DeepSeek V4 Pro

Reasoning, High Effort

Creator

DeepSeek

Released

2026-04-24

Intelligence

49.8

Artificial Analysis Index

Coding

43.2

Artificial Analysis Index

In $/1M

$0.43

input tokens

Out $/1M

$0.87

output tokens

Blended $/1M

$0.54

3:1 blended

Speed

55

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
91
Humanity’s Last Exam
34
MMLU-Pro
SciCode
46
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
94
Terminal-Bench Hard
42
IFBench
71
Via Artificial Analysis