The AI arena is free today

Open Superagent

Codestral-22B vs GPT-4.5

GPT-4.5 leads the LLM Stats Score 20.2 to 0.0.

Mistral AI · OpenAI · Updated for 2026

Which is better?

GPT-4.5 leads the overall LLM Stats Score 20.2 to 0.0, ranking #202 overall.

In the 1 individual benchmarks reported for both models, GPT-4.5 wins 1; this is a narrower head-to-head signal than the composite indexes.

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 GPT-4.5

  • overall performance matters — it scores 20.2 and ranks #202 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you want the most recent training data — it shipped Feb 2025

At a glance

The differences that matter most.

Core performance indexes
0.0
#332
20.2
#202
-0.1
#324
20.4
#193
2.5
#231
5.8
#201
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
— / M
$75.00 / M
Output price
— / M
$150.00 / M
Context window
—
128,000

Individual benchmarks

7 reported for Codestral-22B · 26 for GPT-4.5

1 shared

Codestral-22B outperforms in 0 benchmarks, while GPT-4.5 is better at 1 benchmark (HumanEval).

GPT-4.5 significantly outperforms across most benchmarks.

Sun Sep 27 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only GPT-4.5 specifies input context (128,000 tokens). Only GPT-4.5 specifies output context (4,096 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
OpenAI
GPT-4.5
Input128,000 tokens
Output4,096 tokens
Sun Sep 27 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-4.5 supports multimodal inputs, whereas Codestral-22B does not.

GPT-4.5 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

GPT-4.5

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while GPT-4.5 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

GPT-4.5

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while GPT-4.5 was released on 2025-02-27.

GPT-4.5 is 9 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

GPT-4.5

Feb 27, 2025

1.6 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?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and GPT-4.5 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
GPT-4.5
Open in Playground

FAQ

Common questions about Codestral-22B vs GPT-4.5.

Which is better, Codestral-22B or GPT-4.5?

GPT-4.5 leads the LLM Stats Score 20.2 to 0.0. Codestral-22B is made by Mistral AI and GPT-4.5 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 GPT-4.5 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. GPT-4.5 scores GSM8k: 97.0%, MMLU: 90.8%, CharXiv-D: 90.0%, IFEval: 88.2%, HumanEval: 88.0%.

What are the context window sizes for Codestral-22B and GPT-4.5?

Codestral-22B supports an unknown number of tokens and GPT-4.5 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 GPT-4.5?

Key differences include LLM Stats Score (0.0 vs 20.2), multimodal support (no vs yes), licensing (MNPL-0.1 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and GPT-4.5?

Codestral-22B is developed by Mistral AI and GPT-4.5 is developed by OpenAI.