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
Llama 4 Maverick
Open
Share
Add to comparison
Tool use
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#146
61.7 points · 202 models
Open-weight rank
#70
64.4 points · 120 models
Data coverage
22 items
1 source · updated through 2025-05-14
Domain performance
Coding
#133 / 182
61.4
Research
#136 / 196
71.7
Agents
#134 / 148
52
Evaluation highlights
All evaluations
MMLU-Redux
Reasoning · Qwen3 Technical Report
91.8%
27
/ 102
LiveCodeBench v5
Coding · Qwen3 Technical Report
37.2%
17
/ 36
BFCL v3 Full
Agents · Qwen3 Technical Report
52.9%
36
/ 49
INCLUDE
Multilingual · Qwen3 Technical Report
80.9%
5
/ 69
IFEval strict prompt
Instruction following · Qwen3 Technical Report
86.7%
21
/ 55
AlignBench v1.1
Conversation · Qwen3 Technical Report
7.97score
14
/ 35
Basic information
Context (input / output)
1.05M / 8K
Parameters
402B / 17B active
Release date
2025-04
Input modalities
Text · Image
License
Llama 4 Community License
Output modalities
Text
Architecture
MoE
Availability
SGLang · BF16 · 64K
Deployment options
BF16 · 8 × 141 GB VRAM
Related links
Official site
HuggingFace
Version relationships
Llama 4 family
Llama 4 Maverick
Current
2025-04 · Current model
Llama 4 Maverick Base
2025-04 · Same series
Llama 4 Scout
2025-04 · Same series
Llama 4 Scout Base
2025-04 · Same series