Gemma 4 26B

Open Weights

26B

Parameters

256K

Context

Benchmarks

About Gemma 4 26B

Gemma 4 26B is an AI model developed by Google DeepMind, released in 2026, made available as an open-weights model with 26B params. Gemma 4 26B is a Mixture-of-Experts model in Google's Gemma 4 family, ranking #6 on the Arena AI text leaderboard among .

On this page you'll find Gemma 4 26B's full specifications, including a context window of 256K tokens, 3 benchmark results. Review provider pricing and benchmark scores below, or compare Gemma 4 26B head-to-head with other AI models.

→ More models by Google DeepMind → AI benchmarks leaderboard

Links

Announcement ↗ Paper ↗ Hugging Face ↗

Community

Would you run Gemma 4 26B again?

No votes yet — be the first.

Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Gemma 4 26B benchmark scores▶

Compare on the benchmark table →

Benchmark	Category	Score	Variant
HumanEval	code	79.8%	pass@1
MMLU-Pro	general	70.1%
GPQA Diamond	reasoning	55.9%

More models like Gemma 4 26B

DiffusionGemma 26B-A4B

Google DeepMind · 26B

Gemini 3.5 Live Translate

Google DeepMind

Magenta RealTime 2

Google DeepMind · 2.4B

Gemma 4 12B

Google DeepMind · 12B

Frequently asked questions

What is Gemma 4 26B? ▶

Gemma 4 26B is a Mixture-of-Experts model in Google's Gemma 4 family, ranking #6 on the Arena AI text leaderboard among It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Gemma 4 26B? ▶

Gemma 4 26B was developed by Google DeepMind and released in 2026.

Is Gemma 4 26B open source or proprietary? ▶

Gemma 4 26B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

What is Gemma 4 26B's context window? ▶

Gemma 4 26B supports a context window of 256K tokens, and has 26B params.

How much does Gemma 4 26B cost? ▶

Pricing for Gemma 4 26B depends on the provider. See the providers table on this page for the latest API rates.

How does Gemma 4 26B perform on benchmarks? ▶

Gemma 4 26B is benchmarked across 3 evaluations on GenAIList, including HumanEval (79.8%). See the full benchmark table below and compare it with other models.