# Baidu Open-Sources End-to-End Long Document OCR Model Unlimited-OCR

- Category: Flash (快讯)
- Published: 2026-06-23T11:52:00.000Z
- Source date: 2026-06-23
- HTML: https://www.88z.ai/en/news/flash-20260623-0949fd6c2a61265b
- Markdown: https://www.88z.ai/en/news/flash-20260623-0949fd6c2a61265b.md
- Other language: https://www.88z.ai/news/flash-20260623-0949fd6c2a61265b.md

Baidu has released the open-source OCR model Unlimited OCR, specializing in long document parsing. It achieved a new state-of-the-art comprehensive score of 93.23% on the OmniDocBench benchmark, surpassing DeepSeek OCR. The core innovation is the Reference Sliding Window Attention mechanism, which uses a soft forgetting strategy to maintain constant KV Cache, ensuring inference speed does not drop as document length increases, with TPS improving by approximately 35% at 6000 tokens.

## At a glance

- Unlimited OCR sets a new SOTA on OmniDocBench with a 93.23% score, surpassing DeepSeek OCR.
- Uses Reference Sliding Window Attention mechanism, improving TPS by approximately 35% at 6000 tokens.

## The update

Baidu has officially open-sourced Unlimited OCR, a new end-to-end long document OCR model. Designed to parse dozens of pages in a single pass, the model achieved a breakthrough on the OmniDocBench benchmark with a comprehensive score of 93.23%, setting a new state-of-the-art and outperforming DeepSeek OCR. Technologically, the core innovation of Unlimited OCR lies in its Reference Sliding Window Attention mechanism. By implementing a soft forgetting strategy, the model maintains a constant KV Cache, ensuring that inference speed does not degrade as document length increases. Test data shows that when processing 6000 tokens, its tokens per second improved by approximately 35%, significantly optimizing efficiency for long text processing.

## Sources

- [量子位](https://mp.weixin.qq.com/s/rM2Y3Re8cqRd1Z8d7l88Iw) (2026-06-23)

This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.