Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
Gemma 4 26B A4B
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#119
66.8 points · 202 models
Open-weight rank
#49
69.7 points · 120 models
Data coverage
18 items
4 sources · updated through 2026-09-02
Domain performance
Coding
#87 / 182
68.6
Research
#110 / 196
76.6
Agents
#104 / 148
62.3
Vision
#67 / 82
66.7
Long context
#45 / 95
77.5
Evaluation highlights
All evaluations
MMMLU
Reasoning · Gemma 4 Technical Report
86.3%
7
/ 40
Codeforces ELO
Coding · Gemma 4 Technical Report
1,718Elo
6
/ 20
Arena Vision Rating
Multimodal · Arena.ai Vision
1,241.54Elo
40
/ 133
τ²-Bench
Agents · Gemma 4 Technical Report
68.2%
15
/ 21
MRCR v2 (8-needle 128K)
Long context · Gemma 4 Technical Report
44.1%
10
/ 13
Arena Text Rating
Reasoning · Arena.ai Text
1,438.25Elo
71
/ 375
Basic information
Context (input / output)
262K / 8K
Parameters
25.2B / 3.8B active
Release date
2026-04
License
Apache 2.0
Input modalities
Text · Image
Output modalities
Text
Architecture
MoE
Availability
vLLM · BF16
Deployment options
BF16 · 64 GB VRAM
Related links
Official site
HuggingFace
ModelScope