The AI arena is free today

Open Superagent

Codestral-22B vs Gemma 2 27B

Codestral-22B and Gemma 2 27B are closely matched at 0.5 and -0.2 on the LLM Stats Score.

Mistral AI · Google · Updated for 2026

Which is better?

Codestral-22B and Gemma 2 27B are closely matched on the overall LLM Stats Score at 0.5 and -0.2.

In the 2 individual benchmarks reported for both models, Codestral-22B wins 2; 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 value its reported benchmark strengths — it wins 2 of 2 exact shared results

Choose Gemma 2 27B

  • you want the most recent training data — it shipped Jun 2024

At a glance

The differences that matter most.

Core performance indexes
0.5
#304
-0.2
#308
0.4
#297
-0.6
#305
2.6
#209
-7.9
#244
Cost, coverage & limits
Benchmark wins
2 of 2
0 of 2
Input price
— / M
— / M
Output price
— / M
— / M
Context window

Individual benchmarks

7 reported for Codestral-22B · 16 for Gemma 2 27B

2 shared

Codestral-22B outperforms in 2 benchmarks (HumanEval, MBPP), while Gemma 2 27B is better at 0 benchmarks.

Codestral-22B significantly outperforms across most benchmarks.

Sun Aug 30 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

5.0B diff

Gemma 2 27B has 5.0B more parameters than Codestral-22B, making it 22.5% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Google
Gemma 2 27B
27.2Bparameters
22.2B
Codestral-22B
27.2B
Gemma 2 27B

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Gemma 2 27B uses Gemma.

License differences may affect how you can use these models in commercial or open-source projects.

Codestral-22B

MNPL-0.1

Open weights

Gemma 2 27B

Gemma

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Gemma 2 27B was released on 2024-06-27.

Gemma 2 27B is 1 month newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Gemma 2 27B

Jun 27, 2024

2.2 years ago

4w 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 Gemma 2 27B side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Gemma 2 27B
Open in Playground

FAQ

Common questions about Codestral-22B vs Gemma 2 27B.

Which is better, Codestral-22B or Gemma 2 27B?

Codestral-22B and Gemma 2 27B are closely matched on the LLM Stats Score at 0.5 and -0.2. Codestral-22B is made by Mistral AI and Gemma 2 27B 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 Gemma 2 27B in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Gemma 2 27B scores ARC-E: 88.6%, HellaSwag: 86.4%, BoolQ: 84.8%, TriviaQA: 83.7%, Winogrande: 83.7%.

What are the main differences between Codestral-22B and Gemma 2 27B?

Key differences include LLM Stats Score (0.5 vs -0.2), licensing (MNPL-0.1 vs Gemma). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Gemma 2 27B?

Codestral-22B is developed by Mistral AI and Gemma 2 27B is developed by Google.