The AI arena is free today

Open Superagent

Codestral-22B vs DeepSeek VL2 Small

Codestral-22B and DeepSeek VL2 Small are closely matched at 0.1 and 1.4 on the LLM Stats Score.

Mistral AI · DeepSeek · Updated for 2026

Which is better?

Codestral-22B and DeepSeek VL2 Small are closely matched on the overall LLM Stats Score at 0.1 and 1.4.

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 DeepSeek VL2 Small

  • you want the most recent training data — it shipped Dec 2024

At a glance

The differences that matter most.

Core performance indexes
0.1
#314
1.4
#309
-0.0
#307
-3.6
#326
Cost, coverage & limits
Benchmark wins
Input price
— / M
— / M
Output price
— / M
— / M
Context window

Individual benchmarks

7 reported for Codestral-22B · 14 for DeepSeek VL2 Small

No common benchmarks found

Codestral-22B and DeepSeek VL2 Smalldon'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

6.2B diff

Codestral-22B has 6.2B more parameters than DeepSeek VL2 Small, making it 38.8% larger.

Mistral AI
Codestral-22B
22.2Bparameters
DeepSeek
DeepSeek VL2 Small
16.0Bparameters
22.2B
Codestral-22B
16.0B
DeepSeek VL2 Small

Input capabilities

Documented input modalities across available providers

DeepSeek VL2 Small supports multimodal inputs, whereas Codestral-22B does not.

DeepSeek VL2 Small can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

DeepSeek VL2 Small

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while DeepSeek VL2 Small uses deepseek.

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

Codestral-22B

MNPL-0.1

Open weights

DeepSeek VL2 Small

deepseek

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while DeepSeek VL2 Small was released on 2024-12-13.

DeepSeek VL2 Small is 7 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

DeepSeek VL2 Small

Dec 13, 2024

1.7 years ago

6mo 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 DeepSeek VL2 Small side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
DeepSeek VL2 Small
Open in Playground

FAQ

Common questions about Codestral-22B vs DeepSeek VL2 Small.

Which is better, Codestral-22B or DeepSeek VL2 Small?

Codestral-22B and DeepSeek VL2 Small are closely matched on the LLM Stats Score at 0.1 and 1.4. Codestral-22B is made by Mistral AI and DeepSeek VL2 Small is made by DeepSeek. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to DeepSeek VL2 Small in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. DeepSeek VL2 Small scores DocVQA: 92.3%, ChartQA: 84.5%, OCRBench: 83.4%, TextVQA: 83.4%, MMBench: 80.3%.

What are the main differences between Codestral-22B and DeepSeek VL2 Small?

Key differences include LLM Stats Score (0.1 vs 1.4), multimodal support (no vs yes), licensing (MNPL-0.1 vs deepseek). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and DeepSeek VL2 Small?

Codestral-22B is developed by Mistral AI and DeepSeek VL2 Small is developed by DeepSeek.