The AI arena is free today

Open Superagent

Claude 3.5 Haiku vs Codestral-22B

Claude 3.5 Haiku significantly outperforms across most benchmarks.

Anthropic · Mistral AI · Updated for 2026

Which is better?

Claude 3.5 Haiku outperforms in 1 benchmarks (HumanEval), while Codestral-22B is better at 0 benchmarks. Claude 3.5 Haiku significantly outperforms across most benchmarks.

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

Choose Claude 3.5 Haiku

  • you want the strongest raw capability — it leads on 1 of 1 shared benchmarks
  • you want the most recent training data — it shipped Oct 2024

Choose Codestral-22B

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

At a glance

The differences that matter most.

Claude 3.5 Haiku
Anthropic
Codestral-22B
Mistral AI
Benchmark wins
1 of 1
0 of 1
Input price
$0.80 / M
— / M
Output price
$4.00 / M
— / M
Context window
200,000
—
Released
Oct 2024
May 2024
License
Proprietary
MNPL-0.1

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

Claude 3.5 Haiku outperforms in 1 benchmarks (HumanEval), while Codestral-22B is better at 0 benchmarks.

Claude 3.5 Haiku significantly outperforms across most benchmarks.

Wed Aug 26 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Context Window

Maximum input and output token capacity

Only Claude 3.5 Haiku specifies input context (200,000 tokens). Only Claude 3.5 Haiku specifies output context (200,000 tokens).

Anthropic
Claude 3.5 Haiku
Input200,000 tokens
Output200,000 tokens
Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Wed Aug 26 2026 • llm-stats.com

License

Usage and distribution terms

Claude 3.5 Haiku is licensed under a proprietary license, while Codestral-22B uses MNPL-0.1.

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

Claude 3.5 Haiku

Proprietary

Closed source

Codestral-22B

MNPL-0.1

Open weights

Release Timeline

When each model was launched

Claude 3.5 Haiku was released on 2024-10-22, while Codestral-22B was released on 2024-05-29.

Claude 3.5 Haiku is 5 months newer than Codestral-22B.

Claude 3.5 Haiku

Oct 22, 2024

1.8 years ago

4mo newer
Codestral-22B

May 29, 2024

2.2 years ago

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 Claude 3.5 Haiku and Codestral-22B side-by-side, then vote on the output you prefer.

Claude 3.5 Haiku
✓ Preferred
Codestral-22B
Open in Playground

FAQ

Common questions about Claude 3.5 Haiku vs Codestral-22B.

Which is better, Claude 3.5 Haiku or Codestral-22B?

Claude 3.5 Haiku significantly outperforms across most benchmarks. Claude 3.5 Haiku is made by Anthropic and Codestral-22B is made by Mistral AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Claude 3.5 Haiku compare to Codestral-22B in benchmarks?

Claude 3.5 Haiku scores HumanEval: 88.1%, MGSM: 85.6%, DROP: 83.1%, MATH: 69.4%, MMLU-Pro: 65.0%. Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%.

What are the context window sizes for Claude 3.5 Haiku and Codestral-22B?

Claude 3.5 Haiku supports 200K tokens and Codestral-22B supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Claude 3.5 Haiku and Codestral-22B?

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

Who makes Claude 3.5 Haiku and Codestral-22B?

Claude 3.5 Haiku is developed by Anthropic and Codestral-22B is developed by Mistral AI.

Related comparisons