Gemma 4 26B A4B (Reasoning)
GoogleGemmaOpen WeightApache 2.0 · Commercial OK
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
25.2B
Context Length
262K
Modalities
image, text, video
Capability Radar
28
general
25
coding
79
reasoning
53
scienceest.
90
agents
70
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agents & Tools | 2 | 86.0 | LS |
| Code Ranking | 182 | 43.0 | AA |
| General Ranking | 160 | 56.0 | AA |
| Science | 88 | 63.0 | AA |
Benchmark Scores (LLM Stats)
Agents
t2-bench
85.5%SR
Biology
GPQA
82.3%SR
Finance
MMLU-Pro
82.6%SR
General
MMMLU
86.3%SR
LiveCodeBench v6
77.1%SR
MMMU-Pro
73.8%SR
BIG-Bench Extra Hard
64.8%SR
MRCR v2
44.1%SR
Healthcare
MedXpertQA
58.1%SR
Math
AIME 2026
88.3%SR
MathVision
82.4%SR
Humanity's Last Exam
17.2%SR
AA Evaluation Indices
Intelligence Index31.2
Coding Index22.4
Gpqa0.8
Ifbench0.7
Lcr0.6
Tau20.4
Scicode0.4
Hle0.2
Terminalbench Hard0.1
LLM Stats Category Scores
Tool Calling90
Agents90
Biology80
Chemistry80
Finance80
Language80
Legal80
Physics80
General70
Healthcare70
Math70
Multimodal70
Reasoning70
Vision60
Long Context40
Pricing
Input Price$0.13 / 1M tokens
Output Price$0.4 / 1M tokens
Blended Price (3:1)$0.198 / 1M tokens
Speed
Tokens/sec0.0 tokens/s
Time to First Token0.00s
Time to Answer0.00s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| Novita | 130K | 400K |