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 E2B
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#149
54.5 points · 180 models
Open-weight rank
#81
59.3 points · 109 models
Data coverage
13 items
1 source · updated through 2026-04-03
Domain performance
Coding
#111 / 160
64.8
Research
#143 / 174
64.7
Agents
#93 / 125
60.5
Vision
#62 / 65
65.1
Long context
#51 / 82
71.7
Evaluation highlights
All evaluations
MMLU-Pro
Reasoning · Gemma 4 Technical Report
60%
73
/ 95
MRCR v2 (8-needle 128K)
Long context · Gemma 4 Technical Report
19.1%
4
/ 5
OmniDocBench 1.5
Multimodal · Gemma 4 Technical Report
0.29%
25
/ 28
τ²-Bench
Agents · Gemma 4 Technical Report
24.5%
19
/ 21
Codeforces ELO
Coding · Gemma 4 Technical Report
633Elo
19
/ 20
MMMLU
Reasoning · Gemma 4 Technical Report
67.4%
31
/ 40
Basic information
Context (input / output)
131K / 8K
Parameters
2.3B
Release date
2026-04
License
Apache 2.0
Input modalities
Text · Image · Audio
Output modalities
Text
Total parameters
5.1B (including embeddings)
Availability
vLLM · BF16
Deployment options
BF16 · 13 GB VRAM
Related links
Official site
HuggingFace
ModelScope