# STEP3-VL-10B Technical Report

arXiv: https://arxiv.org/abs/2601.09668 · HTML: https://mlsanity.com/paper/2601.09668/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 91 of its 125 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 30 of 91)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?](https://mlsanity.com/paper/2403.14624/) (2024)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [BLINK: Multimodal Large Language Models Can See but Not Perceive](https://mlsanity.com/paper/2404.12390/) (2024)
- [Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset](https://mlsanity.com/paper/2402.14804/) (2024)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)

## Built on by (most cited first, 30 of 32)

- [DeepSeek-OCR 2: Visual Causal Flow](https://mlsanity.com/paper/2601.20552/) (2026)
- [LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding](https://mlsanity.com/paper/2605.27365/) (2026)
- [MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline](https://mlsanity.com/paper/2603.01050/) (2026)
- [FireRed-OCR Technical Report](https://mlsanity.com/paper/2603.01840/) (2026)
- [VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing](https://mlsanity.com/paper/2605.15677/) (2026)
- [WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics](https://mlsanity.com/paper/2603.13391/) (2026)
- [Unlimited OCR Works](https://mlsanity.com/paper/2606.23050/) (2026)
- [Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence](https://mlsanity.com/paper/2607.12477/) (2026)
- [VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics](https://mlsanity.com/paper/2604.06182/) (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)
- [R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging](https://mlsanity.com/paper/2602.06763/) (2026)
- [CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts](https://mlsanity.com/paper/2606.31986/) (2026)
- [Seeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understanding](https://mlsanity.com/paper/2603.03762/) (2026)
- [Buy versus Build an LLM: A Decision Framework for Governments](https://mlsanity.com/paper/2602.13033/) (2026)
- [EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning](https://mlsanity.com/paper/2603.09731/) (2026)
- [HanMoVLM: Large Vision-Language Models for Professional Artistic Painting Evaluation](https://mlsanity.com/paper/2603.10814/) (2026)
- [EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models](https://mlsanity.com/paper/2605.17070/) (2026)
- [Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?](https://mlsanity.com/paper/2605.22109/) (2026)
- [Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles](https://mlsanity.com/paper/2605.22177/) (2026)
- [PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception](https://mlsanity.com/paper/2606.28322/) (2026)
- [HoloCount: A Holistic Visual Counting Benchmark for MLLMs](https://mlsanity.com/paper/2607.06420/) (2026)
- [Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO](https://mlsanity.com/paper/2607.11581/) (2026)
- [Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension](https://mlsanity.com/paper/2602.13310/) (2026)
- [COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts](https://mlsanity.com/paper/2604.27389/) (2026)
- [iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning](https://mlsanity.com/paper/2605.31096/) (2026)
- [PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction](https://mlsanity.com/paper/2606.19096/) (2026)
- [OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning](https://mlsanity.com/paper/2606.30378/) (2026)
- [MentalThink: Shaping Thoughts in Mental SVG World](https://mlsanity.com/paper/2607.03530/) (2026)
- [MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities](https://mlsanity.com/paper/2608.25490/) (2026)
- [WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing](https://mlsanity.com/paper/2609.20423/) (2026)

## Abstract (arXiv)

We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-VL-10B is realized through two strategic shifts: first, a unified, fully unfrozen pre-training strategy on 1.2T multimodal tokens that integrates a language-aligned Perception Encoder with a Qwen3-8B decoder to establish intrinsic vision-language synergy; and second, a scaled post-training pipeline featuring over 1k iterations of reinforcement learning. Crucially, we implement Parallel Coordinated Reasoning (PaCoRe) to scale test-time compute, allocating resources to scalable perceptual reasoning that explores and synthesizes diverse visual hypotheses. Consequently, despite its compact 10B footprint, STEP3-VL-10B rivals or surpasses models 10×-20× larger (e.g., GLM-4.6V-106B, Qwen3-VL-235B) and top-tier proprietary flagships like Gemini 2.5 Pro and Seed-1.5-VL. Delivering best-in-class performance, it records 92.2% on MMBench and 80.11% on MMMU, while excelling in complex reasoning with 94.43% on AIME2025 and 75.95% on MathVision. We release the full model suite to provide the community with a powerful, efficient, and reproducible baseline.