Enterprise DNA
L Models Best vision

Gemma 3 12B

by Google

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 improv

Visit Google Submit your build →
G3

Models

Gemma 3 12B

Added 10 July 2026

#google

Overview

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,...

How to use / API access

Call via OpenRouter with model id `google/gemma-3-12b-it`.

  • openrouter · google/gemma-3-12b-it Docs

OpenRouter id: google/gemma-3-12b-it

Benchmarks

  • Intelligence Index (artificial-analysis) : 5.5 index
  • Coding Index (artificial-analysis) : 5.8 index
  • Agentic Index (artificial-analysis) : 0.3 index

Notes

Gemma 3 12B is listed in the EDNA Models directory from the OpenRouter catalogue.

← Back to Models Submit your own entry →