DeepSeek V3.1 Terminus

Non-reasoning

Creator

DeepSeek

Released

2025-09-22

Intelligence

28.5

Artificial Analysis Index

Coding

31.9

Artificial Analysis Index

In $/1M

$0.27

input tokens

Out $/1M

$1.00

output tokens

Blended $/1M

$0.45

3:1 blended

Speed

0

tokens / sec

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
75
Humanity’s Last Exam
8
MMLU-Pro
84
SciCode
32
LiveCodeBench
53
MATH-500
AIME 2025
54
τ²-Bench (agentic)
37
Terminal-Bench Hard
32
IFBench
41
Via Artificial Analysis