# olmOCR 2: Unit Test Rewards for Document OCR

arXiv: https://arxiv.org/abs/2510.19817 · HTML: https://mlsanity.com/paper/2510.19817/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://mlsanity.com/paper/2502.18443/) (2025)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model](https://mlsanity.com/paper/2510.14528/) (2025)
- [Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching](https://mlsanity.com/paper/2409.03643/) (2024)
- [Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing](https://mlsanity.com/paper/2510.15349/) (2025)
- [Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models](https://mlsanity.com/paper/2506.20168/) (2025)
- [DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding](https://mlsanity.com/paper/2508.07313/) (2025)
- [DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model](https://mlsanity.com/paper/2508.13238/) (2025)

## Built on by (most cited first, 30 of 47)

- [LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR](https://mlsanity.com/paper/2601.14251/) (2026)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns](https://mlsanity.com/paper/2511.10390/) (2025)
- [Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR](https://mlsanity.com/paper/2601.08834/) (2025)
- [HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding](https://mlsanity.com/paper/2602.12957/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios](https://mlsanity.com/paper/2603.28130/) (2026)
- [OvisOCR2 Technical Report](https://mlsanity.com/paper/2607.13639/) (2026)
- [Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs](https://mlsanity.com/paper/2512.09874/) (2025)
- [Orthogonal Model Merging](https://mlsanity.com/paper/2602.05943/) (2026)
- [RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference](https://mlsanity.com/paper/2605.00392/) (2026)
- [How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings](https://mlsanity.com/paper/2605.07492/) (2026)
- [Infinity-Parser2 Technical Report](https://mlsanity.com/paper/2607.07836/) (2026)
- [MonkeyOCRv2: A Visual-Text Foundation Model for Document AI](https://mlsanity.com/paper/2607.11562/) (2026)
- [GutenOCR: A Grounded Vision-Language Front-End for Documents](https://mlsanity.com/paper/2601.14490/) (2026)
- [Efficient Document Parsing via Parallel Token Prediction](https://mlsanity.com/paper/2603.15206/) (2026)
- [Beyond String Matching: Semantic Evaluation of PDF Table Extraction](https://mlsanity.com/paper/2603.18652/) (2026)
- [GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts](https://mlsanity.com/paper/2604.12978/) (2026)
- [ZAYA1-VL-8B Technical Report](https://mlsanity.com/paper/2605.08560/) (2026)
- [StrucTab: A Structured Optimization Framework for Table Parsing](https://mlsanity.com/paper/2606.29905/) (2026)
- [Benchmarking Vision-Language Models for French PDF-to-Markdown Conversion](https://mlsanity.com/paper/2602.11960/) (2026)
- [Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG](https://mlsanity.com/paper/2603.23562/) (2026)
- [TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction](https://mlsanity.com/paper/2604.22880/) (2026)
- [METATR: A Multilingual, Evolving Benchmark for Automatic Text Recognition](https://mlsanity.com/paper/2605.26712/) (2026)
- [Review Arcade: On the Human Alignment and Gameability of LLM Reviews](https://mlsanity.com/paper/2605.28897/) (2026)
- [Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models](https://mlsanity.com/paper/2605.29303/) (2026)
- [PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception](https://mlsanity.com/paper/2606.28322/) (2026)
- [Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis](https://mlsanity.com/paper/2607.04636/) (2026)
- [daVinci-LLM:Towards the Science of Pretraining](https://mlsanity.com/paper/2603.27164/) (2026)
- [JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding](https://mlsanity.com/paper/2603.27942/) (2026)

## Abstract (arXiv)

We present olmOCR 2, the latest in our family of powerful OCR systems for converting digitized print documents, like PDFs, into clean, naturally ordered plain text. olmOCR 2 is powered by olmOCR-2-7B-1025, a specialized, 7B vision language model (VLM) trained using reinforcement learning with verifiable rewards (RLVR), where our rewards are a diverse set of binary unit tests. To scale unit test creation, we develop a pipeline for generating synthetic documents with diverse and challenging layouts, known ground-truth HTML source code, and extracted test cases. We show that RL training on these test cases results in state-of-the-art performance on olmOCR-Bench, our English-language OCR benchmark, with the largest improvements in math formula conversion, table parsing, and multi-column layouts compared to previous versions. We release our model, data and code under permissive open licenses.