The AI arena is free today

Open Superagent

LFM2.5-VL-3B vs Phi-3.5-vision-instruct

LFM2.5-VL-3B shows notably better performance in the majority of benchmarks.

Liquid AI · Microsoft · Updated for 2026

Which is better?

LFM2.5-VL-3B outperforms in 2 benchmarks (POPE, TextVQA), while Phi-3.5-vision-instruct is better at 1 benchmark (ChartQA). LFM2.5-VL-3B shows notably better performance in the majority of benchmarks.

Based on current benchmark, pricing, and model metadata for 2026.

Choose LFM2.5-VL-3B

  • you want the strongest raw capability — it leads on 2 of 3 shared benchmarks
  • you want the most recent training data — it shipped Aug 2026

Choose Phi-3.5-vision-instruct

  • you are already invested in the Microsoft ecosystem

At a glance

The differences that matter most.

Benchmark wins
2 of 3
1 of 3
Input price
— / M
— / M
Output price
— / M
— / M
Context window
Released
Aug 2026
Aug 2024
License
LFM Open License v1.0
MIT

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

LFM2.5-VL-3B outperforms in 2 benchmarks (POPE, TextVQA), while Phi-3.5-vision-instruct is better at 1 benchmark (ChartQA).

LFM2.5-VL-3B shows notably better performance in the majority of benchmarks.

Tue Aug 25 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Model Size

Parameter count comparison

1.1B diff

Phi-3.5-vision-instruct has 1.1B more parameters than LFM2.5-VL-3B, making it 34.5% larger.

Liquid AI
LFM2.5-VL-3B
3.1Bparameters
Microsoft
Phi-3.5-vision-instruct
4.2Bparameters
3.1B
LFM2.5-VL-3B
4.2B
Phi-3.5-vision-instruct

Input Capabilities

Supported data types and modalities

Both LFM2.5-VL-3B and Phi-3.5-vision-instruct support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

LFM2.5-VL-3B

Text
Images
Audio
Video

Phi-3.5-vision-instruct

Text
Images
Audio
Video

License

Usage and distribution terms

LFM2.5-VL-3B is licensed under LFM Open License v1.0, while Phi-3.5-vision-instruct uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

LFM2.5-VL-3B

LFM Open License v1.0

Open weights

Phi-3.5-vision-instruct

MIT

Open weights

Release Timeline

When each model was launched

LFM2.5-VL-3B was released on 2026-08-12, while Phi-3.5-vision-instruct was released on 2024-08-23.

LFM2.5-VL-3B is 24 months newer than Phi-3.5-vision-instruct.

LFM2.5-VL-3B

Aug 12, 2026

1 weeks ago

2.0yr newer
Phi-3.5-vision-instruct

Aug 23, 2024

2.0 years ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against LFM2.5-VL-3B and Phi-3.5-vision-instruct side-by-side, then vote on the output you prefer.

LFM2.5-VL-3B
✓ Preferred
Phi-3.5-vision-instruct
Open in Playground

FAQ

Common questions about LFM2.5-VL-3B vs Phi-3.5-vision-instruct.

Which is better, LFM2.5-VL-3B or Phi-3.5-vision-instruct?

LFM2.5-VL-3B shows notably better performance in the majority of benchmarks. LFM2.5-VL-3B is made by Liquid AI and Phi-3.5-vision-instruct is made by Microsoft. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does LFM2.5-VL-3B compare to Phi-3.5-vision-instruct in benchmarks?

LFM2.5-VL-3B scores DocVQA: 91.1%, POPE: 88.7%, RefCOCO-avg: 87.9%, TextVQA: 84.3%, OCRBench: 84.2%. Phi-3.5-vision-instruct scores ScienceQA: 91.3%, POPE: 86.1%, MMBench: 81.9%, ChartQA: 81.8%, AI2D: 78.1%.

What are the main differences between LFM2.5-VL-3B and Phi-3.5-vision-instruct?

Key differences include licensing (LFM Open License v1.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes LFM2.5-VL-3B and Phi-3.5-vision-instruct?

LFM2.5-VL-3B is developed by Liquid AI and Phi-3.5-vision-instruct is developed by Microsoft.