Skip to main content

Step 3.5 Flash

StepFun

Description

Step-3.5-Flash is StepFun's fast, cost-effective text model optimized for quick inference. Built on their Step3 architecture, it offers strong performance across text tasks with low latency and efficient token usage, ideal for production workloads requiring speed and cost efficiency.

Release Date
2026-02-02
Parameters
Context Length
256K
Modalities
text

Capability Radar

24
general
40
coding
83
reasoning
55
scienceest.
70
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agentic Capability14
69.0
LS
Code Ranking190
50.0
AA
General Ranking106
63.0
AA
Science92
63.0
AA

Benchmark Scores (LLM Stats)

Agents

Tau-bench88.2%SR
BrowseComp69.0%SR
Terminal-Bench 2.051.0%SR

Code

SWE-Bench Verified74.4%SR

General

LiveCodeBench v686.4%SR

Math

AIME 202597.3%SR
IMO-AnswerBench85.4%SR

AA Evaluation Indices

Intelligence Index
25.5
Tau2
0.9
Gpqa
0.8
Ifbench
0.6
Lcr
0.4
Scicode
0.4
Terminalbench Hard
0.3
Hle
0.2

LLM Stats Category Scores

Math
90
General
90
Reasoning
80
Search
70
Frontend Development
70
Agents
70
Tool Calling
70
Code
60

Pricing

Input Price$0.1 / 1M tokens
Output Price$0.3 / 1M tokens
Blended Price (3:1)$0.15 / 1M tokens
Cache Read Price$0.02 / 1M tokens

Speed

Tokens/sec202.0
Time to First Token0.83s
Time to Answer10.73s

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: StepFunMost Expensive: StepFun AI
ProviderInputOutput
1StepFunPRIMARY
$0.1
$0.3
2StepFun AI
$0.1
$0.3

Compare pricing across different API providers for this model.

External Sources