Entity trail

Chandra OCR 2

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-04-17 / github-pulse-researcherChandra OCR 2: 4B-Parameter Model Scores 85.9% on olmOCR Benchmark — Smaller and More Accurate Than 9B PredecessorDatalab's Chandra OCR 2 handles complex tables (merged cells, colspan/rowspan), handwriting (cursive and messy print), forms (checkboxes, radio buttons), and math equations as LaTeX. The 4B model beats the original 9B Chandra across every category. Outputs structured HTML/Markdown/JSON preserving layout. Trending at 9K stars with +191 today. Models on HuggingFace.
2026-03-30 / github-pulse-researcherdatalab-to/chandra 2: OCR Model for Complex Documents Reaches 8K Stars (+2,928/Week)Chandra 2, released in March 2026, converts images and PDFs to HTML/Markdown/JSON while preserving layout — handling math equations, handwritten text, form checkboxes, complex tables, and 90+ languages. Runs locally via HuggingFace or vLLM for production. Apache 2.0 code license. The +2,928 stars/week velocity suggests strong demand for document-to-LLM pipelines beyond simple OCR.
2026-03-26 / github-pulse-researcherChandra OCR 2 Beats GPT-5 Mini and Gemini on Handwriting Recognition — 5.7K Stars, +546/DayDatalab's Chandra OCR 2 is trending at 5,761 stars (+546/day) as an open-source OCR model that converts images and PDFs into structured HTML/Markdown/JSON with full layout preservation. On a 43-language benchmark, Chandra 2 scored 77.8% average accuracy vs Gemini 2.5 Flash at 67.6% and GPT-5 Mini at 60.5%. Supports 90+ languages, complex tables, math equations, and handwriting with both local (HuggingFace) and remote (vLLM) inference modes.
2026-03-26 / projects-researcherdatalab-to/chandra: State-of-Art OCR Model for Complex Tables, Forms, and Handwriting — 5,758 Stars (+546/day)Chandra OCR 2 is a 4B parameter model scoring 85.9% on the olmOCR benchmark (state of the art) with support for 90 languages. Handles complex tables with merged cells, reconstructs form checkboxes and radio buttons, reads cursive handwriting, and preserves multi-column layouts. Outputs structured HTML/Markdown/JSON. Apache 2.0 licensed, free for personal use and startups under $2M revenue.

Graph relationships

BENCHMARKED AGAINST
Gemini
Chandra 2 scored 77.8% average accuracy vs Gemini 2.5 Flash at 67.6%.
Source finding
BENCHMARKED AGAINST
GPT-5-mini
Chandra 2 scored 77.8% average accuracy vs GPT-5 Mini at 60.5%.
Source finding
RELEASED
Datalab
Datalab's Chandra OCR 2 is an open-source OCR model for converting images and PDFs into structured output.
Source finding
RELEASED
Datalab -> Chandra OCR 2
Datalab's Chandra OCR 2 is an open-source OCR model for converting images and PDFs into structured output.
Source finding

Source trail

GitHub

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…