LFM2.5-VL-3B vs Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks.
Liquid AI · Alibaba Cloud / Qwen Team · Updated for 2026
Which is better?
LFM2.5-VL-3B outperforms in 0 benchmarks, while Qwen2.5 VL 72B Instruct is better at 8 benchmarks (ChartQA, DocVQA, Hallusion Bench, MathVista-Mini, MMMU-Pro, MMStar, OCRBench, OCRBench-V2 (en)). Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks.
Based on current benchmark, pricing, and model metadata for 2026.
Choose LFM2.5-VL-3B
- you want the most recent training data — it shipped Aug 2026
Choose Qwen2.5 VL 72B Instruct
- you want the strongest raw capability — it leads on 8 of 8 shared benchmarks
At a glance
The differences that matter most.
Performance Benchmarks
Comparative analysis across standard metrics
LFM2.5-VL-3B outperforms in 0 benchmarks, while Qwen2.5 VL 72B Instruct is better at 8 benchmarks (ChartQA, DocVQA, Hallusion Bench, MathVista-Mini, MMMU-Pro, MMStar, OCRBench, OCRBench-V2 (en)).
Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks.
Arena Performance
Playground indexes and blind preference scores
Model Size
Parameter count comparison
Qwen2.5 VL 72B Instruct has 68.9B more parameters than LFM2.5-VL-3B, making it 2205.1% larger.
Input Capabilities
Supported data types and modalities
Both LFM2.5-VL-3B and Qwen2.5 VL 72B Instruct support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
LFM2.5-VL-3B
Qwen2.5 VL 72B Instruct
License
Usage and distribution terms
LFM2.5-VL-3B is licensed under LFM Open License v1.0, while Qwen2.5 VL 72B Instruct uses tongyi-qianwen.
License differences may affect how you can use these models in commercial or open-source projects.
LFM Open License v1.0
Open weights
tongyi-qianwen
Open weights
Release Timeline
When each model was launched
LFM2.5-VL-3B was released on 2026-08-12, while Qwen2.5 VL 72B Instruct was released on 2025-01-26.
LFM2.5-VL-3B is 19 months newer than Qwen2.5 VL 72B Instruct.
Aug 12, 2026
1 weeks ago
1.5yr newerJan 26, 2025
1.6 years ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Outputs Comparison
Judge for yourself.
Run your own prompts against LFM2.5-VL-3B and Qwen2.5 VL 72B Instruct side-by-side, then vote on the output you prefer.
FAQ
Common questions about LFM2.5-VL-3B vs Qwen2.5 VL 72B Instruct.