MiniCPM-OCR Jev (2B) is an OCR quality-assessment model for text, formula, and table regions. Given a region image and a candidate OCR result, it returns a score from 0 to 1 — higher means the candidate is more likely correct.
Alternatives to MiniCPM-OCR-Jev
120 open-weight models that do the same job as MiniCPM-OCR-Jev (2.2B OCR), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
Compare MiniCPM-OCR-Jev with the top 3Please refer to the official vLLM recipe for deployment details:
3.3BA1.1B32K ctx MIT5.6M 5KJun 2026- Same category
- Similar size (3.3B vs 2.2B)
- Commercial use OK
- Widely used
Sparse Reference Sliding Window Attention (SR-SWA): Compresses text-visual attention interactions from ultra-long sequences down to a fixed-size set of working references (e.g., 512 tokens).
3.3BA1.1B128K ctx MIT621.8K 714Oct 2026- Same category
- Similar size (3.3B vs 2.2B)
- Commercial use OK
- Newer release
Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.
3.3BA1.1B8K ctx MIT1.8M 3.5KOct 2025- Same category
- Similar size (3.3B vs 2.2B)
- Commercial use OK
- Widely used
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization.
1.3B128K ctx MIT2M 2.2KJan 2026- Same category
- Similar size (1.3B vs 2.2B)
- Commercial use OK
- Widely used
MiniCPM-OCR 1.0 (1.3B) is the first OCR-specific model in the MiniCPM-V/o family. It focuses on text-centric document understanding — text, tables, formulas, charts, seals, and structured information extraction — and balances quality against speed on real-world captures.
1.3B256K ctx Apache 2.0280.7K 447Oct 2026- Same category
- Similar size (1.3B vs 2.2B)
- Commercial use OK
We present dots.mocr. Beyond achieving state-of-the-art (SOTA) performance in standard multilingual document parsing among models of comparable size, dots.mocr excels at converting structured graphics (e.g., charts, UI layouts, scientific figures and etc.) directly into SVG code.
3B128K ctx MIT57.4K 200Mar 2026- Same category
- Similar size (3B vs 2.2B)
- Commercial use OK
dots.ocr is a powerful, multilingual document parser that unifies layout detection and content recognition within a single vision-language model while maintaining good reading order. Despite its compact 1.7B-parameter LLM foundation, it achieves state-of-the-art(SOTA) performance.
3B128K ctx MIT337.2K 1.3KJul 2025- Same category
- Similar size (3B vs 2.2B)
- Commercial use OK
Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.
3.4BA1.2B8K ctx Apache 2.0183.6K 1.2KJan 2026- Same category
- Similar size (3.4B vs 2.2B)
- Commercial use OK
Nanonets-OCR2 by Nanonets is a family of powerful, state-of-the-art image-to-markdown OCR models that go far beyond traditional text extraction.
3.8B125K ctx Unknown licence892.7K 518Oct 2025- Same category
- Similar size (3.8B vs 2.2B)
TeleOCR is a lightweight (~1.2B parameters), open-source Vision-Language Model designed specifically for document parsing.
1.4B125K ctx Apache 2.016.6K 1.3KAug 2026- Same category
- Similar size (1.4B vs 2.2B)
- Commercial use OK
📦 Model layout. This repository hosts HunyuanOCR-1.5 checkpoint at the root (target base weights). The DFlash speculative-decoding draft lives under dflash/, and the previous HunyuanOCR-1.0 is archived under v1.0/ (load it with subfolder="v1.0", or download the v1.0/ directory directly).
1.1B128K ctx Tencent Hunyuan Community License610.8K 849Nov 2025- Same category
- Similar size (1.1B vs 2.2B)
Chandra 2 is a state of the art OCR model from Datalab that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.
5.3B256K ctx OpenRAIL1.3M 610Mar 2026- Same category
- Larger (5.3B vs 2.2B)
OvisOCR3 is a unified 0.8B multimodal model for OCR and document understanding. It integrates document parsing, general OCR, key information extraction, document figure captioning, and cross-page table reconstruction into a single compact model.
853M256K ctx Apache 2.0437.7K 128Oct 2026- Same category
- Smaller (853M vs 2.2B)
- Commercial use OK
Best OCR model . LightOnOCR-2-1B is LightOn's flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.
1B16K ctx Apache 2.0672.3K 852Jan 2026- Same category
- Smaller (1B vs 2.2B)
- Commercial use OK
MinerU2.5-Pro is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board:
1.2B8K ctx Apache 2.033.7K 118May 2026- Same category
- Similar size (1.2B vs 2.2B)
- Commercial use OK
jina-ocr-v1 is an end-to-end document parsing model designed for high-quality OCR at an efficient serving point. The model builds on DeepSeek-OCR and inherits two of its efficiency-oriented components: a DeepEncoder vision tower that represents a 1024×1024 global view with 256 visual tokens and…
3.4BA1.2B32K ctx CC BY-NC 4.01.2K 207Sept 2026- Same category
- Similar size (3.4B vs 2.2B)
Best OCR model. LightOnOCR-3-4B is the largest and most accurate model of the LightOnOCR-3 family, LightOn's new generation of lightweight end-to-end OCR models with layout and visual understanding. We recommend it for most OCR tasks.
4.5B256K ctx Apache 2.013.1K 150Oct 2026- Same category
- Larger (4.5B vs 2.2B)
- Commercial use OK
MinerU2.5-Pro is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board:
1.2B8K ctx Apache 2.028.3K 185Apr 2026- Same category
- Similar size (1.2B vs 2.2B)
- Commercial use OK
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
959M128K ctx Apache 2.096K 596May 2026- Same category
- Smaller (959M vs 2.2B)
- Commercial use OK
MinerU2.5 is a 1.2B-parameter vision-language model for document parsing that achieves state-of-the-art accuracy with high computational efficiency.
1.2B16K ctx AGPL 3.077.7K 374Sept 2025- Same category
- Similar size (1.2B vs 2.2B)
- Commercial use OK
- [2026/3/24] 🔥 We release MinerU-Diffusion-V1 — a diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
2.7B32K ctx MIT173 30Mar 2026- Same category
- Similar size (2.7B vs 2.2B)
- Commercial use OK
It works on a range of documents (see usage and benchmarks).
686M256K ctx OpenRAIL573.8K 147May 2026- Same category
- Smaller (686M vs 2.2B)
We also ship smaller models for line-level text detection and ocr error detection. It works on a range of documents (see usage and benchmarks).
689M256K ctx OpenRAIL144.4K 54Oct 2026- Same category
- Smaller (689M vs 2.2B)
- Newer release
Qianfan-OCR is a 4B-parameter end-to-end document intelligence model developed by the Baidu Qianfan Team. It unifies document parsing, layout analysis, and document understanding within a single vision-language architecture.
4.7B32K ctx Apache 2.015.9K 1.2KMar 2026- Same category
- Larger (4.7B vs 2.2B)
- Commercial use OK