The AI arena is free today

Open Superagent

Codestral-22B vs DeepSeek-V3

DeepSeek-V3 leads the LLM Stats Score 15.7 to 0.1.

Mistral AI · DeepSeek · Updated for 2026

Which is better?

DeepSeek-V3 leads the overall LLM Stats Score 15.7 to 0.1, ranking #216 overall.

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-V3

  • overall performance matters — it scores 15.7 and ranks #216 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Dec 2024

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
DeepSeek-V3
DeepSeek
Core performance indexes
LLM Stats Score
0.1
#314
15.7
#216
Reasoning
-0.0
#307
14.8
#217
Coding
2.5
#218
6.5
#184
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.27 / M
Output price
— / M
$1.10 / M
Context window
—
131,072

Individual benchmarks

7 reported for Codestral-22B · 20 for DeepSeek-V3

No common benchmarks found

Codestral-22B and DeepSeek-V3don'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

648.8B diff

DeepSeek-V3 has 648.8B more parameters than Codestral-22B, making it 2922.5% larger.

Mistral AI
Codestral-22B
22.2Bparameters
DeepSeek
DeepSeek-V3
671.0Bparameters
22.2B
Codestral-22B
671.0B
DeepSeek-V3

Context Window

Maximum input and output token capacity

Only DeepSeek-V3 specifies input context (131,072 tokens). Only DeepSeek-V3 specifies output context (131,072 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
DeepSeek
DeepSeek-V3
Input131,072 tokens
Output131,072 tokens
Fri Sep 04 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while DeepSeek-V3 uses MIT + Model License (Commercial use allowed).

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

Codestral-22B

MNPL-0.1

Open weights

DeepSeek-V3

MIT + Model License (Commercial use allowed)

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while DeepSeek-V3 was released on 2024-12-25.

DeepSeek-V3 is 7 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

DeepSeek-V3

Dec 25, 2024

1.7 years ago

7mo 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-V3 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
DeepSeek-V3
Open in Playground

FAQ

Common questions about Codestral-22B vs DeepSeek-V3.

Which is better, Codestral-22B or DeepSeek-V3?

DeepSeek-V3 leads the LLM Stats Score 15.7 to 0.1. Codestral-22B is made by Mistral AI and DeepSeek-V3 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-V3 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. DeepSeek-V3 scores DROP: 91.6%, CLUEWSC: 90.9%, MATH-500: 90.2%, MMLU-Redux: 89.1%, MMLU: 88.5%.

What are the context window sizes for Codestral-22B and DeepSeek-V3?

Codestral-22B supports an unknown number of tokens and DeepSeek-V3 supports 131K 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 DeepSeek-V3?

Key differences include LLM Stats Score (0.1 vs 15.7), licensing (MNPL-0.1 vs MIT + Model License (Commercial use allowed)). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and DeepSeek-V3?

Codestral-22B is developed by Mistral AI and DeepSeek-V3 is developed by DeepSeek.

Related comparisons