Liquid AI model product
LFM2.5 VL 3B
5 VL 3B is Liquid AI’s open-weight vision-language model for image-text-to-text tasks on devices and at the edge.
Updated Oct 23, 2026. Default version: LFM2.5-VL-3B
LLMBoard Score4.8LFM2.5-VL-3B
Coverage20%22 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
LFM2.5 VL 3B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
LFM2.5 VL 3B Benchmark Results
Benchmark scores for LFM2.5-VL-3B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMME | Score73.10% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMM IF-Eval | Score60.60% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPOPE | Score88.70% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTextVQA | Score84.30% | Rank04 | Participants16 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkRefCOCO-avg | Score0.88 points | Rank08 | Participants9 | Percentile12.50% | EvidenceC | Evaluated |
| BenchmarkMMMU (val) | Score48.40% | Rank12 | Participants13 | Percentile8.33% | EvidenceC | Evaluated |
| BenchmarkMuirBench | Score58.30% | Rank14 | Participants14 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (en) | Score47.50% | Rank14 | Participants15 | Percentile7.14% | EvidenceC | Evaluated |
| BenchmarkBLINK | Score61.50% | Rank15 | Participants17 | Percentile12.50% | EvidenceC | Evaluated |
| BenchmarkMMBench-V1.1 | Score81.00% | Rank16 | Participants20 | Percentile21.05% | EvidenceC | Evaluated |
| BenchmarkOCRBench | Score84.20% | Rank17 | Participants24 | Percentile30.43% | EvidenceC | Evaluated |
| BenchmarkSimpleVQA | Score0.35 points | Rank17 | Participants17 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkDocVQA | Score91.10% | Rank19 | Participants28 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score81.30% | Rank20 | Participants26 | Percentile24.00% | EvidenceC | Evaluated |
| BenchmarkHallusion Bench | Score47.20% | Rank20 | Participants20 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkBFCL-V4 | Score32.50% | Rank21 | Participants22 | Percentile4.76% | EvidenceC | Evaluated |
| BenchmarkMathVista-Mini | Score68.50% | Rank22 | Participants26 | Percentile16.00% | EvidenceC | Evaluated |
| BenchmarkMMStar | Score63.30% | Rank23 | Participants27 | Percentile15.38% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score59.40% | Rank23 | Participants25 | Percentile8.33% | EvidenceC | Evaluated |
| BenchmarkRealWorldQA | Score73.10% | Rank24 | Participants32 | Percentile25.81% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score25.80% | Rank45 | Participants46 | Percentile2.22% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score82.30% | Rank52 | Participants70 | Percentile26.09% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score30.50% | Rank73 | Participants73 | Percentile0.00% | EvidenceC | Evaluated |
LFM2.5 VL 3B 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.
LFM2.5 VL 3B 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.
LFM2.5 VL 3B Runtime Performance
Provider-specific output speed and catalog latency for LFM2.5-VL-3B. 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.
LFM2.5 VL 3B Specifications
Technical details for the model's default version.
- Version
- LFM2.5-VL-3B
- Released
- Aug 12, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 3.1B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- LFM Open License v1.0
LFM2.5 VL 3B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLFM2.5-VL-3B | Released | LLMBoard4.84 | Parameters3.1B | ContextN/A | Max outputN/A | Open weightsYes | LicenseLFM Open License v1.0 |
Models similar to LFM2.5 VL 3B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
LA
LFM2.5 2.6B
Liquid AI
OP
GPT-4o-mini
OpenAI
MA
Mistral Small 3 24B
Mistral AI
MI
Phi 4 multimodal
Microsoft
MA
Mistral Small 3.1 24B
Mistral AI
NR
Hermes 3 70B
Nous Research
What is LFM2.5 VL 3B?
Key information about LFM2.5 VL 3B and its available data.
6B language backbone with a SigLIP2 400M NaFlex vision encoder. It has a 32,768-token context and supports image-text-to-text processing.
Data as of 2026-10-22.
FAQ
Common questions about LFM2.5 VL 3B.
When was LFM2.5 VL 3B released?
LFM2.5 VL 3B's default version was released on Aug 12, 2026.
How much does LFM2.5 VL 3B cost?
No official standard PAYG price is currently available for LFM2.5 VL 3B.
Who created LFM2.5 VL 3B?
LFM2.5 VL 3B was created by Liquid AI.
What is the context window for LFM2.5 VL 3B?
A context window is not available for the default version.
Is LFM2.5 VL 3B open weight?
Yes. The default version is marked as open weight under LFM Open License v1.0.
How many API providers offer LFM2.5 VL 3B?
No provider offering is currently linked to the default version.