full release of ExtractBench here:
llamaindex.ai/blog/introduci…
If you want to check it out, come sign up for an account on LlamaParse:
cloud.llamaindex.ai
Aug 11
Introducing ExtractBench, the most comprehensive benchmark for information extraction from complex enterprise documents. The latest models are pushing the frontier of coding and knowledge work, but surprisingly they still struggle on complex doc extraction tasks in production. A
Show more
$
00:00
/$
1:46 PM · Aug 13, 2026
7K
Views
8
6
60
30