Skip to main content

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

10
general
31
coding
69
reasoning
44
science
58
agents
85
multimodal

Rankings

Domain#RankScoreSource
Code Ranking544
4.0
AA
General Ranking477
24.0
AA
Science272
47.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Communication

Multi-Challenge62.6%SR

General

MMMU78.1%SR

Math

AIME 202587.7%SR
MathVista84.0%SR
MathVision70.8%SR

Multimodal

MMBench91.8%SR

AA Evaluation Indices

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
9.3
Gpqa(NYU + Cohere + Anthropic (2023))
0.7
Ifbench(Google Research (2023))
0.5
Scicode(UIUC + Argonne National Lab (2024))
0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1
Lcr(Artificial Analysis)
0.0

LLM Stats Category Scores

(LLM Stats (zeroeval))
Math
80
Multimodal
80
Reasoning
80
General
80
Healthcare
80
Vision
80
Communication
60

Pricing

Input PriceFree
Output PriceFree
Blended Price (3:1)Free

Speed

Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s

Provider Price Ranking

No provider data available

External Sources