llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1367 models808 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

StepFun model product

Step 3.7 Flash

7 Flash is a StepFun large language model for agents, coding, and multimodal prompts.

Updated Oct 23, 2026. Default version: Step 3.7 Flash

LLMBoard Score49.3Step 3.7 Flash
Coverage80%4 benchmark families
Context window262.1KTokens
Official input price$0.20StepFun (Global) API

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Step 3.7 Flash Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Step 3.7 Flash LLMBoard score breakdown

Step 3.7 Flash Benchmark Results

Benchmark scores for Step 3.7 Flash.

11 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkGDPvalScore45.80%Rank04Participants4Percentile0.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkHumanity's Last Exam (with tools, text-only)Score47.20%Rank08Participants10Percentile22.22%EvidenceCEvaluatedOct 22, 2026
BenchmarkTerminal-Bench 2.1Score59.50%Rank38Participants48Percentile21.28%EvidenceCEvaluatedOct 22, 2026
BenchmarkSWE-Bench ProScore56.30%Rank39Participants63Percentile38.71%EvidenceCEvaluatedOct 22, 2026
BenchmarkAA SciCode SubtasksScore43.87%Rank51Participants89Percentile43.18%EvidenceBEvaluatedN/A
BenchmarkAA IFBenchScore67.28%Rank60Participants168Percentile64.67%EvidenceBEvaluatedN/A
BenchmarkAA LCR v1.1Score73.67%Rank71Participants193Percentile63.54%EvidenceBEvaluatedN/A
BenchmarkAA CritPtScore2.29%Rank72Participants200Percentile64.32%EvidenceBEvaluatedN/A
BenchmarkAA Omniscience AccuracyScore25.78%Rank80Participants201Percentile60.50%EvidenceBEvaluatedN/A
BenchmarkAA HLE Text No ToolsScore21.41%Rank85Participants200Percentile57.79%EvidenceBEvaluatedN/A
BenchmarkAA GPQA DiamondScore80.91%Rank95Participants199Percentile52.53%EvidenceBEvaluatedN/A

Step 3.7 Flash Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

Step 3.7 Flash Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
$0.20 input, $1.15 output per 1M
Official provider
StepFun (Global)
Lowest third-party
From $0.19 input, $1.14 output per 1M via Ambient
Tracked offerings
19
17 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderUnoRouterProvider model IDstep-3.7-flash:freeRegionglobalInput / 1MN/AOutput / 1MN/AContext256KUpdatedOct 23, 2026
ProviderAmbientProvider model IDstepfun/step-3.7-flashRegionglobalInput / 1M$0.19Output / 1M$1.14Context262.1KUpdatedOct 23, 2026
ProviderDeep InfraProvider model IDstepfun-ai/Step-3.7-FlashRegionglobalInput / 1M$0.20Output / 1M$1.15Context262.1KUpdatedOct 23, 2026
ProviderHugging FaceProvider model IDstepfun-ai/Step-3.7-FlashRegionglobalInput / 1M$0.20Output / 1M$1.15Context262.1KUpdatedOct 23, 2026
ProviderOpenRouterProvider model IDstepfun/step-3.7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context262.1KUpdatedOct 23, 2026
ProviderStepFun (Global)Provider model IDstep-3.7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context256KUpdatedOct 23, 2026
ProviderZenMuxProvider model IDstepfun/step-3.7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context256KUpdatedOct 23, 2026
ProviderRequestyProvider model IDstep-3.7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context262.1KUpdatedOct 23, 2026
ProviderEmpirioLabs AIProvider model IDstep-3-7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context256KUpdatedOct 23, 2026
ProviderVercel AI GatewayProvider model IDstepfun/step-3.7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context256KUpdatedOct 23, 2026
ProviderKilo GatewayProvider model IDstepfun/step-3.7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context256KUpdatedOct 23, 2026
ProviderDevPass (LLM Gateway)Provider model IDstep-3.7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context262.1KUpdatedOct 23, 2026
ProviderNovita AIProvider model IDstepfun/step-3.7-flashRegionglobalInput / 1M$0.20Output / 1M$1.15Context262.1KUpdatedOct 23, 2026
ProviderCommandCodeProvider model IDstepfun/Step-3.7-FlashRegionglobalInput / 1M$0.20Output / 1M$1.15Context256KUpdatedOct 23, 2026
ProviderStepFun (China)Provider model IDstep-3.7-flashRegionglobalInput / 1M$0.2018Output / 1M$1.21Context256KUpdatedOct 23, 2026
ProviderAIHubMixProvider model IDstep-3.7-flashRegionglobalInput / 1M$0.22Output / 1M$1.32Context256KUpdatedOct 23, 2026
ProviderKenariProvider model IDstep-3-7-flashRegionglobalInput / 1M$0.24Output / 1M$1.37Context256KUpdatedOct 23, 2026

Step 3.7 Flash Runtime Performance

Provider-specific output speed and catalog latency for Step 3.7 Flash. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Step 3.7 Flash Specifications

Technical details for the model's default version.

Version
Step 3.7 Flash
Released
Jun 10, 2026
Knowledge cutoff
Unknown
Parameters
198B
Context window
262.1K
Max output
262.1K
Inputs
image, text, video
Outputs
text
Open weights
Yes
License
Apache 2.0

Step 3.7 Flash Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionStep 3.7 FlashReleasedJun 10, 2026LLMBoard49.27Parameters198BContext262.1KMax output262.1KOpen weightsYesLicenseApache 2.0

Models similar to Step 3.7 Flash

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#170-8.22
ST

Step3 VL 10B

StepFun

41.05 LLMBoard

Details
#98+9.22
ST

Step 3.5 Flash

StepFun

58.49 LLMBoard

Details
#136+0.37
NV

Nemotron 3.5 Bolt

NVIDIA

49.64 LLMBoard

Details
#138-0.39
XI

MiMo V2 Omni

Xiaomi

48.88 LLMBoard

Details
#139-0.64
GO

Gemini 2.5 Pro

Google

48.63 LLMBoard

Details
#140-0.69
OP

GPT-5.1-Codex

OpenAI

48.58 LLMBoard

Details

What is Step 3.7 Flash?

Key information about Step 3.7 Flash and its available data.

7 Flash is a newer StepFun flash model designed for agents, coding, and multimodal prompts.

Data as of 2026-10-22.

FAQ

Common questions about Step 3.7 Flash.

When was Step 3.7 Flash released?

Step 3.7 Flash's default version was released on Jun 10, 2026.

How much does Step 3.7 Flash cost?

Step 3.7 Flash's official API price is $0.20 per million input tokens and $1.15 per million output tokens via StepFun (Global). The lowest tracked third-party offer starts at $0.19 input and $1.14 output via Ambient.

Who created Step 3.7 Flash?

Step 3.7 Flash was created by StepFun.

What is the context window for Step 3.7 Flash?

The default version has a 262.1K token context window.

Is Step 3.7 Flash open weight?

Yes. The default version is marked as open weight under Apache 2.0.

How many API providers offer Step 3.7 Flash?

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

19 provider offerings are linked to the default version.

Browse runtime rankings