The AI arena is free today

Open Superagent

LFM3-VL-2B vs Qwen2.5 VL 32B Instruct

LFM3-VL-2B leads the LLM Stats Score 15.5 to 9.5.

Liquid AI · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

LFM3-VL-2B leads the overall LLM Stats Score 15.5 to 9.5, ranking #265 overall.

In the 11 individual benchmarks reported for both models, LFM3-VL-2B wins 7; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose LFM3-VL-2B

  • overall performance matters — it scores 15.5 and ranks #265 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 7 of 11 exact shared results
  • you want the most recent training data — it shipped Oct 2026

Choose Qwen2.5 VL 32B Instruct

  • you are already invested in the Alibaba Cloud / Qwen Team ecosystem

At a glance

The differences that matter most.

LFM3-VL-2B
Liquid AI
Qwen2.5 VL 32B Instruct
Alibaba Cloud / Qwen Team
Core performance indexes
LLM Stats Score
15.5
#265
9.5
#306
Reasoning
16.2
#252
8.0
#312
Cost, coverage & limits
Benchmark wins
7 of 11
4 of 11
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
LFM3-VL-2B
Qwen2.5 VL 32B Instruct
Math
19.0#187
11.2#263
Vision
11.4#133
6.4#175
Multimodal
12.6#124
9.0#143
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

41 reported for LFM3-VL-2B · 28 for Qwen2.5 VL 32B Instruct

11 shared

LFM3-VL-2B outperforms in 7 benchmarks (DocVQA, InfoVQA, MathVision, MathVista-Mini, MMStar, OCRBench-V2 (en), ScreenSpot Pro), while Qwen2.5 VL 32B Instruct is better at 4 benchmarks (LVBench, MMMU-Pro, VideoMME w/o sub., VideoMME w sub.).

LFM3-VL-2B shows notably better performance in the majority of benchmarks.

Tue Nov 03 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

31.6B diff

Qwen2.5 VL 32B Instruct has 31.6B more parameters than LFM3-VL-2B, making it 1644.8% larger.

Liquid AI
LFM3-VL-2B
1.9Bparameters
Alibaba Cloud / Qwen Team
Qwen2.5 VL 32B Instruct
33.5Bparameters
1.9B
LFM3-VL-2B
33.5B
Qwen2.5 VL 32B Instruct

Input capabilities

Documented input modalities across available providers

Both LFM3-VL-2B and Qwen2.5 VL 32B Instruct support multimodal inputs.

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

LFM3-VL-2B

Text
Images
Audio
Video

Qwen2.5 VL 32B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

LFM3-VL-2B is licensed under LFM Open License v1.0, while Qwen2.5 VL 32B Instruct uses Apache 2.0.

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

LFM3-VL-2B

LFM Open License v1.0

Open weights

Qwen2.5 VL 32B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

LFM3-VL-2B was released on 2026-10-27, while Qwen2.5 VL 32B Instruct was released on 2025-02-28.

LFM3-VL-2B is 20 months newer than Qwen2.5 VL 32B Instruct.

LFM3-VL-2B

Oct 27, 2026

5 days ago

1.7yr newer
Qwen2.5 VL 32B Instruct

Feb 28, 2025

1.7 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?

Judge for yourself.

Run your own prompts against LFM3-VL-2B and Qwen2.5 VL 32B Instruct side-by-side, then vote on the output you prefer.

LFM3-VL-2B
✓ Preferred
Qwen2.5 VL 32B Instruct
Open in Playground

FAQ

Common questions about LFM3-VL-2B vs Qwen2.5 VL 32B Instruct.

Which is better, LFM3-VL-2B or Qwen2.5 VL 32B Instruct?

LFM3-VL-2B leads the LLM Stats Score 15.5 to 9.5. LFM3-VL-2B is made by Liquid AI and Qwen2.5 VL 32B Instruct is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does LFM3-VL-2B compare to Qwen2.5 VL 32B Instruct in benchmarks?

LFM3-VL-2B scores DocVQA: 96.7%, CountBench: 93.0%, ChartQA: 92.7%, RefCOCO-avg: 90.5%, POPE: 88.7%. Qwen2.5 VL 32B Instruct scores DocVQA: 94.8%, Android Control Low_EM: 93.3%, HumanEval: 91.5%, ScreenSpot: 88.5%, MBPP: 84.0%.

What are the main differences between LFM3-VL-2B and Qwen2.5 VL 32B Instruct?

Key differences include LLM Stats Score (15.5 vs 9.5), licensing (LFM Open License v1.0 vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes LFM3-VL-2B and Qwen2.5 VL 32B Instruct?

LFM3-VL-2B is developed by Liquid AI and Qwen2.5 VL 32B Instruct is developed by Alibaba Cloud / Qwen Team.

Related comparisons