The AI arena is free today

Open Superagent

Codestral-22B vs Mistral Small 3.1 24B Instruct

Codestral-22B and Mistral Small 3.1 24B Instruct are closely matched at 0.0 and 4.2 on the LLM Stats Score.

Mistral AI · Mistral AI · Updated for 2026

Which is better?

Codestral-22B and Mistral Small 3.1 24B Instruct are closely matched on the overall LLM Stats Score at 0.0 and 4.2.

The models split the 2 individual benchmarks reported for both models evenly.

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 Mistral Small 3.1 24B Instruct

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

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Mistral Small 3.1 24B Instruct
Mistral AI
Core performance indexes
LLM Stats Score
0.0
#334
4.2
#311
Reasoning
-0.1
#326
4.2
#304
Coding
2.5
#233
9.7
#178
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—

Individual benchmarks

7 reported for Codestral-22B · 9 for Mistral Small 3.1 24B Instruct

2 shared

Codestral-22B outperforms in 1 benchmarks (MBPP), while Mistral Small 3.1 24B Instruct is better at 1 benchmark (HumanEval).

Both models are evenly matched across the benchmarks.

Fri Oct 02 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

1.8B diff

Mistral Small 3.1 24B Instruct has 1.8B more parameters than Codestral-22B, making it 8.1% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Mistral AI
Mistral Small 3.1 24B Instruct
24.0Bparameters
22.2B
Codestral-22B
24.0B
Mistral Small 3.1 24B Instruct

Input capabilities

Documented input modalities across available providers

Mistral Small 3.1 24B Instruct supports multimodal inputs, whereas Codestral-22B does not.

Mistral Small 3.1 24B Instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Mistral Small 3.1 24B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Mistral Small 3.1 24B Instruct 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

Mistral Small 3.1 24B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Mistral Small 3.1 24B Instruct was released on 2025-03-17.

Mistral Small 3.1 24B Instruct is 10 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Mistral Small 3.1 24B Instruct

Mar 17, 2025

1.5 years ago

9mo 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?

Judge for yourself.

Run your own prompts against Codestral-22B and Mistral Small 3.1 24B Instruct side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Mistral Small 3.1 24B Instruct
Open in Playground

FAQ

Common questions about Codestral-22B vs Mistral Small 3.1 24B Instruct.

Which is better, Codestral-22B or Mistral Small 3.1 24B Instruct?

Codestral-22B and Mistral Small 3.1 24B Instruct are closely matched on the LLM Stats Score at 0.0 and 4.2. Codestral-22B is made by Mistral AI and Mistral Small 3.1 24B Instruct 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 Mistral Small 3.1 24B Instruct in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Mistral Small 3.1 24B Instruct scores HumanEval: 88.4%, MMLU: 80.6%, TriviaQA: 80.5%, MBPP: 74.7%, MATH: 69.3%.

What are the main differences between Codestral-22B and Mistral Small 3.1 24B Instruct?

Key differences include LLM Stats Score (0.0 vs 4.2), multimodal support (no vs yes), licensing (MNPL-0.1 vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Related comparisons