# LFM2.5-VL-3B vs LFM2.5-VL-450M

> Side-by-side benchmark comparison for LFM2.5-VL-3B and LFM2.5-VL-450M across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/lfm2-5-vl-3b-vs-lfm2-5-vl-450m
- Last updated: September 10, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick LFM2.5-VL-450M if you want the stronger benchmark profile. LFM2.5-VL-3B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- LFM2.5-VL-450M leads overall 37 to 0.
- The biggest single benchmark swing is IFEval in Instruction Following, with scores of 82.3% and 61.2%.
- LFM2.5-VL-450M also has the larger context window at 128K.

## Model Snapshot

| Property | LFM2.5-VL-3B | LFM2.5-VL-450M |
|----------|----------|----------|
| Creator | LiquidAI | LiquidAI |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | 32K | 128K |
| Overall Score | null | null |
| Benchmarks Covered | 10 | 7 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- LFM2.5-VL-3B public-lane score: Coming soon
- LFM2.5-VL-450M public-lane score: 42.2 (Estimated · #105/152)

| Benchmark | LFM2.5-VL-3B | LFM2.5-VL-450M | Winner |
|-----------|-----------|-----------|--------|
| BFCL v4 | 32.5% | 21.1% | LFM2.5-VL-3B |

### Multimodal & Grounded

- Winner: Coming soon
- LFM2.5-VL-3B public-lane score: Coming soon
- LFM2.5-VL-450M public-lane score: Coming soon

| Benchmark | LFM2.5-VL-3B | LFM2.5-VL-450M | Winner |
|-----------|-----------|-----------|--------|
| RealWorldQA | 73.1% | 58.4% | LFM2.5-VL-3B |
| SimpleVQA | 35.4% | Coming soon | Coming soon |
| CountBench | 87.3% | 73.3% | LFM2.5-VL-3B |
| MMMU | 48.4% | 32.7% | LFM2.5-VL-3B |
| MMMU-Pro | 30.5% | Coming soon | Coming soon |
| OCRBench V2 | 47.5% | Coming soon | Coming soon |
| RefCOCO (avg) | 87.9% | Coming soon | Coming soon |

### Knowledge

- Winner: Coming soon
- LFM2.5-VL-3B public-lane score: Coming soon
- LFM2.5-VL-450M public-lane score: 33.7 (Estimated · #166/183)

| Benchmark | LFM2.5-VL-3B | LFM2.5-VL-450M | Winner |
|-----------|-----------|-----------|--------|
| GPQA | Coming soon | 25.7% | Coming soon |
| MMLU-Pro | Coming soon | 19.3% | Coming soon |

### Instruction Following

- Winner: Coming soon
- LFM2.5-VL-3B public-lane score: Coming soon
- LFM2.5-VL-450M public-lane score: Coming soon

| Benchmark | LFM2.5-VL-3B | LFM2.5-VL-450M | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 82.3% | 61.2% | LFM2.5-VL-3B |
| IFBench | 25.8% | Coming soon | Coming soon |

## FAQ

### Which is better overall, LFM2.5-VL-3B or LFM2.5-VL-450M?

LFM2.5-VL-450M is ahead overall on BenchLM right now.

### How many benchmarks does LFM2.5-VL-3B cover on BenchLM?

LFM2.5-VL-3B currently has 10 sourced benchmark scores on BenchLM.

### How many benchmarks does LFM2.5-VL-450M cover on BenchLM?

LFM2.5-VL-450M currently has 7 sourced benchmark scores on BenchLM.

## Related Comparisons

- [LFM2.5-VL-3B vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-lfm2-5-vl-3b)
- [LFM2.5-VL-450M vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-lfm2-5-vl-450m)
- [LFM2.5-VL-3B vs GPT-6 Astra](/compare/gpt-6-astra-vs-lfm2-5-vl-3b)
- [LFM2.5-VL-450M vs GPT-6 Astra](/compare/gpt-6-astra-vs-lfm2-5-vl-450m)

## Explore More

- [LFM2.5-VL-3B profile](/models/lfm2-5-vl-3b)
- [LFM2.5-VL-450M profile](/models/lfm2-5-vl-450m)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)