Model Comparison

Codestral-22B vs Kimi K3Which is better in 2026?

Comparing Codestral-22B and Kimi K3 across benchmarks, pricing, and capabilities.

Verdict: Codestral-22B vs Kimi K3 — which is better?

Codestral-22B (by Mistral AI) and Kimi K3 (by Moonshot AI) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Choose Codestral-22B if…

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

Choose Kimi K3 if…

  • you want the most recent training data — it shipped Jul 2026

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

Codestral-22B and Kimi K3don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Arena Performance

Human preference votes

Model Size

Parameter count comparison

2777.8B diff

Kimi K3 has 2777.8B more parameters than Codestral-22B, making it 12512.6% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Moonshot AI
Kimi K3
2.8Tparameters
22.2B
Codestral-22B
2800.0B
Kimi K3

Context Window

Maximum input and output token capacity

Only Kimi K3 specifies input context (1,048,576 tokens). Only Kimi K3 specifies output context (1,048,576 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Moonshot AI
Kimi K3
Input1,048,576 tokens
Output1,048,576 tokens
Sat Jul 18 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Kimi K3 supports multimodal inputs, whereas Codestral-22B does not.

Kimi K3 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Kimi K3

Text
Images
Audio
Video

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Kimi K3 was released on 2026-07-16.

Kimi K3 is 26 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.1 years ago

Kimi K3

Jul 16, 2026

2 days ago

2.1yr 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→

Key Takeaways

Mistral AI

No standout differentiators in the data we have for this pair.

Moonshot AI
Larger context window (1,048,576 tokens)
Supports multimodal inputs

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Codestral-22B and Kimi K3 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Kimi K3
Open in Playground
AI Model Comparison Table
Feature
Mistral AI
Codestral-22B
Moonshot AI
Kimi K3

FAQ

Common questions about Codestral-22B vs Kimi K3.

Which is better, Codestral-22B or Kimi K3?

Codestral-22B (Mistral AI) and Kimi K3 (Moonshot AI) 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 Kimi K3 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Kimi K3 scores MathVision: 97.8%, DeepSearchQA: 95.0%, GPQA: 93.5%, CharXiv-R: 91.3%, BrowseComp: 91.2%.

What are the context window sizes for Codestral-22B and Kimi K3?

Codestral-22B supports an unknown number of tokens and Kimi K3 supports 1.0M 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 Kimi K3?

Key differences include multimodal support (no vs yes), licensing (MNPL-0.1 vs Unknown). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Kimi K3?

Codestral-22B is developed by Mistral AI and Kimi K3 is developed by Moonshot AI.

Related comparisons