The AI arena is free today

Open Superagent

Codestral-22B vs LFM2.5-VL-3B

Comparing Codestral-22B and LFM2.5-VL-3B across benchmarks, pricing, and capabilities.

Mistral AI · Liquid AI · Updated for 2026

Which is better?

Codestral-22B and LFM2.5-VL-3B trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

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

Choose Codestral-22B

  • you are already invested in the Mistral AI ecosystem

Choose LFM2.5-VL-3B

  • you want the most recent training data — it shipped Aug 2026

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
LFM2.5-VL-3B
Liquid AI
Benchmark wins
—
—
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—
Released
May 2024
Aug 2026
License
MNPL-0.1
LFM Open License v1.0

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

Codestral-22B and LFM2.5-VL-3Bdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Arena Performance

Playground indexes and blind preference scores

Model Size

Parameter count comparison

19.1B diff

Codestral-22B has 19.1B more parameters than LFM2.5-VL-3B, making it 610.7% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Liquid AI
LFM2.5-VL-3B
3.1Bparameters
22.2B
Codestral-22B
3.1B
LFM2.5-VL-3B

Input Capabilities

Supported data types and modalities

LFM2.5-VL-3B supports multimodal inputs, whereas Codestral-22B does not.

LFM2.5-VL-3B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

LFM2.5-VL-3B

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while LFM2.5-VL-3B uses LFM Open License v1.0.

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

Codestral-22B

MNPL-0.1

Open weights

LFM2.5-VL-3B

LFM Open License v1.0

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while LFM2.5-VL-3B was released on 2026-08-12.

LFM2.5-VL-3B is 27 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.2 years ago

LFM2.5-VL-3B

Aug 12, 2026

1 weeks ago

2.2yr newer

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 Codestral-22B and LFM2.5-VL-3B side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
LFM2.5-VL-3B
Open in Playground

FAQ

Common questions about Codestral-22B vs LFM2.5-VL-3B.

Which is better, Codestral-22B or LFM2.5-VL-3B?

Codestral-22B (Mistral AI) and LFM2.5-VL-3B (Liquid AI) each have strengths in different areas. Compare their benchmark scores, pricing, context windows, and capabilities above to determine which fits your needs.

How does Codestral-22B compare to LFM2.5-VL-3B in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. LFM2.5-VL-3B scores DocVQA: 91.1%, POPE: 88.7%, RefCOCO-avg: 87.9%, TextVQA: 84.3%, OCRBench: 84.2%.

What are the main differences between Codestral-22B and LFM2.5-VL-3B?

Key differences include multimodal support (no vs yes), licensing (MNPL-0.1 vs LFM Open License v1.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and LFM2.5-VL-3B?

Codestral-22B is developed by Mistral AI and LFM2.5-VL-3B is developed by Liquid AI.

Related comparisons