The AI arena is free today

Open Superagent

Claude 3.7 Sonnet vs Codestral-22B

Claude 3.7 Sonnet leads the LLM Stats Score 24.0 to 0.1.

Anthropic · Mistral AI · Updated for 2026

Which is better?

Claude 3.7 Sonnet leads the overall LLM Stats Score 24.0 to 0.1, ranking #167 overall.

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

Choose Claude 3.7 Sonnet

  • overall performance matters — it scores 24.0 and ranks #167 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Feb 2025

Choose Codestral-22B

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

At a glance

The differences that matter most.

Claude 3.7 Sonnet
Anthropic
Codestral-22B
Mistral AI
Core performance indexes
LLM Stats Score
24.0
#167
0.1
#324
Reasoning
23.1
#163
-0.1
#316
Coding
13.7
#134
2.5
#223
Cost, coverage & limits
Benchmark wins
—
—
Input price
$3.00 / M
— / M
Output price
$15.00 / M
— / M
Context window
200,000
—

Individual benchmarks

11 reported for Claude 3.7 Sonnet · 7 for Codestral-22B

No common benchmarks found

Claude 3.7 Sonnet and Codestral-22Bdon'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

Context Window

Maximum input and output token capacity

Only Claude 3.7 Sonnet specifies input context (200,000 tokens). Only Claude 3.7 Sonnet specifies output context (128,000 tokens).

Anthropic
Claude 3.7 Sonnet
Input200,000 tokens
Output128,000 tokens
Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Wed Sep 09 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Claude 3.7 Sonnet supports multimodal inputs, whereas Codestral-22B does not.

Claude 3.7 Sonnet can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude 3.7 Sonnet

Text
Images
Audio
Video

Codestral-22B

Text
Images
Audio
Video

License

Usage and distribution terms

Claude 3.7 Sonnet 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 3.7 Sonnet

Proprietary

Closed source

Codestral-22B

MNPL-0.1

Open weights

Release Timeline

When each model was launched

Claude 3.7 Sonnet was released on 2025-02-24, while Codestral-22B was released on 2024-05-29.

Claude 3.7 Sonnet is 9 months newer than Codestral-22B.

Claude 3.7 Sonnet

Feb 24, 2025

1.5 years ago

9mo newer
Codestral-22B

May 29, 2024

2.3 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 3.7 Sonnet and Codestral-22B side-by-side, then vote on the output you prefer.

Claude 3.7 Sonnet
✓ Preferred
Codestral-22B
Open in Playground

FAQ

Common questions about Claude 3.7 Sonnet vs Codestral-22B.

Which is better, Claude 3.7 Sonnet or Codestral-22B?

Claude 3.7 Sonnet leads the LLM Stats Score 24.0 to 0.1. Claude 3.7 Sonnet is made by Anthropic and Codestral-22B is made by Mistral AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude 3.7 Sonnet compare to Codestral-22B in benchmarks?

Claude 3.7 Sonnet scores MATH-500: 96.2%, IFEval: 93.2%, MMMLU: 86.1%, GPQA: 84.8%, TAU-bench Retail: 81.2%. 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 3.7 Sonnet and Codestral-22B?

Claude 3.7 Sonnet 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 3.7 Sonnet and Codestral-22B?

Key differences include LLM Stats Score (24.0 vs 0.1), multimodal support (yes vs no), licensing (Proprietary vs MNPL-0.1). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3.7 Sonnet and Codestral-22B?

Claude 3.7 Sonnet is developed by Anthropic and Codestral-22B is developed by Mistral AI.

Related comparisons