The AI arena is free today

Open Superagent

Codestral-22B vs Gemini 1.5 Flash 8B

Codestral-22B and Gemini 1.5 Flash 8B are closely matched at 0.1 and -0.6 on the LLM Stats Score.

Mistral AI · Google · Updated for 2026

Which is better?

Codestral-22B and Gemini 1.5 Flash 8B are closely matched on the overall LLM Stats Score at 0.1 and -0.6.

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

Choose Codestral-22B

  • you want the most recent training data — it shipped May 2024
  • you need open weights you can self-host or fine-tune

Choose Gemini 1.5 Flash 8B

  • you want predictable pricing at $0.07/M input and $0.30/M output

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Gemini 1.5 Flash 8B
Google
Core performance indexes
LLM Stats Score
0.1
#314
-0.6
#319
Reasoning
-0.0
#307
-0.3
#308
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.07 / M
Output price
— / M
$0.30 / M
Context window
—
1,048,576

Individual benchmarks

7 reported for Codestral-22B · 13 for Gemini 1.5 Flash 8B

No common benchmarks found

Codestral-22B and Gemini 1.5 Flash 8Bdon'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

Model Size

Parameter count comparison

14.2B diff

Codestral-22B has 14.2B more parameters than Gemini 1.5 Flash 8B, making it 177.5% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Google
Gemini 1.5 Flash 8B
8.0Bparameters
22.2B
Codestral-22B
8.0B
Gemini 1.5 Flash 8B

Context Window

Maximum input and output token capacity

Only Gemini 1.5 Flash 8B specifies input context (1,048,576 tokens). Only Gemini 1.5 Flash 8B specifies output context (8,192 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Google
Gemini 1.5 Flash 8B
Input1,048,576 tokens
Output8,192 tokens
Sat Sep 05 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemini 1.5 Flash 8B supports multimodal inputs, whereas Codestral-22B does not.

Gemini 1.5 Flash 8B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Gemini 1.5 Flash 8B

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Gemini 1.5 Flash 8B 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 1.5 Flash 8B

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Gemini 1.5 Flash 8B was released on 2024-03-15.

Codestral-22B is 3 months newer than Gemini 1.5 Flash 8B.

Codestral-22B

May 29, 2024

2.3 years ago

2mo newer
Gemini 1.5 Flash 8B

Mar 15, 2024

2.5 years ago

Knowledge Cutoff

When training data ends

Gemini 1.5 Flash 8B has a documented knowledge cutoff of 2024-10-01, while Codestral-22B's cutoff date is not specified.

We can confirm Gemini 1.5 Flash 8B's training data extends to 2024-10-01, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

Gemini 1.5 Flash 8B

Oct 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and Gemini 1.5 Flash 8B side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Gemini 1.5 Flash 8B
Open in Playground

FAQ

Common questions about Codestral-22B vs Gemini 1.5 Flash 8B.

Which is better, Codestral-22B or Gemini 1.5 Flash 8B?

Codestral-22B and Gemini 1.5 Flash 8B are closely matched on the LLM Stats Score at 0.1 and -0.6. Codestral-22B is made by Mistral AI and Gemini 1.5 Flash 8B 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 1.5 Flash 8B in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Gemini 1.5 Flash 8B scores XSTest: 92.6%, FLEURS: 86.4%, Natural2Code: 75.5%, WMT23: 72.6%, Video-MME: 66.2%.

What are the context window sizes for Codestral-22B and Gemini 1.5 Flash 8B?

Codestral-22B supports an unknown number of tokens and Gemini 1.5 Flash 8B 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 1.5 Flash 8B?

Key differences include LLM Stats Score (0.1 vs -0.6), 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 1.5 Flash 8B?

Codestral-22B is developed by Mistral AI and Gemini 1.5 Flash 8B is developed by Google.

Related comparisons