The AI arena is free today

Open Superagent

Codestral-22B vs Gemini 2.0 Flash-Lite

Codestral-22B and Gemini 2.0 Flash-Lite are closely matched at 0.2 and 12.5 on the LLM Stats Score.

Mistral AI · Google · Updated for 2026

Which is better?

Codestral-22B and Gemini 2.0 Flash-Lite are closely matched on the overall LLM Stats Score at 0.2 and 12.5.

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 2.0 Flash-Lite

  • you want the most recent training data — it shipped Feb 2025

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Gemini 2.0 Flash-Lite
Google
Core performance indexes
LLM Stats Score
0.2
#309
12.5
#235
Reasoning
0.1
#303
12.7
#228
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 2.0 Flash-Lite

No common benchmarks found

Codestral-22B and Gemini 2.0 Flash-Litedon'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 2.0 Flash-Lite specifies input context (1,048,576 tokens). Only Gemini 2.0 Flash-Lite specifies output context (8,192 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Google
Gemini 2.0 Flash-Lite
Input1,048,576 tokens
Output8,192 tokens
Tue Sep 01 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemini 2.0 Flash-Lite supports multimodal inputs, whereas Codestral-22B does not.

Gemini 2.0 Flash-Lite can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Gemini 2.0 Flash-Lite

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Gemini 2.0 Flash-Lite 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 2.0 Flash-Lite

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Gemini 2.0 Flash-Lite was released on 2025-02-05.

Gemini 2.0 Flash-Lite is 8 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Gemini 2.0 Flash-Lite

Feb 5, 2025

1.6 years ago

8mo newer

Knowledge Cutoff

When training data ends

Gemini 2.0 Flash-Lite has a documented knowledge cutoff of 2024-06-01, while Codestral-22B's cutoff date is not specified.

We can confirm Gemini 2.0 Flash-Lite's training data extends to 2024-06-01, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

Gemini 2.0 Flash-Lite

Jun 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and Gemini 2.0 Flash-Lite side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Gemini 2.0 Flash-Lite
Open in Playground

FAQ

Common questions about Codestral-22B vs Gemini 2.0 Flash-Lite.

Which is better, Codestral-22B or Gemini 2.0 Flash-Lite?

Codestral-22B and Gemini 2.0 Flash-Lite are closely matched on the LLM Stats Score at 0.2 and 12.5. Codestral-22B is made by Mistral AI and Gemini 2.0 Flash-Lite 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 2.0 Flash-Lite in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Gemini 2.0 Flash-Lite scores MATH: 86.8%, FACTS Grounding: 83.6%, Global-MMLU-Lite: 78.2%, MMLU-Pro: 71.6%, MMMU: 68.0%.

What are the context window sizes for Codestral-22B and Gemini 2.0 Flash-Lite?

Codestral-22B supports an unknown number of tokens and Gemini 2.0 Flash-Lite 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 2.0 Flash-Lite?

Key differences include LLM Stats Score (0.2 vs 12.5), 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 2.0 Flash-Lite?

Codestral-22B is developed by Mistral AI and Gemini 2.0 Flash-Lite is developed by Google.

Related comparisons