The AI arena is free today

Open Superagent

Codestral-22B vs Qwen4-Max

Qwen4-Max leads the LLM Stats Score 50.2 to -0.5.

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

Which is better?

Qwen4-Max leads the overall LLM Stats Score 50.2 to -0.5, ranking #20 overall.

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

Choose Codestral-22B

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

Choose Qwen4-Max

  • overall performance matters — it scores 50.2 and ranks #20 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you want the most recent training data — it shipped Nov 2026

At a glance

The differences that matter most.

Core performance indexes
-0.5
#377
50.2
#20
-0.7
#368
48.8
#20
2.3
#271
36.5
#30
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$1.50 / M
Output price
— / M
$4.50 / M
Context window
—
983,616

Individual benchmarks

7 reported for Codestral-22B · 11 for Qwen4-Max

No common benchmarks found

Codestral-22B and Qwen4-Maxdon'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

2377.8B diff

Qwen4-Max has 2377.8B more parameters than Codestral-22B, making it 10710.8% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Alibaba Cloud / Qwen Team
Qwen4-Max
2.4Tparameters
22.2B
Codestral-22B
2400.0B
Qwen4-Max

Context Window

Maximum input and output token capacity

Only Qwen4-Max specifies input context (983,616 tokens). Only Qwen4-Max specifies output context (262,144 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Alibaba Cloud / Qwen Team
Qwen4-Max
Input983,616 tokens
Output262,144 tokens
Tue Nov 17 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Qwen4-Max supports multimodal inputs, whereas Codestral-22B does not.

Qwen4-Max can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Qwen4-Max

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Qwen4-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

Qwen4-Max

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Qwen4-Max was released on 2026-11-16.

Qwen4-Max is 30 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.5 years ago

Qwen4-Max

Nov 16, 2026

1 days ago

2.5yr 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?

Judge for yourself.

Run your own prompts against Codestral-22B and Qwen4-Max side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Qwen4-Max
Open in Playground

FAQ

Common questions about Codestral-22B vs Qwen4-Max.

Which is better, Codestral-22B or Qwen4-Max?

Qwen4-Max leads the LLM Stats Score 50.2 to -0.5. Codestral-22B is made by Mistral AI and Qwen4-Max 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 Qwen4-Max in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Qwen4-Max scores WebDev Arena: 87.5%, BioMysteryBench: 85.0%, DeepSWE 1.1: 75.7%, APEX-Agents: 72.1%, Job Bench: 68.5%.

What are the context window sizes for Codestral-22B and Qwen4-Max?

Codestral-22B supports an unknown number of tokens and Qwen4-Max supports 984K 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 Qwen4-Max?

Key differences include LLM Stats Score (-0.5 vs 50.2), multimodal support (no vs yes), licensing (MNPL-0.1 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Qwen4-Max?

Codestral-22B is developed by Mistral AI and Qwen4-Max is developed by Alibaba Cloud / Qwen Team.