DeepSeek V3.2 Exp

Non-reasoning

Creator

DeepSeek

Released

2025-09-29

Intelligence

28.4

Artificial Analysis Index

Coding

30.0

Artificial Analysis Index

In $/1M

$0.28

input tokens

Out $/1M

$0.41

output tokens

Blended $/1M

$0.31

3:1 blended

Speed

0

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
74
Humanity’s Last Exam
9
MMLU-Pro
84
SciCode
40
LiveCodeBench
55
MATH-500
AIME 2025
58
τ²-Bench (agentic)
34
Terminal-Bench Hard
25
IFBench
43
Via Artificial Analysis