The AI arena is free today

Open Superagent

Codestral-22B vs Gemini 4 Hydrogen

Gemini 4 Hydrogen leads the LLM Stats Score 48.8 to -0.5.

Mistral AI · Google · Updated for 2026

Which is better?

Gemini 4 Hydrogen leads the overall LLM Stats Score 48.8 to -0.5, ranking #29 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 4 Hydrogen

  • overall performance matters — it scores 48.8 and ranks #29 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you want the most recent training data — it shipped Nov 2026

At a glance

The differences that matter most.

Core performance indexes
-0.5
#377
48.8
#29
-0.7
#368
47.2
#30
2.3
#271
25.9
#94
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$1.50 / M
Output price
— / M
$7.50 / M
Context window
—
1,048,576

Individual benchmarks

7 reported for Codestral-22B · 5 for Gemini 4 Hydrogen

No common benchmarks found

Codestral-22B and Gemini 4 Hydrogendon'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 4 Hydrogen specifies input context (1,048,576 tokens). Only Gemini 4 Hydrogen specifies output context (1,048,576 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Google
Gemini 4 Hydrogen
Input1,048,576 tokens
Output1,048,576 tokens
Tue Nov 17 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemini 4 Hydrogen supports multimodal inputs, whereas Codestral-22B does not.

Gemini 4 Hydrogen can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Gemini 4 Hydrogen

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Gemini 4 Hydrogen 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 4 Hydrogen

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Gemini 4 Hydrogen was released on 2026-11-12.

Gemini 4 Hydrogen is 30 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.5 years ago

Gemini 4 Hydrogen

Nov 12, 2026

5 days ago

2.5yr 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 Gemini 4 Hydrogen side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Gemini 4 Hydrogen
Open in Playground

FAQ

Common questions about Codestral-22B vs Gemini 4 Hydrogen.

Which is better, Codestral-22B or Gemini 4 Hydrogen?

Gemini 4 Hydrogen leads the LLM Stats Score 48.8 to -0.5. Codestral-22B is made by Mistral AI and Gemini 4 Hydrogen 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 4 Hydrogen in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Gemini 4 Hydrogen scores Vending-Bench 2: 100.0%, OSWorld 2.1 (partial): 77.6%, Agents' Last Exam: 71.6%, Chartography (no tools): 66.6%, Terminal-Bench-Science 0.1: 51.4%.

What are the context window sizes for Codestral-22B and Gemini 4 Hydrogen?

Codestral-22B supports an unknown number of tokens and Gemini 4 Hydrogen 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 4 Hydrogen?

Key differences include LLM Stats Score (-0.5 vs 48.8), 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 4 Hydrogen?

Codestral-22B is developed by Mistral AI and Gemini 4 Hydrogen is developed by Google.