D
DeepSeek·active
DeepSeek: DeepSeek V4 Pro 0813
DeepSeek's efficiency model. Long-context specialist with 1.0M window.
Overall score
—
no data
Input
$1.12
per 1M tokens
Output
$3.37
per 1M tokens
Context
1.0M
tokens
Blended
$2.81
3:1 out:in ratio
Scores by test
Methodology →Structured Output
—
Strategic Analysis
—
Constrained Rewriting
—
Creative Problem Solving
—
Tool Calling
—
Faithfulness
—
Classification
—
Long Context
—
Safety Calibration
—
Persona Consistency
—
Agentic Planning
—
Multilingual
—
Tabular Data
—
AIME 2025
98.6
GPQA Diamond
91.7