Google's Gemma 4 26B A4B instruction-tuned model built for scalable reasoning, coding, long-context, and multimodal workflows. This route is tuned for faster direct answers while preserving multimodal and structured output support.
Added Apr 2, 2026
Model weightsContext Window
262.1K
Max Output
131.1K
Avg output tokens (7d)
398 tokens
Input Price (Auto)
$0.14/1M
Output Price (Auto)
$0.42/1M
Cache Read (Auto)
$0.068/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
25.7
Coding Index
39.3
Agentic Index
11.0
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
79.2%
Better than 75% of models compared
HLE
Humanity's Last Exam
18.3%
Better than 81% of models compared
IFBench
Instruction-following benchmark
72.4%
Better than 89% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
43.6%
Better than 49% of models compared
AA-LCR
Long context reasoning evaluation
55.7%
Better than 69% of models compared
GDPval-AA
Economically valuable tasks
13.4%
CritPt
Research-level physics reasoning
0.0%
Coding
SciCode
Python programming for scientific computing
40.0%
Better than 78% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
13.6%
Better than 52% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
19.1%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
86.4%
Last updated Jun 28, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare Gemma 4 26B A4B with similar models from the same provider or model family.
Gemma 4 26B A4B Thinking
google/gemma-4-26b-a4b-it:thinkingGoogle's Gemma 4 26B A4B instruction-tuned model with structured reasoning for more deliberate coding, multimodal analysis, and long-context problem solving.
Gemma 4 31B
google/gemma-4-31b-itGoogle's Gemma 4 31B instruction-tuned model for heavier reasoning, coding, agentic workflows, and long-context multimodal understanding. This route keeps tokenizer thinking disabled for faster direct answers.
Gemma 4 31B Thinking
google/gemma-4-31b-it:thinkingGoogle's Gemma 4 31B instruction-tuned model with thinking explicitly enabled, exposing reasoning traces for complex multimodal and coding workflows.
Gemma 4 26B A4B Uncensored TEE
TEE/gemma-4-26b-a4b-uncensoredGemma 4 26B A4B Uncensored Heretic is a multimodal MoE model tuned to reduce refusal behavior while preserving coding, reasoning, and function-calling strengths. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Gemma 4 12B Instruct
gemma-4-12b-itGoogle'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.
Gemma 4 E2B Instruct
gemma-4-e2b-itGoogle'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.