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
1464 models816 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

Liquid AI model product

LFM3 VL 2B

LFM3 VL 2B is an open-weight vision-language model that accepts text, images, and video and produces text.

Updated Nov 22, 2026. Default version: LFM3-VL-2B

LLMBoard Score25.2LFM3-VL-2B
Coverage0%37 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

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

LFM3 VL 2B Capability Profile

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

LFM3-VL-2B LLMBoard score breakdown

LFM3 VL 2B Benchmark Results

Benchmark scores for LFM3-VL-2B.

30 of 41 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkActivityNetScore71.20%Rank01Participants2Percentile100.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkChartQAScore92.70%Rank01Participants27Percentile100.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkDocVQAScore96.70%Rank01Participants29Percentile100.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkInfoVQAScore86.20%Rank01Participants11Percentile100.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkMMEScore86.90%Rank01Participants5Percentile100.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkMM IF-EvalScore72.80%Rank01Participants3Percentile100.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkTextVQAScore87.90%Rank01Participants17Percentile100.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkHR-Bench (4k)Score82.30%Rank02Participants2Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkPOPEScore88.70%Rank02Participants4Percentile66.67%EvidenceCEvaluatedNov 21, 2026
BenchmarkRoboSpatialHomeScore0.63 pointsRank02Participants2Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkWe-MathScore68.60%Rank02Participants2Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkBLINKScore71.10%Rank05Participants18Percentile76.47%EvidenceCEvaluatedNov 21, 2026
BenchmarkDynaMathScore79.20%Rank06Participants10Percentile44.44%EvidenceCEvaluatedNov 21, 2026
BenchmarkMotionBenchScore64.00%Rank06Participants6Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkRefCOCO-avgScore0.91 pointsRank07Participants10Percentile33.33%EvidenceCEvaluatedNov 21, 2026
BenchmarkEmbSpatialBenchScore0.83 pointsRank08Participants9Percentile12.50%EvidenceCEvaluatedNov 21, 2026
BenchmarkHallusion BenchScore65.60%Rank08Participants21Percentile65.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkMMVUScore52.90%Rank08Participants8Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkCountBenchScore0.93 pointsRank09Participants10Percentile11.11%EvidenceCEvaluatedNov 21, 2026
BenchmarkMLVU-MScore71.30%Rank09Participants9Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkOCRBench-V2 (en)Score63.50%Rank09Participants16Percentile46.67%EvidenceCEvaluatedNov 21, 2026
BenchmarkRefSpatialBenchScore0.50 pointsRank09Participants9Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkCharXiv-DScore87.50%Rank10Participants19Percentile50.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkMMMU (val)Score55.70%Rank11Participants14Percentile23.08%EvidenceCEvaluatedNov 21, 2026
BenchmarkMuirBenchScore66.40%Rank11Participants16Percentile33.33%EvidenceCEvaluatedNov 21, 2026
BenchmarkVideoMME w/o sub.Score62.80%Rank11Participants11Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkMathVista-MiniScore84.20%Rank12Participants27Percentile57.69%EvidenceCEvaluatedNov 21, 2026
BenchmarkMMBench-V1.1Score86.10%Rank13Participants21Percentile40.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkVideoMME w sub.Score69.00%Rank13Participants13Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkMMStarScore74.40%Rank15Participants28Percentile48.15%EvidenceCEvaluatedNov 21, 2026

LFM3 VL 2B 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.

LFM3 VL 2B 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.

LFM3 VL 2B Runtime Performance

Provider-specific output speed and catalog latency for LFM3-VL-2B. 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.

LFM3 VL 2B Specifications

Technical details for the model's default version.

Version
LFM3-VL-2B
Released
Oct 27, 2026
Knowledge cutoff
Unknown
Parameters
1.9B
Context window
N/A
Max output
N/A
Inputs
image, text
Outputs
text
Open weights
Yes
License
LFM Open License v1.0

LFM3 VL 2B 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
VersionLFM3-VL-2BReleasedOct 27, 2026LLMBoard25.22Parameters1.9BContextN/AMax outputN/AOpen weightsYesLicenseLFM Open License v1.0

Models similar to LFM3 VL 2B

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

#239+4.17
LA

LFM2.5 2.6B

Liquid AI

29.39 LLMBoard

Details
#190+16.29
LA

LFM3 1.7B

Liquid AI

41.51 LLMBoard

Details
#320-20.53
LA

LFM2.5 VL 3B

Liquid AI

4.69 LLMBoard

Details
#255-0.41
XA

Grok 4.20 Beta Reasoning

xAI

24.81 LLMBoard

Details
#253+0.71
AC

Qwen3 VL 8B Thinking

Alibaba Cloud / Qwen Team

25.93 LLMBoard

Details
#252+0.75
AC

Qwen3 VL 30B A3B

Alibaba Cloud / Qwen Team

25.97 LLMBoard

Details

What is LFM3 VL 2B?

Key information about LFM3 VL 2B and its available data.

92B-parameter vision-language model. It processes text, images, and video sampled at 2 fps, with text output.

Data as of 2026-11-21.

FAQ

Common questions about LFM3 VL 2B.

When was LFM3 VL 2B released?

LFM3 VL 2B's default version was released on Oct 27, 2026.

How much does LFM3 VL 2B cost?

No official standard PAYG price is currently available for LFM3 VL 2B.

Who created LFM3 VL 2B?

LFM3 VL 2B was created by Liquid AI.

What is the context window for LFM3 VL 2B?

A context window is not available for the default version.

Is LFM3 VL 2B open weight?

Yes. The default version is marked as open weight under LFM Open License v1.0.

How many API providers offer LFM3 VL 2B?

No provider offering is currently linked to the default version.

Browse runtime rankings