The AI arena is free today

Open Superagent

Codestral-22B vs DeepSeek VL2 Tiny

Codestral-22B leads the LLM Stats Score 0.0 to -4.7.

Mistral AI · DeepSeek · Updated for 2026

Which is better?

Codestral-22B leads the overall LLM Stats Score 0.0 to -4.7, ranking #342 overall.

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

Choose Codestral-22B

  • overall performance matters — it scores 0.0 and ranks #342 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes

Choose DeepSeek VL2 Tiny

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

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
DeepSeek VL2 Tiny
DeepSeek
Core performance indexes
LLM Stats Score
0.0
#342
-4.7
#367
Reasoning
-0.1
#334
-12.7
#378
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 Tiny

No common benchmarks found

Codestral-22B and DeepSeek VL2 Tinydon'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

19.2B diff

Codestral-22B has 19.2B more parameters than DeepSeek VL2 Tiny, making it 640.0% larger.

Mistral AI
Codestral-22B
22.2Bparameters
DeepSeek
DeepSeek VL2 Tiny
3.0Bparameters
22.2B
Codestral-22B
3.0B
DeepSeek VL2 Tiny

Input capabilities

Documented input modalities across available providers

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

DeepSeek VL2 Tiny 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 Tiny

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while DeepSeek VL2 Tiny 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 Tiny

deepseek

Open weights

Release Timeline

When each model was launched

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

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

Codestral-22B

May 29, 2024

2.4 years ago

DeepSeek VL2 Tiny

Dec 13, 2024

1.8 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?

Judge for yourself.

Run your own prompts against Codestral-22B and DeepSeek VL2 Tiny side-by-side, then vote on the output you prefer.

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

FAQ

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

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

Codestral-22B leads the LLM Stats Score 0.0 to -4.7. Codestral-22B is made by Mistral AI and DeepSeek VL2 Tiny 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 Tiny in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. DeepSeek VL2 Tiny scores DocVQA: 88.9%, ChartQA: 81.0%, OCRBench: 80.9%, TextVQA: 80.7%, AI2D: 71.6%.

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

Key differences include LLM Stats Score (0.0 vs -4.7), 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 Tiny?

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

Related comparisons