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
DeepSeek-V3
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Pricing
Evaluations
Evaluation overview
Overall rank
#145
61.8 points · 202 models
Open-weight rank
#69
64.4 points · 120 models
Data coverage
41 items
4 sources · updated through 2026-09-02
Domain performance
Coding
#126 / 182
62.7
Research
#138 / 196
71.4
Agents
#129 / 148
54.3
Long context
#67 / 95
70.7
Evaluation highlights
All evaluations
DROP
Reasoning · DeepSeek-R1 Technical Report
91.6%
2
/ 15
HumanEval-Mul
Coding · DeepSeek-V3 Technical Report
82.6%
1
/ 7
BFCL v3 Full
Agents · Qwen3 Technical Report
57.6%
30
/ 49
LongBench v2
Long context · DeepSeek-V3 Technical Report
48.7%
18
/ 27
INCLUDE
Multilingual · Qwen3 Technical Report
76.7%
9
/ 69
AlignBench v1.1
Conversation · Qwen3 Technical Report
8.64score
8
/ 35
Basic information
Context (input / output)
131K / 8K
Parameters
671B / 37B active
Release date
2024-12
License
MIT
Input modalities
Text
Output modalities
Text
Availability
DeepSeek
Full pricing
Input
≈ $0.1429 /1M
Output
≈ $0.2857 /1M
vLLM · FP8
Deployment options
FP8 · 8 × 141 GB VRAM
Related links
Official site
HuggingFace
ModelScope
Version relationships
DeepSeek-V3 family
DeepSeek-V3
Current
2024-12 · Current model
DeepSeek-V3 Base
2024-12 · Same series
DeepSeek-V3-0324
2025-03 · Same series
DeepSeek-V3.2
2025-12 · Same series