Skip to main content

Gemma 4 26B A4B (Non-reasoning)

GoogleGemma

Description

Gemma 4 26B-A4B is Google DeepMind's Mixture-of-Experts multimodal model with 26 billion total parameters and 3.8 billion activated parameters per token, with a 256K context window. Ranks #6 among open models on Arena AI, outcompeting models 20x its size. Achieves an estimated LMArena text score of 1441. Supports image and text inputs.

Release Date
2026-04-02
Parameters
Context Length
262K
Modalities
image, text

Capability Radar

18
general
37
coding
71
reasoning
47
scienceest.
90
agents
70
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking213
46.0
AA
General Ranking279
38.0
AA
Science174
51.0
AA

Benchmark Scores (LLM Stats)

Agents

t2-bench85.5%SR

Biology

GPQA82.3%SR

Finance

MMLU-Pro82.6%SR

General

MMMLU86.3%SR
LiveCodeBench v677.1%SR
MMMU-Pro73.8%SR
BIG-Bench Extra Hard64.8%SR
MRCR v244.1%SR

Healthcare

MedXpertQA58.1%SR

Math

AIME 202688.3%SR
MathVision82.4%SR
Humanity's Last Exam17.2%SR

AA Evaluation Indices

Intelligence Index
20.1
Gpqa
0.7
Ifbench
0.5
Tau2
0.4
Lcr
0.4
Scicode
0.4
Terminalbench Hard
0.3
Hle
0.1

LLM Stats Category Scores

Agents
90
Tool Calling
90
Language
80
Legal
80
Physics
80
Finance
80
Biology
80
Chemistry
80
Math
70
Multimodal
70
Reasoning
70
General
70
Healthcare
70
Vision
60
Long Context
40

Pricing

Input Price$0.13 / 1M tokens
Output Price$0.4 / 1M tokens
Blended Price (3:1)$0.198 / 1M tokens

Speed

Tokens/sec39.7
Time to First Token1.24s
Time to Answer1.24s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1GooglePRIMARY
$0.13
$0.4

Compare pricing across different API providers for this model.

External Sources