DeepSeek V3.1 (Non-reasoning)

Last updated: Recently

Model Type

Agent

Max Context

164K

Max Output

32,768 tokens

Parameter Scale

DeepSeek V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model& x27;s original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model& x27;s performance in coding and search agents. 163,840 token context window, maximum output of 32,768 tokens. Higher uptime with 4 providers. Includes independent benchmarks from Artificial Analysis.

Input Modality

text

Output Modality

text

Inference Speed

Latest Release Date

8/21/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

DeepSeek V3.1 (Non-reasoning)

Release date

8/21/2025

Performance

model_creator.name

DeepSeek

AA Evaluation Scores

AA Intelligence Index

28.1

AA Coding Index

28.4

AA Math Index

49.7

MMLU Pro

0.833

GPQA

0.735

HLE

0.063

LiveCodeBench

0.577

SciCode

0.367

Math-500

AIME

AIME 2025

0.496666666666667

IFBench

0.378231292517007

LCR

0.45

TerminalBench Hard

0.242424242424242

TAU2

0.347953216374269

Output Speed (tokens/s)

TTFT (s)

First Answer Token (s)

DeepSeek

DeepSeek V3.1 (Non-reasoning)

$0.56/M$1.67/M

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0