STEP3-VL-10B 技术报告

STEP3-VL-10B Technical Report

January 14, 2026

作者: Ailin Huang, Chengyuan Yao, Chunrui Han, Fanqi Wan, Hangyu Guo, Haoran Lv, Hongyu Zhou, Jia Wang, Jian Zhou, Jianjian Sun, Jingcheng Hu, Kangheng Lin, Liang Zhao, Mitt Huang, Song Yuan, Wenwen Qu, Xiangfeng Wang, Yanlin Lai, Yingxiu Zhao, Yinmin Zhang, Yukang Shi, Yuyang Chen, Zejia Weng, Ziyang Meng, Ang Li, Aobo Kong, Bo Dong, Changyi Wan, David Wang, Di Qi, Dingming Li, En Yu, Guopeng Li, Haiquan Yin, Han Zhou, Hanshan Zhang, Haolong Yan, Hebin Zhou, Hongbo Peng, Jiaran Zhang, Jiashu Lv, Jiayi Fu, Jie Cheng, Jie Zhou, Jisheng Yin, Jingjing Xie, Jingwei Wu, Jun Zhang, Junfeng Liu, Kaijun Tan, Kaiwen Yan, Liangyu Chen, Lina Chen, Mingliang Li, Qian Zhao, Quan Sun, Shaoliang Pang, Shengjie Fan, Shijie Shang, Siyuan Zhang, Tianhao You, Wei Ji, Wuxun Xie, Xiaobo Yang, Xiaojie Hou, Xiaoran Jiao, Xiaoxiao Ren, Xiangwen Kong, Xin Huang, Xin Wu, Xing Chen, Xinran Wang, Xuelin Zhang, Yana Wei, Yang Li, Yanming Xu, Yeqing Shen, Yuang Peng, Yue Peng, Yu Zhou, Yusheng Li, Yuxiang Yang, Yuyang Zhang, Zhe Xie, Zhewei Huang, Zhenyi Lu, Zhimin Fan, Zihui Cheng, Daxin Jiang, Qi Han, Xiangyu Zhang, Yibo Zhu, Zheng Ge

cs.AI

摘要

我們推出STEP3-VL-10B，這款輕量級開源基礎模型旨在重新定義緊湊效率與前沿多模態智能之間的平衡。該模型通過兩大戰略轉型實現突破：首先採用統一且全參數解凍的預訓練策略，在1.2萬億多模態詞元上融合語言對齊的感知編碼器與Qwen3-8B解碼器，建立內在的視覺-語言協同；其次構建規模化後訓練管道，進行超過千次強化學習迭代。關鍵創新在於實施並行協調推理（PaCoRe）機制，通過動態分配計算資源實現可擴展的感知推理，探索並融合多元視覺假設。因此，儘管僅具備100億參數的緊湊架構，STEP3-VL-10B在性能上可媲美或超越規模10-20倍的模型（如GLM-4.6V-106B、Qwen3-VL-235B），並與Gemini 2.5 Pro、Seed-1.5-VL等頂級專有旗艦模型抗衡。其在MMBench獲得92.2%、MMMU達80.11%的頂尖成績，複雜推理任務表現尤為突出：AIME2025達94.43%，MathVision獲75.95%。我們完整開源模型套件，為學界提供強大、高效且可復現的基準系統。

English

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 10times-20times 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.