The AI arena is free today

Open Superagent

Codestral-22B vs Kimi K2 Base

Comparing Codestral-22B and Kimi K2 Base across benchmarks, pricing, and capabilities.

Mistral AI · Moonshot AI · Updated for 2026

Which is better?

Codestral-22B and Kimi K2 Base 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 are already invested in the Mistral AI ecosystem

Choose Kimi K2 Base

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

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Kimi K2 Base
Moonshot AI
Benchmark wins
—
—
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—
Released
May 2024
Jul 2025
License
MNPL-0.1
MIT

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

Codestral-22B and Kimi K2 Basedon'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

Kimi K2 Base has 977.8B more parameters than Codestral-22B, making it 4404.5% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Moonshot AI
Kimi K2 Base
1.0Tparameters
22.2B
Codestral-22B
1000.0B
Kimi K2 Base

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Kimi K2 Base 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

Kimi K2 Base

MIT

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Kimi K2 Base was released on 2025-07-11.

Kimi K2 Base is 14 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.2 years ago

Kimi K2 Base

Jul 11, 2025

1.1 years ago

1.1yr 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→

Judge for yourself.

Run your own prompts against Codestral-22B and Kimi K2 Base side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Kimi K2 Base
Open in Playground

FAQ

Common questions about Codestral-22B vs Kimi K2 Base.

Which is better, Codestral-22B or Kimi K2 Base?

Codestral-22B (Mistral AI) and Kimi K2 Base (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 K2 Base in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Kimi K2 Base scores C-Eval: 92.5%, GSM8k: 92.1%, MMLU-redux-2.0: 90.2%, MMLU: 87.8%, TriviaQA: 85.1%.

What are the main differences between Codestral-22B and Kimi K2 Base?

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

Who makes Codestral-22B and Kimi K2 Base?

Codestral-22B is developed by Mistral AI and Kimi K2 Base is developed by Moonshot AI.

Related comparisons