Step3 VL 10B

Step3 VL 10B

StepFun · Released Jan 20, 2026
Intelligence #638 / 715
13.6 our score
AA Index #285 / 428
9.3 Artificial Analysis
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Step3 VL 10B is a StepFun model released in January 2026 with general reasoning, science, instruction-following, and terminal-use measurements. The available results indicate limited reasoning depth and weak execution reliability, while the instruction-following result is adequate for simple, tightly specified prompts. The supplied record does not include pricing, context capacity, speed, or explicit modality details beyond the model's VL designation.

It may be useful for small-scale experiments involving straightforward visual-language tasks, provided those tasks are validated carefully. It is not a strong fit for autonomous agents, software engineering, complex document work, or unsupervised client content. The low terminal and tau results are particularly relevant for workflows that require dependable actions rather than text generation alone. Consider it only when its specific deployment characteristics are more important than broad capability.

Assessed August 9, 2026

Editorial notes

Step3 VL 10B provides basic multimodal-oriented reasoning with measured instruction following and limited coding evidence. Weak terminal and tool-use results make it a poor choice for autonomous business workflows.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Step3 VL 10B provides basic multimodal-oriented reasoning with measured instruction following and limited coding evidence. Weak terminal and tool-use results make it a poor choice for autonomous business workflows.

#638 of 715 overall Down 11 this week

Benchmark scores

GPQA Diamond 69%
HLE 10.2%
SciCode 31.1%
TerminalBench Hard 5.3%
τ²-Bench 16.1%
IFBench 50.2%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

9.3 Intelligence Index

How Step3 VL 10B compares

Step3 VL 10B ranks #285 of 428 AI models we track for overall intelligence. Step3 VL 10B is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 11% of models #638
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Step3 VL 10B $0.00 in $0.00 out
OpenAI: GPT-5.6 Sol $2.00 in $10.00 out
Claude Opus 5 $5.00 in $25.00 out
SpaceXAI: Grok 4.6 $2.00 in $6.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence2.2Technical0Value0Content3.5
Performance profile

Strongest on content. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Frequently asked questions about Step3 VL 10B

How much does Step3 VL 10B cost?

Step3 VL 10B is currently available for free via OpenRouter.

Who created Step3 VL 10B?

Step3 VL 10B is developed by StepFun and was released on January 20, 2026.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.