The AI arena is free today

Open Superagent

Codestral-22B vs Qwen3 Max

Comparing Codestral-22B and Qwen3 Max across benchmarks, pricing, and capabilities.

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

Which is better?

Codestral-22B and Qwen3 Max trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

Based on current benchmark, pricing, and model metadata for 2026.

Choose Codestral-22B

  • you need open weights you can self-host or fine-tune

Choose Qwen3 Max

  • you want the most recent training data — it shipped Dec 2025

At a glance

The differences that matter most.

Benchmark wins
Input price
— / M
$0.50 / M
Output price
— / M
$5.00 / M
Context window
256,000
Released
May 2024
Dec 2025
License
MNPL-0.1
Proprietary

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

Codestral-22B and Qwen3 Maxdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Arena Performance

Playground indexes and blind preference scores

Model Size

Parameter count comparison

977.8B diff

Qwen3 Max has 977.8B more parameters than Codestral-22B, making it 4404.5% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Alibaba Cloud / Qwen Team
Qwen3 Max
1.0Tparameters
22.2B
Codestral-22B
1000.0B
Qwen3 Max

Context Window

Maximum input and output token capacity

Only Qwen3 Max specifies input context (256,000 tokens). Only Qwen3 Max specifies output context (131,072 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Alibaba Cloud / Qwen Team
Qwen3 Max
Input256,000 tokens
Output131,072 tokens
Wed Aug 26 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Qwen3 Max uses a proprietary license.

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

Codestral-22B

MNPL-0.1

Open weights

Qwen3 Max

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Qwen3 Max was released on 2025-12-15.

Qwen3 Max is 19 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.2 years ago

Qwen3 Max

Dec 15, 2025

8 months ago

1.5yr 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 Qwen3 Max side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Qwen3 Max
Open in Playground

FAQ

Common questions about Codestral-22B vs Qwen3 Max.

Which is better, Codestral-22B or Qwen3 Max?

Codestral-22B (Mistral AI) and Qwen3 Max (Alibaba Cloud / Qwen Team) each have strengths in different areas. Compare their benchmark scores, pricing, context windows, and capabilities above to determine which fits your needs.

How does Codestral-22B compare to Qwen3 Max in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Qwen3 Max scores AIME 2025: 81.6%, t2-bench: 74.8%, SWE-Bench Verified: 69.6%, LiveCodeBench v6: 69.0%, SuperGPQA: 65.1%.

What are the context window sizes for Codestral-22B and Qwen3 Max?

Codestral-22B supports an unknown number of tokens and Qwen3 Max supports 256K 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 Qwen3 Max?

Key differences include licensing (MNPL-0.1 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Qwen3 Max?

Codestral-22B is developed by Mistral AI and Qwen3 Max is developed by Alibaba Cloud / Qwen Team.