Stepfun logo

Step 3.7 Flash – Benchmarks, Pricing & Intelligence Analysis

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

Not available on LLMBase

Step 3.7 Flash is not currently available in LLMBase Chat or the LLMBase Inference API. Benchmarks, pricing, and model details remain available for research and comparison.

Input Price$0.20/1M tokens
Output Price$1.15/1M tokens
Intelligence30.3
Coding39.6

Specifications

Technical details and pricing.

ProviderStepfun
Context Window256,000 tokens
Release DateMay 29, 2026
ModalitiesText
CapabilitiesFunction Calling
AvailabilityNot available

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA80.9%
HLE19.9%
SciCode40.0%
LCR63.7%
IFBench67.3%
Tau298.5%
TerminalBench Hard35.6%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is Step 3.7 Flash good for?

Use Step 3.7 Flash for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Step 3.7 Flash cost?

Pricing is based on usage. Current rates are $0.20/1M tokens for input and $1.15/1M tokens for output.

Is Step 3.7 Flash available in LLMBase Chat yet?

Not yet on this page. We will add chat and inference actions automatically once an exact catalog entry exists for Step 3.7 Flash.

Does Step 3.7 Flash support images or audio?

Step 3.7 Flash focuses on text-based tasks.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.