WiseOne AI logo
WiseOneAI
Provider logo

Gemma 4 12B Instruct

gemma-4-12b-it
Back
Provider logo

Gemma 4 12B Instruct

gemma-4-12b-it
Back

Google's Gemma 4 12B Instruct is an open-weight multimodal model for text, image, audio, and video understanding, with tool calling and structured output support.

Added Aug 1, 2026

Context Window

262.1K

Max Output

32.8K

Avg output tokens (7d)

72 tokens

5%

Input Price (Auto)

$0.050/1M

Output Price (Auto)

$0.25/1M

Cache Read (Auto)

$0.025/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

9.4

Better than 38% of models compared

Agentic work

T²-Bench Telecom (legacy)

Legacy fallback · Conversational AI agents in dual-control scenarios

31.9%

Better than 40% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

35.0%

Better than 33% of models compared

Reasoning

HLE

Humanity's Last Exam

6.3%

Better than 38% of models compared

IFBench

Instruction-following benchmark

45.2%

Better than 52% of models compared

Coding

Terminal-Bench Hard (legacy)

Legacy fallback · Agentic coding and terminal use

11.4%

Better than 47% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

66.1%

Better than 42% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

35.0%

Better than 33% of models compared

Last updated Oct 1, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare Gemma 4 12B Instruct with similar models from the same provider or model family.

Gemma 4 12B Semancer

gemma-4-12b-it-semancer

Gemma 4 12B Semancer is an open-weight finetune by UnstableLlama trained on a custom occult-philosophy dataset. It is designed for in-depth philosophical discussion of topics such as truth, free will, consciousness, and meaning, with answers developed from first principles. It supports image understanding, tool calling, optional reasoning, and a 131,072-token context window.

Gemma 4 12B StationKeeper

gemma-4-12b-it-station-keeper

Gemma 4 12B StationKeeper is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 131,072-token context window.

Gemma 4 E2B Instruct

gemma-4-e2b-it

Google's Gemma 4 E2B Instruct is a compact open-weight multimodal model with 2B active parameters, supporting text, image, audio, video, tools, and structured output.

Gemma 4 E4B Instruct

gemma-4-e4b-it

Google's Gemma 4 E4B Instruct is an efficient open-weight multimodal model with 4B active parameters, supporting text, image, audio, video, tools, and structured output.

Gemma 4 26B A4B Cybersecurity

google/gemma-4-26b-a4b-it-cybersecurity

Gemma 4 26B A4B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.

Gemma 4 31B Split-Untied

google/gemma4-31b-splituntied

Blazed-Forge's Split-Untied is a text-only Gemma 4 31B community finetune with an untied BF16 output head, built for creative writing, roleplay, expressive dialogue, and tool use.