Google Models
Google logo

Gemma 3 12B

12B

byGoogle

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Input Price$0.09/1M tokens
Output Price$0.29/1M tokens
Intelligence8.8
Coding6.3

Specifications

Technical details and pricing.

ProviderGoogle
Context Window131,072 tokens
Release DateMar 12, 2025
ModalitiesText, Image β†’ Text
CapabilitiesVision

Benchmarks

12 benchmark scores from Artificial Analysis.

GPQA34.9%
MMLU Pro59.5%
HLE4.8%
LiveCodeBench13.7%
MATH 50085.3%
AIME 202518.3%
AIME22.0%
SciCode17.4%
LCR6.7%
IFBench36.7%
Tau210.8%
TerminalBench Hard0.8%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is Gemma 3 12B good for?

Use Gemma 3 12B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Gemma 3 12B cost?

Pricing is based on usage. Current rates are $0.09/1M tokens for input and $0.29/1M tokens for output.

Can I try Gemma 3 12B for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Gemma 3 12B support images or audio?

Gemma 3 12B can understand images.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.