The AI arena is free today

Open Superagent

Codestral-22B vs Gemini 2.5 Pro

Gemini 2.5 Pro leads the LLM Stats Score 27.8 to 0.0.

Mistral AI · Google · Updated for 2026

Which is better?

Gemini 2.5 Pro leads the overall LLM Stats Score 27.8 to 0.0, ranking #137 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 Gemini 2.5 Pro

  • overall performance matters — it scores 27.8 and ranks #137 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped May 2025

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Gemini 2.5 Pro
Google
Core performance indexes
LLM Stats Score
0.0
#325
27.8
#137
Reasoning
-0.1
#317
27.3
#137
Coding
2.5
#224
12.8
#140
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$1.25 / M
Output price
— / M
$10.00 / M
Context window
—
1,000,000

Individual benchmarks

7 reported for Codestral-22B · 16 for Gemini 2.5 Pro

No common benchmarks found

Codestral-22B and Gemini 2.5 Prodon'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 Gemini 2.5 Pro specifies input context (1,000,000 tokens). Only Gemini 2.5 Pro specifies output context (1,000,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Google
Gemini 2.5 Pro
Input1,000,000 tokens
Output1,000,000 tokens
Sun Sep 13 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemini 2.5 Pro supports multimodal inputs, whereas Codestral-22B does not.

Gemini 2.5 Pro can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Gemini 2.5 Pro

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Gemini 2.5 Pro 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

Gemini 2.5 Pro

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Gemini 2.5 Pro was released on 2025-05-20.

Gemini 2.5 Pro is 12 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Gemini 2.5 Pro

May 20, 2025

1.3 years ago

11mo newer

Knowledge Cutoff

When training data ends

Gemini 2.5 Pro has a documented knowledge cutoff of 2025-01-31, while Codestral-22B's cutoff date is not specified.

We can confirm Gemini 2.5 Pro's training data extends to 2025-01-31, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

Gemini 2.5 Pro

Jan 2025

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and Gemini 2.5 Pro side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Gemini 2.5 Pro
Open in Playground

FAQ

Common questions about Codestral-22B vs Gemini 2.5 Pro.

Which is better, Codestral-22B or Gemini 2.5 Pro?

Gemini 2.5 Pro leads the LLM Stats Score 27.8 to 0.0. Codestral-22B is made by Mistral AI and Gemini 2.5 Pro is made by Google. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to Gemini 2.5 Pro in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Gemini 2.5 Pro scores MRCR: 93.0%, AIME 2024: 92.0%, Global-MMLU-Lite: 88.6%, Video-MME: 84.8%, AIME 2025: 83.0%.

What are the context window sizes for Codestral-22B and Gemini 2.5 Pro?

Codestral-22B supports an unknown number of tokens and Gemini 2.5 Pro supports 1.0M 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 Gemini 2.5 Pro?

Key differences include LLM Stats Score (0.0 vs 27.8), 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 Gemini 2.5 Pro?

Codestral-22B is developed by Mistral AI and Gemini 2.5 Pro is developed by Google.

Related comparisons