The AI arena is free today

Open Superagent

Codestral-22B vs o3-mini

o3-mini leads the LLM Stats Score 21.5 to 0.1.

Mistral AI · OpenAI · Updated for 2026

Which is better?

o3-mini leads the overall LLM Stats Score 21.5 to 0.1, ranking #178 overall.

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

Choose Codestral-22B

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

Choose o3-mini

  • overall performance matters — it scores 21.5 and ranks #178 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Jan 2025

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
o3-mini
OpenAI
Core performance indexes
LLM Stats Score
0.1
#314
21.5
#178
Reasoning
-0.0
#307
20.7
#176
Coding
2.5
#218
5.3
#194
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$1.10 / M
Output price
— / M
$4.40 / M
Context window
—
200,000

Individual benchmarks

7 reported for Codestral-22B · 25 for o3-mini

No common benchmarks found

Codestral-22B and o3-minidon'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 o3-mini specifies input context (200,000 tokens). Only o3-mini specifies output context (100,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
OpenAI
o3-mini
Input200,000 tokens
Output100,000 tokens
Sun Sep 06 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while o3-mini uses a proprietary license.

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

Codestral-22B

MNPL-0.1

Open weights

o3-mini

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while o3-mini was released on 2025-01-30.

o3-mini is 8 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

o3-mini

Jan 30, 2025

1.6 years ago

8mo newer

Knowledge Cutoff

When training data ends

o3-mini has a documented knowledge cutoff of 2023-09-30, while Codestral-22B's cutoff date is not specified.

We can confirm o3-mini's training data extends to 2023-09-30, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

o3-mini

Sep 2023

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and o3-mini side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
o3-mini
Open in Playground

FAQ

Common questions about Codestral-22B vs o3-mini.

Which is better, Codestral-22B or o3-mini?

o3-mini leads the LLM Stats Score 21.5 to 0.1. Codestral-22B is made by Mistral AI and o3-mini is made by OpenAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to o3-mini in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. o3-mini scores COLLIE: 98.7%, MATH: 97.9%, IFEval: 93.9%, MGSM: 92.0%, AIME 2024: 87.3%.

What are the context window sizes for Codestral-22B and o3-mini?

Codestral-22B supports an unknown number of tokens and o3-mini supports 200K 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 o3-mini?

Key differences include LLM Stats Score (0.1 vs 21.5), licensing (MNPL-0.1 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and o3-mini?

Codestral-22B is developed by Mistral AI and o3-mini is developed by OpenAI.

Related comparisons