Baidu open-sources Unlimited-OCR, a 3B model that reads 40-page documents in one pass
HankYeomans · x · 2026-07-24
A thread says Baidu has open-sourced Unlimited-OCR, an OCR model designed to read entire documents in one pass.
- The model has 3B parameters, with only 500M active at inference time.
- It can run 100% locally and uses a 32K context window.
- The goal is to preserve text, formulas, tables, and reading order across pages, instead of chopping documents page by page.
- The thread claims 93% accuracy on a standard benchmark, about 6 points above the baseline, and an error rate below 0.11 even beyond 40 pages.
Related event: Baidu Open-Sources Unlimited-OCR for Long Documents(3 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11