Step3-VL-10B

STEP3-VL-10B is a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. Built on a unified, fully unfrozen pre-training strategy on 1.2T multimodal tokens integrating a language-aligned Perception Encoder with a Qwen3-8B decoder. Features Parallel Coordinated Reasoning (PaCoRe) to scale test-time compute for complex perceptual reasoning.