# LFM2.5-VL-3B Benchmark Scores & Performance

> LFM2.5-VL-3B by LiquidAI has 10 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/lfm2-5-vl-3b

Last updated: September 10, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | LiquidAI |
| Source Type | Open Weight |
| Reasoning Type | Non-Reasoning |
| Context Window | 32K |
| Official model card | [Liquid AI LFM2.5-VL-3B model card](https://huggingface.co/LiquidAI/LFM2.5-VL-3B) |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: LFM2.5-VL-3B
- Variant: base
- Benchmarks covered: 10 of 434
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [BFCL v4](/benchmarks/bfcl-v4) | 32.5% |

## Multimodal & Grounded Benchmarks

| Benchmark | Score |
|-----------|-------|
| [RealWorldQA](/benchmarks/realworldqa) | 73.1% |
| [SimpleVQA](/benchmarks/simplevqa) | 35.4% |
| [CountBench](/benchmarks/countbench) | 87.3% |
| [MMMU](/benchmarks/mmmu) | 48.4% |
| [MMMU-Pro](/benchmarks/mmmu-pro) | 30.5% |
| [OCRBench V2](/benchmarks/ocrbenchv2) | 47.5% |
| [RefCOCO (avg)](/benchmarks/refcocoavg) | 87.9% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [IFEval](/benchmarks/ifeval) | 82.3% |
| [IFBench](/benchmarks/ifbench) | 25.8% |

## Other LiquidAI Models

- [LFM2.5-2.6B](/models/lfm2-5-2-6b) - Score: 39.6
- [LFM2.5-8B-A1B](/models/lfm2-5-8b-a1b) - Score: 38.98
- [LFM2-24B-A2B](/models/lfm2-24b-a2b) - Score: 18.57
- [LFM2.5-1.2B-Thinking](/models/lfm2-5-1-2b-thinking) - Score: 16.74
- [LFM2.5-1.2B-Instruct](/models/lfm2-5-1-2b-instruct) - Score: 16.06
- [LFM2.5-VL-450M](/models/lfm2-5-vl-450m) - Score: not computed
- [LFM2.5-230M](/models/lfm2-5-230m) - Score: not computed
- [LFM2.5-VL-1.6B-Extract](/models/lfm2-5-vl-1-6b-extract) - Score: not computed
- [LFM2.5-VL-450M-Extract](/models/lfm2-5-vl-450m-extract) - Score: not computed
- [LFM2.5-ColBERT-350M](/models/lfm2-5-colbert-350m) - Score: not computed
- [LFM2.5-Embedding-350M](/models/lfm2-5-embedding-350m) - Score: not computed
- [LFM2.5-1.2B-JP-202606](/models/lfm2-5-1-2b-jp-202606) - Score: not computed
- [LFM2.5-350M](/models/lfm2-5-350m) - Score: not computed