LLM2025-04-01

Gemma 3 27B

Enhanced reasoning and native multimodal.

Overview

Major leap over Gemma 2.

●

Reasoning jump

●

Native vision

●

Open weights

MMLU Score

85%

HumanEval (Coding)

88%

GPQA Diamond

70%

MATH Benchmark

82%

Learn to Master This Model

Take our free structured Gemma course — from basics to advanced techniques.

Context128,000 tokens

Params27B

LicenseGemma 3 Terms

ArchTransformer

$0 / 1M input tokens

Output: $0 / 1M tokens

✓ Free tier available

Google's AI research lab — creators of Gemini, the highest context-window multimodal LLM.

Prompt Library

Browse Coding Prompts →

Previous Version