The AI arena is free today

Open Superagent

Codestral-22B vs Phi-4-multimodal-instruct

Codestral-22B and Phi-4-multimodal-instruct are closely matched at 0.1 and 3.0 on the LLM Stats Score.

Mistral AI · Microsoft · Updated for 2026

Which is better?

Codestral-22B and Phi-4-multimodal-instruct are closely matched on the overall LLM Stats Score at 0.1 and 3.0.

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

Choose Codestral-22B

  • you are already invested in the Mistral AI ecosystem

Choose Phi-4-multimodal-instruct

  • you want the most recent training data — it shipped Feb 2025

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Phi-4-multimodal-instruct
Microsoft
Core performance indexes
LLM Stats Score
0.1
#314
3.0
#300
Reasoning
-0.0
#307
0.1
#305
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.05 / M
Output price
— / M
$0.10 / M
Context window
—
128,000

Individual benchmarks

7 reported for Codestral-22B · 15 for Phi-4-multimodal-instruct

No common benchmarks found

Codestral-22B and Phi-4-multimodal-instructdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

16.6B diff

Codestral-22B has 16.6B more parameters than Phi-4-multimodal-instruct, making it 296.4% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Microsoft
Phi-4-multimodal-instruct
5.6Bparameters
22.2B
Codestral-22B
5.6B
Phi-4-multimodal-instruct

Context Window

Maximum input and output token capacity

Only Phi-4-multimodal-instruct specifies input context (128,000 tokens). Only Phi-4-multimodal-instruct specifies output context (128,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Microsoft
Phi-4-multimodal-instruct
Input128,000 tokens
Output128,000 tokens
Mon Sep 07 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Phi-4-multimodal-instruct supports multimodal inputs, whereas Codestral-22B does not.

Phi-4-multimodal-instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Phi-4-multimodal-instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Phi-4-multimodal-instruct uses MIT.

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

Codestral-22B

MNPL-0.1

Open weights

Phi-4-multimodal-instruct

MIT

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Phi-4-multimodal-instruct was released on 2025-02-01.

Phi-4-multimodal-instruct is 8 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Phi-4-multimodal-instruct

Feb 1, 2025

1.6 years ago

8mo newer

Knowledge Cutoff

When training data ends

Phi-4-multimodal-instruct has a documented knowledge cutoff of 2024-06-01, while Codestral-22B's cutoff date is not specified.

We can confirm Phi-4-multimodal-instruct's training data extends to 2024-06-01, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

Phi-4-multimodal-instruct

Jun 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and Phi-4-multimodal-instruct side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Phi-4-multimodal-instruct
Open in Playground

FAQ

Common questions about Codestral-22B vs Phi-4-multimodal-instruct.

Which is better, Codestral-22B or Phi-4-multimodal-instruct?

Codestral-22B and Phi-4-multimodal-instruct are closely matched on the LLM Stats Score at 0.1 and 3.0. Codestral-22B is made by Mistral AI and Phi-4-multimodal-instruct is made by Microsoft. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to Phi-4-multimodal-instruct in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Phi-4-multimodal-instruct scores ScienceQA Visual: 97.5%, DocVQA: 93.2%, MMBench: 86.7%, POPE: 85.6%, OCRBench: 84.4%.

What are the context window sizes for Codestral-22B and Phi-4-multimodal-instruct?

Codestral-22B supports an unknown number of tokens and Phi-4-multimodal-instruct supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Codestral-22B and Phi-4-multimodal-instruct?

Key differences include LLM Stats Score (0.1 vs 3.0), multimodal support (no vs yes), licensing (MNPL-0.1 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Phi-4-multimodal-instruct?

Codestral-22B is developed by Mistral AI and Phi-4-multimodal-instruct is developed by Microsoft.

Related comparisons