Step3-VL-10B

Overview

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.

Step3-VL-10B was released on January 15, 2026.

Benchmarks

Step3-VL-10B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

Share

llm-stats.com - Mon Jan 19 2026

Pricing

Pricing, performance, and capabilities for Step3-VL-10B across different providers:

API Access