NOUMENOpen app
NOUMEN

stepfun · Open weights

Step 3.5 Flash

Added Feb 2, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

StepFun's most capable open-source reasoning model with visible reasoning traces. Built on a sparse Mixture-of-Experts architecture with 196B total parameters and only 11B active per token, it achieves frontier-level performance in math, logic, and agentic coding while reaching up to 350 tokens/sec. Supports 256K context. NOTE: This model runs via StepFun, which may log and train on your prompts.

  • Reasoning
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.30

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
65.5K
Average output (7 days)
2.4K tokens
Longer than 94% of 468 models

Side by side

Step 3.5 Flash compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Step 3.5 FlashstepfunThis modelOpenAI o4-mini highOpenAIRemove
ProviderstepfunOpenAI
Discovery tierOpen weightsEfficient
AddedFeb 2, 2026Dec 4, 2025
Limits
Context window262.14KBest200K
Max output65.54K100KBest
Average output2.4K tokens75 tokens
Pricing, USD per 1M tokens
Input$0.10Best$1.10
Output$0.30Best$4.40
Cache read—$0.55
Performance
Request success (24h)100.0%—
Benchmark indexes
Intelligence Index16.616.7Best
Math Index—90.7
Capabilities
ReasoningYesYes
ToolsNoYes
Structured outputNoYes
Reasoning effort—low, medium, high

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Step 3.5 Flash
  • OpenAI o4-mini high

Intelligence Index

  • Step 3.5 Flash16.6
  • OpenAI o4-mini high16.7

Step 3.5 Flash: Better than 43% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Step 3.5 Flash: —
    • OpenAI o4-mini high: 90.7

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Step 3.5 Flash: 50.0%
    • OpenAI o4-mini high: 61.0%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Step 3.5 Flash: 21.1%Top
    • OpenAI o4-mini high: 16.5%

  • GPQA Diamond

    Graduate-level science questions

    • Step 3.5 Flash: 83.1%Top
    • OpenAI o4-mini high: 78.4%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Step 3.5 Flash: —
    • OpenAI o4-mini high: 83.2%

  • IFBench

    Following precise output instructions

    • Step 3.5 Flash: 64.6%
    • OpenAI o4-mini high: 68.7%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Step 3.5 Flash: —
    • OpenAI o4-mini high: 85.9%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Step 3.5 Flash: —
    • OpenAI o4-mini high: 90.7%

  • AIME

    Competition mathematics

    • Step 3.5 Flash: —
    • OpenAI o4-mini high: 94.0%

  • MATH-500

    Competition math problems

    • Step 3.5 Flash: —
    • OpenAI o4-mini high: 98.9%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Step 3.5 Flash: 27.3%Top
    • OpenAI o4-mini high: 15.2%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Step 3.5 Flash: 94.4%Top
    • OpenAI o4-mini high: 55.6%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Step 3.5 Flash: 50.0%
    • OpenAI o4-mini high: 61.0%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Prompt cache hits
0.0%
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 100.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepfun-ai/step-3.5-flash",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="stepfun-ai/step-3.5-flash",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

stepfun

Other stepfun models, starting with the same family.