OCR
6 pieces on OCR.
News & Analysis
Jina-ocr-v1: 3.4B MoE Parses 2.57 Pages/sec on One A100
Jina AI's 3.4B MoE document parser posts 2.57 pages/sec on a single A100 — highest of 14 systems benchmarked — via lossless speculative decoding.
Reducto r-1 Cuts Document Parsing Cost to 1¢ Per Page With Single-Pass Model
Reducto r-1 replaces a 4-stage agentic OCR pipeline with one full-page pass, cutting price from 3–6¢ to 1¢ and reporting 20% fewer errors.
Cohere Parse 5: 2.3B-Parameter VLM Beats Gemini 3 Flash on ParseBench
Cohere's Parse 5 scores 79.2 on ParseBench, outperforming Mistral OCR and Gemini 3 Flash with a 2.3B-parameter VLM that outputs Markdown plus bounding boxes.
Cohere Parse 5: 2.3B Model Converts Enterprise Docs to Markdown at $1.50/1K Pages
Cohere's parse-v5.0 replaces OCR stacks with a single 2.3B vision-language model call — but its 79.2 ParseBench score covers only 3 of 5 dimensions.
How Baidu Unlimited-OCR Solves Long-Document Transcription
Baidu's Unlimited-OCR fixes the output-side KV cache bottleneck in long-document OCR using Reference Sliding Window Attention, keeping memory constant at m+n tokens.
Chandra OCR 2 Shows How Fast Open-Source Document AI Is Catching Up
Datalab's Chandra OCR 2 is pushing open-source OCR past legacy parsers with stronger layout, math, table, and multilingual performance.