The AI arena is free today

Open Superagent

Codestral-22B vs DeepSeek R1 Distill Qwen 32B

DeepSeek R1 Distill Qwen 32B leads the LLM Stats Score 13.2 to 0.1.

Mistral AI · DeepSeek · Updated for 2026

Which is better?

DeepSeek R1 Distill Qwen 32B leads the overall LLM Stats Score 13.2 to 0.1, ranking #236 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 R1 Distill Qwen 32B

  • overall performance matters — it scores 13.2 and ranks #236 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Jan 2025

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
DeepSeek R1 Distill Qwen 32B
DeepSeek
Core performance indexes
LLM Stats Score
0.1
#314
13.2
#236
Reasoning
-0.0
#307
13.4
#227
Coding
2.5
#218
8.3
#175
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.12 / M
Output price
— / M
$0.18 / M
Context window
—
128,000

Individual benchmarks

7 reported for Codestral-22B · 4 for DeepSeek R1 Distill Qwen 32B

No common benchmarks found

Codestral-22B and DeepSeek R1 Distill Qwen 32Bdon'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

10.6B diff

DeepSeek R1 Distill Qwen 32B has 10.6B more parameters than Codestral-22B, making it 47.7% larger.

Mistral AI
Codestral-22B
22.2Bparameters
DeepSeek
DeepSeek R1 Distill Qwen 32B
32.8Bparameters
22.2B
Codestral-22B
32.8B
DeepSeek R1 Distill Qwen 32B

Context Window

Maximum input and output token capacity

Only DeepSeek R1 Distill Qwen 32B specifies input context (128,000 tokens). Only DeepSeek R1 Distill Qwen 32B specifies output context (128,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
DeepSeek
DeepSeek R1 Distill Qwen 32B
Input128,000 tokens
Output128,000 tokens
Sat Sep 05 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while DeepSeek R1 Distill Qwen 32B 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

DeepSeek R1 Distill Qwen 32B

MIT

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while DeepSeek R1 Distill Qwen 32B was released on 2025-01-20.

DeepSeek R1 Distill Qwen 32B is 8 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

DeepSeek R1 Distill Qwen 32B

Jan 20, 2025

1.6 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 R1 Distill Qwen 32B side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
DeepSeek R1 Distill Qwen 32B
Open in Playground

FAQ

Common questions about Codestral-22B vs DeepSeek R1 Distill Qwen 32B.

Which is better, Codestral-22B or DeepSeek R1 Distill Qwen 32B?

DeepSeek R1 Distill Qwen 32B leads the LLM Stats Score 13.2 to 0.1. Codestral-22B is made by Mistral AI and DeepSeek R1 Distill Qwen 32B 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 R1 Distill Qwen 32B in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. DeepSeek R1 Distill Qwen 32B scores MATH-500: 94.3%, AIME 2024: 83.3%, GPQA: 62.1%, LiveCodeBench: 57.2%.

What are the context window sizes for Codestral-22B and DeepSeek R1 Distill Qwen 32B?

Codestral-22B supports an unknown number of tokens and DeepSeek R1 Distill Qwen 32B 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 DeepSeek R1 Distill Qwen 32B?

Key differences include LLM Stats Score (0.1 vs 13.2), licensing (MNPL-0.1 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and DeepSeek R1 Distill Qwen 32B?

Codestral-22B is developed by Mistral AI and DeepSeek R1 Distill Qwen 32B is developed by DeepSeek.

Related comparisons