The AI arena is free today

Open Superagent

Codestral-22B vs Devstral Small 1.1

Codestral-22B and Devstral Small 1.1 are closely matched at 0.1 and 9.6 on the LLM Stats Score.

Mistral AI · Mistral AI · Updated for 2026

Which is better?

Codestral-22B and Devstral Small 1.1 are closely matched on the overall LLM Stats Score at 0.1 and 9.6.

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

Choose Codestral-22B

  • you are already invested in the Mistral AI ecosystem

Choose Devstral Small 1.1

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

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Devstral Small 1.1
Mistral AI
Core performance indexes
LLM Stats Score
0.1
#314
9.6
#258
Reasoning
-0.0
#307
9.5
#250
Coding
2.5
#218
1.1
#227
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.10 / M
Output price
— / M
$0.30 / M
Context window
—
128,000

Individual benchmarks

7 reported for Codestral-22B · 1 for Devstral Small 1.1

No common benchmarks found

Codestral-22B and Devstral Small 1.1don'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

1.8B diff

Devstral Small 1.1 has 1.8B more parameters than Codestral-22B, making it 8.1% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Mistral AI
Devstral Small 1.1
24.0Bparameters
22.2B
Codestral-22B
24.0B
Devstral Small 1.1

Context Window

Maximum input and output token capacity

Only Devstral Small 1.1 specifies input context (128,000 tokens). Only Devstral Small 1.1 specifies output context (128,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Mistral AI
Devstral Small 1.1
Input128,000 tokens
Output128,000 tokens
Sun Sep 06 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Devstral Small 1.1 uses Apache 2.0.

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

Codestral-22B

MNPL-0.1

Open weights

Devstral Small 1.1

Apache 2.0

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Devstral Small 1.1 was released on 2025-07-11.

Devstral Small 1.1 is 14 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Devstral Small 1.1

Jul 11, 2025

1.2 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 Devstral Small 1.1 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Devstral Small 1.1
Open in Playground

FAQ

Common questions about Codestral-22B vs Devstral Small 1.1.

Which is better, Codestral-22B or Devstral Small 1.1?

Codestral-22B and Devstral Small 1.1 are closely matched on the LLM Stats Score at 0.1 and 9.6. Codestral-22B is made by Mistral AI and Devstral Small 1.1 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 Codestral-22B compare to Devstral Small 1.1 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Devstral Small 1.1 scores SWE-Bench Verified: 53.6%.

What are the context window sizes for Codestral-22B and Devstral Small 1.1?

Codestral-22B supports an unknown number of tokens and Devstral Small 1.1 supports 128K 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 Devstral Small 1.1?

Key differences include LLM Stats Score (0.1 vs 9.6), licensing (MNPL-0.1 vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Related comparisons