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
Input Price (Auto)
$0.063/1M
Output Price (Auto)
$0.31/1M
Cache Read (Auto)
$0.032/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
13.2
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
66.1%
Better than 44% of models compared
HLE
Humanity's Last Exam
6.3%
Better than 43% of models compared
IFBench
Instruction-following benchmark
45.2%
Better than 51% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
31.9%
Better than 40% of models compared
AA-LCR
Long context reasoning evaluation
31.3%
Better than 37% of models compared
Coding
SciCode
Python programming for scientific computing
29.7%
Better than 41% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
11.4%
Better than 47% of models compared
Last updated Aug 16, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…