Datalab open-sources Indra OCR: a 1M-parameter model that beats PaddleOCR on CPU
VikParuchuri · x · 2026-10-23
Datalab released Indra OCR, a 1M-parameter model that runs on CPU via ONNX Runtime. It scores 66.7 on OmniParseBench (beating PaddleOCR's full PP-StructureV3 pipeline at 58.4), processes 44 pages/s on 32 cores (15x Tesseract), supports 80+ languages, handwriting, and skewed scans, and outputs layout boxes with reading order.
More from Models
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23
- Marker's lite mode scores 75.1 vs 42.3 for Azure Read on OmniParseBench — VikParuchuri · 2026-10-23
- Datalab launches lite OCR at $0.50 per 1,000 pages, 20-30x cheaper than Azure, Google and AWS layout APIs — VikParuchuri · 2026-10-23
- LiveNerf's 29-day data finds no nerfing of Claude Opus 5.5 — TheOnlyVibemaster · 2026-10-23
- PHP Foundation reveals Anthropic's Claude cyber model scanned PHP, validated with OpenAI's Daybreak Red — saibharadwaj · 2026-10-23