ParseBench: A Document Parsing Benchmark for AI Agents

TL;DR

ParseBench is a comprehensive benchmark with around 2,000 enterprise document pages designed to evaluate AI agents on semantic correctness across multiple document parsing capabilities.

Contribution

It introduces a new benchmark covering five key parsing dimensions and evaluates diverse methods, revealing capability gaps and the highest-performing system.

Findings

No method excels across all five dimensions.

LlamaParse Agentic achieves 84.9% overall score.

Benchmark exposes gaps in current document parsing systems.

Abstract

AI agents are changing the requirements for document parsing. What matters is semantic correctness: parsed output must preserve the structure and meaning needed for autonomous decisions, including correct table structure, precise chart data, semantically meaningful formatting, and visual grounding. Existing benchmarks do not fully capture this setting for enterprise automation, relying on narrow document distributions and text-similarity metrics that miss agent-critical failures. We introduce ParseBench, a benchmark of ${\sim}2{,}000$ human-verified pages from enterprise documents spanning insurance, finance, and government, organized around five capability dimensions: tables, charts, content faithfulness, semantic formatting, and visual grounding. Across 14 methods spanning vision-language models, specialized document parsers, and LlamaParse, the benchmark reveals a fragmented capability landscape: no method is consistently strong across all five dimensions. LlamaParse Agentic achieves the highest overall score at 84.9%, and the benchmark highlights the remaining capability gaps across current systems. Dataset and evaluation code are available on https://huggingface.co/datasets/llamaindex/ParseBench and https://github.com/run-llama/ParseBench.