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 DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 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 BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

StepFun model product

Step3 VL 10B

STEP3-VL-10B is a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence.

Updated Aug 17, 2026. Default version: Step3-VL-10B

Compare
LLMBoard Score43.0Step3-VL-10B
Coverage40%6 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

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

Step3 VL 10B Capability Profile

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

Step3-VL-10B LLMBoard score breakdown

Step3 VL 10B Benchmark Results

Benchmark scores for Step3-VL-10B.

6 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkMMBenchScore91.8%Rank01Participants9Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMathVistaScore84.0%Rank05Participants39Percentile89.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkMulti-ChallengeScore62.6%Rank07Participants29Percentile78.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkMathVisionScore70.8%Rank16Participants33Percentile53.1%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMMUScore78.1%Rank16Participants63Percentile75.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkAIME 2025Score87.7%Rank54Participants115Percentile53.5%EvidenceCEvaluatedAug 17, 2026

Step3 VL 10B 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.

Step3 VL 10B Pricing

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

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No provider prices

The default version has no current input or output token prices.

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

Step3 VL 10B Runtime Performance

Provider-specific output speed and catalog latency for Step3-VL-10B. Runtime does not affect the capability score.

No runtime data

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

Browse runtime rankings

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

Step3 VL 10B Specifications

Technical details for the model's default version.

Version
Step3-VL-10B
Released
Jan 15, 2026
Knowledge cutoff
Unknown
Parameters
10B
Context window
N/A
Max output
N/A
Inputs
image, text
Outputs
text
Open weights
No
License
Apache 2.0

Step3 VL 10B Versions

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

1 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionStep3-VL-10BReleasedJan 15, 2026LLMBoard43.0Parameters10BContextN/AMax outputN/AOpen weightsNoLicenseApache 2.0

Step3 VL 10B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Step3 VL 10BvsDeepSeek-R1Step3 VL 10BvsNova 2 OmniStep3 VL 10BvsGPT-OSS-120BStep3 VL 10BvsQwen3 VL 235B A22BStep3 VL 10BvsNova 2 LiteStep3 VL 10BvsQwen3 235B A22B

Models similar to Step3 VL 10B

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

#62+17.3
ST

Step 3.5 Flash

StepFun

60.3 LLMBoard

DetailsCompare
#124+0.2
OP

GPT-OSS-120B

OpenAI

43.2 LLMBoard

DetailsCompare
#123+0.4
AM

Nova 2 Omni

Amazon

43.4 LLMBoard

DetailsCompare
#126-0.4
AC

Qwen3 VL 235B A22B

Alibaba Cloud / Qwen Team

42.7 LLMBoard

DetailsCompare
#122+0.4
DE

DeepSeek-R1

DeepSeek

43.5 LLMBoard

DetailsCompare
#127-0.6
AM

Nova 2 Lite

Amazon

42.4 LLMBoard

DetailsCompare

What is Step3 VL 10B?

Key information about Step3 VL 10B and its available data.

STEP3-VL-10B is a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. 2T multimodal tokens integrating a language-aligned Perception Encoder with a Qwen3-8B decoder.

Features Parallel Coordinated Reasoning (PaCoRe) to scale test-time compute for complex perceptual reasoning.

Data as of 2026-08-17.

FAQ

Common questions about Step3 VL 10B.

When was Step3 VL 10B released?

Step3 VL 10B's default version was released on Jan 15, 2026.

How much does Step3 VL 10B cost?

No official standard PAYG price is currently available for Step3 VL 10B.

Who created Step3 VL 10B?

Step3 VL 10B was created by StepFun.

What is the context window for Step3 VL 10B?

A context window is not available for the default version.

Is Step3 VL 10B open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Step3 VL 10B?

No provider offering is currently linked to the default version.

What models should I compare Step3 VL 10B with?

Nearby ranked alternatives include DeepSeek-R1, Nova 2 Omni, GPT-OSS-120B.