← Back to all models
D

DeepSeek V3

by DeepSeek
Flagship Open source 🏆 Ranked #9 of 22
81.0
Overall Score
out of 100
About

DeepSeek's breakthrough open-source model that shocked the AI industry with frontier-level performance at a fraction of the training cost. DeepSeek V3 demonstrates that cutting-edge AI is no longer exclusive to the largest technology companies.

Key Metrics
Context Window
128K
tokens
Avg Response
680
milliseconds
Input Cost
$0.27
per million tokens
Output Cost
$1.1
per million tokens
Arena ELO
1302
Chatbot Arena rating
MT-Bench
8.9
out of 10
Benchmark Scores
MMLU
88.5%
HumanEval
89.1%
MATH
87.2%
GPQA
51.3%
MT-Bench
89.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Exceptional value ✓ Open source ✓ Strong mathematics ✓ Coding capability ✓ Cost-effective API
Limitations
⚠ Primarily Chinese-developed (potential regional biases) ⚠ Newer ecosystem ⚠ Limited multimodal support
Ideal Use Cases
Cost-sensitive applications Mathematics and science Code generation Academic research Open-source projects
Model Details
Provider DeepSeek
Released 2024-12-26
Open source Yes
Multimodal No
Tier Flagship
Global rank #9 / 22
Pricing (USD)
Input tokens $0.27/M
Output tokens $1.1/M
Per 1,000 tokens ≈ $0.0003 input / $0.0011 output
All Benchmarks
MMLU 88.5%
HumanEval 89.1%
MATH 87.2%
GPQA 51.3%
MT-Bench 8.9/10
Arena ELO 1302
Compare this model View leaderboard
Similar Models

You might also consider

o
o3
OpenAI
93.7
score
Flagship

OpenAI's most powerful reasoning model, using extended chain-of-thought to tackle the hardest problems in mathematics, science, and coding. o3 sets new standards on GPQA and competitive maths at the cost of higher latency and price.
C
Claude Opus 4
Anthropic
90.7
score
Flagship

Anthropic's most powerful and intelligent model, built for the most demanding tasks where quality outweighs cost. Claude Opus 4 leads on complex multi-step reasoning, graduate-level science, and nuanced long-form writing.
C
Claude Sonnet 4.6
Anthropic
88.3
score
Flagship

The latest and most capable Sonnet model to date. Claude Sonnet 4.6 brings further gains in mathematical reasoning and instruction following, making it Anthropic's most well-rounded model at the Sonnet price point.