LlamaIndex 为 LlamaParse 的 Agentic Plus 模式新增 Max Effort 开关，按页面与 schema 复杂度动态分配 token，用于处理井测曲线、数百页保险费率文件、施工蓝图等复杂文档。
Today we're introducing Extract Max Effort - the best frontier agent in the world for document extraction 💫.
🚀 It is an absolute bazooka. Use this when you absolutely need perfect 100% extraction accuracy over the most complex documents and schemas. This includes reasoning over dense well log chats, full insurance rate filings spanning 100s of pages, or dense construction blueprints.
📈 It sets a new state of the art on ExtractBench Pro, achieving 61% perfect extraction accuracy. It beats Codex+Astra and Claude Code+Opus 5.5 on price/performance.
It achieves this accuracy by allocating dynamic tokens depending on page and schema complexity. It is a toggle on top of our Agentic Plus mode, so additional pricing depends on any additional compute required.
Blog: https://www.llamaindex.ai/blog/introducing-max-effort-for-extract-agentic-plus
Come check it out in LlamaParse! https://cloud.llamaindex.ai/
Benchmark: https://extractbenchpro.ai/
Agentic Plus now has a new setting: max effort. It's built for your gnarliest documents, where extraction accuracy matters the most. With max effort, Agentic Plus can spend additional compute when needed, zooming in on tricky details like dense charts and diagrams to extract data more accurately. On ExtractBench Pro, our benchmark for particularly challenging extraction tasks, accuracy improved from 77.7 to 92.9 Value F1. Max effort uses variable pricing based on the computation required, giving you the option to prioritize extraction quality over a fixed per-page price. Learn more: https://www.llamaindex.ai/blog/introducing-max-effort-for-extract-agentic-plus Try it on your hardest docs at: https://cloud.llamaindex.ai/在 X 查看被引用的帖子
来源：Jerry Liu · x.com