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
Capability Radar
17
general
39
coding
79
reasoning
54
science
90
agents
70
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 22 | 58.0 | LS |
| Code Ranking | 311 | 48.0 | AA |
| General Ranking | 280 | 45.0 | AA |
| Multimodal Ranking | 84 | 49.0 | LS |
| Science | 229 | 55.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
t2-bench
85.5%SR
Healthcare
MedXpertQA
58.1%SR
Language
MMMLU
86.3%SR
MMLU-Pro
82.6%SR
Long Context
MRCR v2 (8-needle)
44.1%SR
Math
AIME 2026
88.3%SR
MathVision
82.4%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
82.3%SR
LiveCodeBench v6
77.1%SR
BIG-Bench Extra Hard
64.8%SR
Humanity's Last Exam
17.2%SR
Vision
MMMU-Pro
73.8%SR
AA Evaluation Indices
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))79.2
Ifbench(Google Research (2023))72.4
Lcr(Artificial Analysis)65.7
Tau2(Sierra + U Toronto + Vector Institute (2025))43.6
Scicode(UIUC + Argonne National Lab (2024))40.0
Coding Index(Artificial Analysis)39.3
Terminalbench V2 139.0
Hle(Center for AI Safety + Scale AI (2025))19.3
Intelligence Index(Artificial Analysis)16.7
Terminalbench Hard(Stanford × Laude Institute (2026))13.6
Tau Banking12.0
LLM Stats Category Scores
(LLM Stats (zeroeval))Agents90
Tool Calling90
Language80
Legal80
Physics80
Finance80
Biology80
Chemistry80
Math70
Multimodal70
Reasoning70
General70
Healthcare70
Vision60
Long Context40
Pricing
Input Price$0.1 / 1M tokens
Output Price$0.37 / 1M tokens
Blended Price (3:1)$0.168 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
16 providers
Cheapest: DeepInfraMost Expensive: Scaleway
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2Novita
$0
$0
3Kilo Gateway
$0.042
$0.22
4EmpirioLabs AI
$0.05
$0.29
5OrcaRouter
$0.06
$0.33
6Requesty
$0.07
$0.34
7DevPass (LLM Gateway)
$0.07
$0.34
8OpenRouter
$0.09
$0.3
9Charm Hyper
$0.098
$0.334
10GooglePRIMARY
$0.1
$0.37
11Cortecs
$0.111
$0.557
12NanoGPT
$0.12
$0.38
13NovitaAI
$0.13
$0.4
14Merge Gateway
$0.13
$0.4
15Vercel AI Gateway
$0.15
$0.6
16Scaleway
$0.25
$0.5
Compare pricing across different API providers for this model.