# LlamaParse Agentic scores 179/179 on document parsing benchmark

> Original title: 3/ The results:

- Source: LlamaIndex
- Published: 2026-10-29T16:36:18.000Z
- Bad Influence: https://badinfluence.news/items/hsk59y3l0fnycipmq558r7pul
- Original: https://x.com/llama_index/status/2115845188388085874

## Summary

LlamaIndex says its LlamaParse Agentic and Agentic Plus modes scored 179 of 179 with zero Boos on its benchmark. The post reports the best frontier VLMs, GPT-6 Luna and GPT-6.1 Terra, reached 99.4%, while open VLMs ranged from 61% to 93%.

## Post

3/ The results:
- LlamaParse Agentic and Agentic Plus: 179/179, zero Boos
- Best frontier VLMs (GPT-6 Luna, GPT-6.1 Terra): 99.4%
- Open VLMs: 61% to 93%