StepFun: Step 3.5 Flash

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

stepfun/step-3.5-flash

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

Specifications & capabilities

Input
text
Output
text
Context window · tokens
262144
Published model ID
step-3.5-flash
Capabilities
promptCaching, reasoning, streaming, structuredOutputs, toolCalling

Evaluations

21–40 / 95

LMArena

1,412.135

source id
lmarena
leaderboard name
LMArena Text Factuality Russian
dimension
factuality
metric
Arena rating
rank
123
sample size
5415
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1404.3435210855464
confidence upper
1419.9262786400275
Original result ↗

LMArena

1,472.646

source id
lmarena
leaderboard name
LMArena Text Factuality Coding
dimension
factuality
metric
Arena rating
rank
124
sample size
12855
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1466.9299735809748
confidence upper
1478.362010410755
Original result ↗

LMArena

1,403.725

source id
lmarena
leaderboard name
LMArena Text German
dimension
general
metric
Arena rating
rank
126
sample size
1069
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1385.077397263263
confidence upper
1422.3735958629024
Original result ↗

LMArena

1,438.43

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Life And Physical And Social Science
dimension
factuality
metric
Arena rating
rank
127
sample size
7515
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1431.4995621774578
confidence upper
1445.3601711958652
Original result ↗

LMArena

1,452.49

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts English
dimension
factuality
metric
Arena rating
rank
128
sample size
13969
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1446.9264685288315
confidence upper
1458.0529853864427
Original result ↗

LMArena

1,352.439

source id
lmarena
leaderboard name
LMArena Text Japanese
dimension
general
metric
Arena rating
rank
128
sample size
641
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1327.9455625768478
confidence upper
1376.9320392643756
Original result ↗

LMArena

1,459.872

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Software And It Services
dimension
factuality
metric
Arena rating
rank
129
sample size
21223
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1455.2281170927251
confidence upper
1464.515998808636
Original result ↗

LMArena

1,435.64

source id
lmarena
leaderboard name
LMArena Text Coding
dimension
general
metric
Arena rating
rank
130
sample size
15074
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1429.9902087250907
confidence upper
1441.290731193497
Original result ↗

LMArena

1,421.174

source id
lmarena
leaderboard name
LMArena Text French
dimension
general
metric
Arena rating
rank
131
sample size
2040
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1406.6606348120156
confidence upper
1435.686840086482
Original result ↗

LMArena

1,419.749

source id
lmarena
leaderboard name
LMArena Text Factuality Multi Turn
dimension
factuality
metric
Arena rating
rank
133
sample size
8011
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1412.7953577374196
confidence upper
1426.7035667218481
Original result ↗

LMArena

1,409.873

source id
lmarena
leaderboard name
LMArena Text Factuality Instruction Following
dimension
factuality
metric
Arena rating
rank
133
sample size
16878
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1404.9569340500823
confidence upper
1414.7894444871677
Original result ↗

LMArena

1,374.708

source id
lmarena
leaderboard name
LMArena Text Factuality Creative Writing
dimension
factuality
metric
Arena rating
rank
133
sample size
7431
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1368.1839202076378
confidence upper
1381.2324915036215
Original result ↗

LMArena

1,446.162

source id
lmarena
leaderboard name
LMArena Text Chinese
dimension
general
metric
Arena rating
rank
135
sample size
3607
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1436.0783172578176
confidence upper
1456.2452135391977
Original result ↗

LMArena

1,434.507

source id
lmarena
leaderboard name
LMArena Text Industry Software And It Services
dimension
general
metric
Arena rating
rank
135
sample size
22592
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1429.6032037691223
confidence upper
1439.4098068455685
Original result ↗

LMArena

1,432.159

source id
lmarena
leaderboard name
LMArena Text Factuality English
dimension
factuality
metric
Arena rating
rank
135
sample size
24374
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1427.893186368174
confidence upper
1436.4248413621044
Original result ↗

LMArena

1,392.895

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Writing And Literature And Language
dimension
factuality
metric
Arena rating
rank
136
sample size
12238
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1387.4239826044386
confidence upper
1398.3650646687654
Original result ↗

LMArena

1,421.299

source id
lmarena
leaderboard name
LMArena Text Expert
dimension
general
metric
Arena rating
rank
137
sample size
5247
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1412.858950142681
confidence upper
1429.7398968668622
Original result ↗

LMArena

1,419.696

source id
lmarena
leaderboard name
LMArena Text Industry Mathematical
dimension
general
metric
Arena rating
rank
137
sample size
3116
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1408.7743570578828
confidence upper
1430.6181578729515
Original result ↗

LMArena

1,416.665

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Business And Management And Financial Operations
dimension
factuality
metric
Arena rating
rank
138
sample size
9341
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1410.05196984845
confidence upper
1423.2782495612812
Original result ↗

LMArena

1,424.418

source id
lmarena
leaderboard name
LMArena Text Factuality Longer Query
dimension
factuality
metric
Arena rating
rank
139
sample size
20308
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1419.7388772572515
confidence upper
1429.0972357323747
Original result ↗

Published prices

1–7 / 7

stepfun-ai/Step-3.5-Flash ↗

$0.10

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)

stepfun-ai/Step-3.5-Flash ↗

$0.30

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)

step-3.5-flash ↗

$0.02

Inference provider
stepFun
Platform
StepFun
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input / 1M tokens

step-3.5-flash ↗

$0.10

Inference provider
stepFun
Platform
StepFun
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input / 1M tokens (cache miss)

step-3.5-flash ↗

$0.30

Inference provider
stepFun
Platform
StepFun
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output / 1M tokens

Provider specifications & access

1–2 / 2

Step 3.5 Flash ↗

source model id
step-3.5-flash
hosting
stepfun-global-hosted
platforms
  • StepFun
context length
256000
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • streaming
  • structuredOutputs
  • toolCalling

Step-3.5-Flash ↗

source model id
stepfun-ai/Step-3.5-Flash
hosting
siliconflow-hosted
platforms
  • SiliconFlow
max output tokens
65536
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • toolCalling

Source specification observations

1–3 / 3

siliconFlow ↗

field
context_length
value
262K
scope
source-model
source id
siliconFlow
confidence
1

stepFun ↗

field
context_length
value
256000
normalized value
256000
scope
source-model
source id
stepFun
confidence
1

siliconFlow ↗

field
max_output_tokens
value
66K
scope
source-model
source id
siliconFlow
confidence
1

Original sources

1–14 / 14

SiliconFlow · Model page ↗

StepFun · Model reference ↗

Hugging Face · Model repository ↗

DeepInfra · Model page ↗

SiliconFlow · Playground ↗

SiliconFlow · API documentation ↗

StepFun · Model documentation ↗

DeepInfra · Catalog ↗

Epoch AI · Catalog ↗

Hugging Face · Catalog ↗

Hugging Face · Catalog ↗

LMArena · Catalog ↗

SiliconFlow · Catalog ↗

StepFun · Catalog ↗

Source links

1–9 / 9

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace