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 31B
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#67
70.5 points · 180 models
Open-weight rank
#23
77.9 points · 109 models
Data coverage
25 items
6 sources · updated through 2026-07-16
Domain performance
Coding
#56 / 160
73.4
Research
#65 / 174
81.5
Agents
#72 / 125
65.8
Vision
#41 / 65
77.7
Long context
#30 / 82
78.9
Evaluation highlights
All evaluations
Codeforces ELO
Coding · Gemma 4 Technical Report
2,150Elo
1
/ 20
MMMLU
Reasoning · Gemma 4 Technical Report
88.4%
3
/ 40
Arena Vision Rating
Multimodal · Arena.ai Vision
1,255.41Elo
20
/ 121
MRCR v2 (8-needle 128K)
Long context · Gemma 4 Technical Report
66.4%
1
/ 5
τ²-Bench
Agents · Gemma 4 Technical Report
76.9%
12
/ 21
Arena Text Rating
Reasoning · Arena.ai Text
1,451.15Elo
38
/ 354
Basic information
Context (input / output)
262K / 8K
Parameters
30.7B
Release date
2026-04
License
Apache 2.0
Input modalities
Text · Image
Output modalities
Text
Availability
vLLM · BF16
Deployment options
BF16 · 75 GB VRAM
Related links
Official site
HuggingFace
ModelScope