Step3 VL 10B
StepFunOpen WeightApache 2.0 · Commercial OK
Description
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.
Release Date
2026-01-20
Parameters
10.0B
Context Length
—
Modalities
—
Capability Radar
80
general
0
coding
80
reasoning
68
scienceest.
56
agents
85
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Chat
Multi-Challenge
62.6%SR
Math
AIME 2025
87.7%SR
MathVista
84.0%SR
MathVision
70.8%SR
Multimodal
MMMU
78.1%SR
Vision
MMBench
91.8%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Math80
Multimodal80
Reasoning80
General80
Healthcare80
Vision80
Chat60
Communication60
Pricing
No pricing data available
Speed
No speed data available
Provider Price Ranking
No provider data available