@jerryjliu0: We've massively improved our document parsing capabilities across the board in the past ~3 months. Our LlamaParse cost-…
Summary
LlamaIndex has significantly improved LlamaParse over the past three months, achieving 10-20% better accuracy on complex tables, charts, and grounding while maintaining costs below 0.4 cents per page, as measured against their ParseBench benchmark.
View Cached Full Text
Cached at: 09/06/26, 10:48 AM
We’ve massively improved our document parsing capabilities across the board in the past ~3 months.
Our LlamaParse cost-effective mode is one of the cheapest OCR solutions out there at <0.4c per page, and it has improved a lot on parsing since when we first put out the ParseBench paper a few months ago. 📈 10%+ improvement on complex tables 📈 10%+ improvement on charts 📈 20%+ improvement on grounding
We plot this along with other modes against a comprehensive set of models on ParseBench, our comprehensive benchmark for real-world docs.
This includes the latest VLMs like Gemini 3.8 Flash / Fable 5.1, along with new modes from specialized OCR providers.
Some providers don’t have native chart parsing (or are relegated to other modes), so for the sake of completeness we also include the benchmark that excludes the chart dimension entirely.
Our team is shipping like crazy and only accelerating 🚀
ParseBench: https://parsebench.ai LlamaParse: https://cloud.llamaindex.ai
Similar Articles
@jerryjliu0: We pride ourselves on building document processing that is not only accurate and cheap, but massively scalable to milli…
LlamaParse now offers latency metrics for Parse, Extract, and Classify jobs, providing queue time, processing time, and total latency breakdowns. This helps users monitor and scale their document processing.
@jerryjliu0: Our core mission today is using AI to solve document OCR. All of our product offerings, from commercial (LlamaParse) to…
LlamaIndex has revamped its website and reaffirmed its core mission of AI-powered document OCR, with offerings including commercial product LlamaParse and open-source tools LiteParse and ParseBench. LlamaParse uses VLM-powered agentic document understanding to handle complex layouts, tables, charts, and handwritten text at scale.
@jerryjliu0: We’re excited to rollout an official batch parsing experience to LlamaParse. Instead of hitting our APIs one file at a …
LlamaIndex announced an official batch parsing experience for LlamaParse, allowing users to parse up to 10,000 files at once through a dedicated UI with batch auditing and failure inspection, removing the need for custom async scripts.
@itsclelia: Do you actually own your document parsing infrastructure? At @llama_index, we wanted to make that easier, so we built �…
LlamaIndex introduces liteparse-server, an open-source, self-hosted HTTP backend for parsing PDFs, images, and Office documents with spatial layout extraction, OCR, and screenshot generation, designed for AI and data workflows.
@jerryjliu0: We created a document OCR router that can estimate the complexity of every single page and parse it with the relevant m…
LlamaIndex introduces Parse Gateway, a page-level document OCR router that estimates each page's complexity and routes it to the appropriate parsing tier (LiteParse or LlamaParse), balancing cost, latency, and quality.