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-V4-Pro
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Pricing
Evaluations
Evaluation overview
Overall rank
#25
82.4 points · 180 models
Open-weight rank
#4
93.5 points · 109 models
Data coverage
111 items
11 sources · updated through 2026-07-16
Domain performance
Coding
#28 / 160
83
Research
#15 / 174
93.1
Agents
#30 / 125
79.9
Long context
#22 / 82
80.9
Evaluation highlights
All evaluations
LiveCodeBench-v6
Reasoning · Qwen3.7-Plus Technical Report
93.5%
1
/ 49
VITA-Bench
Agents · Qwen3.7-Plus Technical Report
51.9%
1
/ 12
SWE-bench Verified
Coding · Hy3 Hugging Face README
80.6%
7
/ 60
LongBench v2
Long context · Nemotron-3-Ultra Technical Report
62.1%
3
/ 22
IFEval
Instruction following · Qwen3.7-Plus Technical Report
91.9%
11
/ 30
Chinese-SimpleQA
Knowledge · DeepSeek-V4-Pro Technical Report
84.4%
2
/ 16
Basic information
Context (input / output)
1M / 393K
Parameters
1600B / 49B active
Release date
2026-04
License
MIT
Input modalities
Text
Output modalities
Text
Architecture
MoE (384 experts), DSA
Active parameters
49B
Availability
DeepSeek
Full pricing
Input
≈ $0.4286 /1M
Output
≈ $0.8571 /1M
vLLM · FP8 · 200K
Deployment options
FP8 · 8 × 141 GB VRAM
Related links
Official site
HuggingFace
ModelScope
Version relationships
DeepSeek-V4 family
DeepSeek-V4-Flash
2026-04 · Same series
DeepSeek-V4-Flash Base
2026-04 · Same series
DeepSeek-V4-Pro
Current
2026-04 · Current model
DeepSeek-V4-Pro Base
2026-04 · Same series
Runtime modes
Thinking