---
format: "aidr-story-markdown/v1"
id: "f68bef58912d2a2c4433fc756fe033dab3903898132755bbd62e78f8b325da96"
canonical_url: "https://aidr.today/f68bef58?lang=en"
title: "LlamaIndex Launches ParseBench-2 Benchmark and New OCRia-1.5 Parsing Models"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-12T18:00:43.000Z"
category: "Open Source"
topics: ["open-source"]
source_urls: ["https://marketbrief.now/ai/llamaindex-launches-parsebench-2-benchmark-and-new-ocria-15-parsing-mode-2fc9cb06","https://x.com/jerryjliu0/status/2120921239619612921","https://x.com/gelorria/status/2120924993102225521","https://x.com/aresotik/status/2120930325526176240","https://x.com/Javtorr_/status/2120935051022229659","https://x.com/mattknowsai/status/2120930360624095744","https://huggingnews.com/ai/llamaindex-launches-parsebench-2-benchmark-and-new-ocria-15-parsing-mode-2fc9cb06"]
summary: "LlamaIndex released ParseBench-2, an open-source benchmark quantifying AI accuracy in extracting data from complex documents. The release also includes the OCRia-1.5 parsing models. LlamaParse achieved an overall score of 90.1 on the new benchmark, while the Claude Opus 5.5 model scored 92.7 in text parsing."
---

# LlamaIndex Launches ParseBench\-2 Benchmark and New OCRia\-1\.5 Parsing Models

> [Open the canonical story](<https://aidr.today/f68bef58?lang=en>)

**Published:** 2026-11-12T18:00:43.000Z
**Category:** Open Source
**Topics:** open\-source

## Summary

LlamaIndex released ParseBench\-2, an open\-source benchmark quantifying AI accuracy in extracting data from complex documents\. The release also includes the OCRia\-1\.5 parsing models\. LlamaParse achieved an overall score of 90\.1 on the new benchmark, while the Claude Opus 5\.5 model scored 92\.7 in text parsing\.

## Sources

- [Story source](<https://marketbrief.now/ai/llamaindex-launches-parsebench-2-benchmark-and-new-ocria-15-parsing-mode-2fc9cb06>)
- [Story source](<https://x.com/jerryjliu0/status/2120921239619612921>)
- [Supporting source](<https://x.com/gelorria/status/2120924993102225521>)
- [Supporting source](<https://x.com/aresotik/status/2120930325526176240>)
- [Supporting source](<https://x.com/Javtorr_/status/2120935051022229659>)
- [Supporting source](<https://x.com/mattknowsai/status/2120930360624095744>)
- [Story source](<https://huggingnews.com/ai/llamaindex-launches-parsebench-2-benchmark-and-new-ocria-15-parsing-mode-2fc9cb06>)