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 3.1 405B Instruct
Open
Share
Add to comparison
Tool use
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#139
57.6 points · 180 models
Open-weight rank
#73
62.7 points · 109 models
Data coverage
24 items
1 source · updated through 2024-12-27
Domain performance
Coding
#127 / 160
61.9
Research
#131 / 174
68.8
Long context
#65 / 82
63.7
Evaluation highlights
All evaluations
MMLU
Reasoning · DeepSeek-V3 Technical Report
88.6%
8
/ 46
Codeforces Percentile
Coding · DeepSeek-V3 Technical Report
25.3%
9
/ 13
LongBench v2
Long context · DeepSeek-V3 Technical Report
36.1%
19
/ 22
IFEval strict prompt
Instruction following · DeepSeek-V3 Technical Report
86%
25
/ 55
SimpleQA
Knowledge · DeepSeek-V3 Technical Report
17.1%
8
/ 13
Arena-Hard
Conversation · DeepSeek-V3 Technical Report
69.3%
25
/ 39
Basic information
Context (input / output)
128K / 4K
Parameters
405B
Release date
2024-07
Input modalities
Text
License
Llama 3.1 Community License
Output modalities
Text
Availability
SGLang · BF16
Deployment options
BF16 · 8 × 80 GB VRAM
Related links
Official site
HuggingFace
ModelScope
Version relationships
Llama 3.1 family
Llama 3.1 405B
2024-07 · Same series
Llama 3.1 405B Instruct
Current
2024-07 · Current model
Llama 3.1 8B Instruct
2024-07 · Same series