The AI arena is free today

Open Superagent

Codestral-22B vs QwQ-32B-Preview

Codestral-22B and QwQ-32B-Preview are closely matched at 0.5 and 9.4 on the LLM Stats Score.

Mistral AI · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Codestral-22B and QwQ-32B-Preview are closely matched on the overall LLM Stats Score at 0.5 and 9.4.

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 QwQ-32B-Preview

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

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
QwQ-32B-Preview
Alibaba Cloud / Qwen Team
Core performance indexes
LLM Stats Score
0.5
#304
9.4
#251
Reasoning
0.4
#297
9.6
#244
Coding
2.6
#209
4.5
#192
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.15 / M
Output price
— / M
$0.20 / M
Context window
—
32,768

Individual benchmarks

7 reported for Codestral-22B · 4 for QwQ-32B-Preview

No common benchmarks found

Codestral-22B and QwQ-32B-Previewdon'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

10.3B diff

QwQ-32B-Preview has 10.3B more parameters than Codestral-22B, making it 46.4% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Alibaba Cloud / Qwen Team
QwQ-32B-Preview
32.5Bparameters
22.2B
Codestral-22B
32.5B
QwQ-32B-Preview

Context Window

Maximum input and output token capacity

Only QwQ-32B-Preview specifies input context (32,768 tokens). Only QwQ-32B-Preview specifies output context (32,768 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Alibaba Cloud / Qwen Team
QwQ-32B-Preview
Input32,768 tokens
Output32,768 tokens
Sat Aug 29 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while QwQ-32B-Preview uses Apache 2.0.

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

Codestral-22B

MNPL-0.1

Open weights

QwQ-32B-Preview

Apache 2.0

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while QwQ-32B-Preview was released on 2024-11-28.

QwQ-32B-Preview is 6 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.2 years ago

QwQ-32B-Preview

Nov 28, 2024

1.7 years ago

6mo newer

Knowledge Cutoff

When training data ends

QwQ-32B-Preview has a documented knowledge cutoff of 2024-11-28, while Codestral-22B's cutoff date is not specified.

We can confirm QwQ-32B-Preview's training data extends to 2024-11-28, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

QwQ-32B-Preview

Nov 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and QwQ-32B-Preview side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
QwQ-32B-Preview
Open in Playground

FAQ

Common questions about Codestral-22B vs QwQ-32B-Preview.

Which is better, Codestral-22B or QwQ-32B-Preview?

Codestral-22B and QwQ-32B-Preview are closely matched on the LLM Stats Score at 0.5 and 9.4. Codestral-22B is made by Mistral AI and QwQ-32B-Preview is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to QwQ-32B-Preview in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. QwQ-32B-Preview scores MATH-500: 90.6%, GPQA: 65.2%, AIME 2024: 50.0%, LiveCodeBench: 50.0%.

What are the context window sizes for Codestral-22B and QwQ-32B-Preview?

Codestral-22B supports an unknown number of tokens and QwQ-32B-Preview supports 33K 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 QwQ-32B-Preview?

Key differences include LLM Stats Score (0.5 vs 9.4), licensing (MNPL-0.1 vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and QwQ-32B-Preview?

Codestral-22B is developed by Mistral AI and QwQ-32B-Preview is developed by Alibaba Cloud / Qwen Team.

Related comparisons