Qwen3 Next 80B A3B (Reasoning)

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Qwen3 Next 80B A3B Reasoning by Alibaba: Text model; TTFT 1.125s, 167.2 tok/s.

Input Modality

Output Modality

Inference Speed

167.196 tokens/s

Latest Release Date

9/11/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Qwen3 Next 80B A3B (Reasoning)

Release date

9/11/2025

Performance

167.196 tokens/s

model_creator.name

Alibaba

AA Evaluation Scores

AA Intelligence Index

26.7

AA Coding Index

19.5

AA Math Index

84.3

MMLU Pro

0.824

GPQA

0.759

HLE

0.117

LiveCodeBench

0.784

SciCode

0.388

Math-500

AIME

AIME 2025

0.843

IFBench

0.607

LCR

0.603

TerminalBench Hard

0.098

TAU2

0.415

Output Speed (tokens/s)

167.196 tok/s

TTFT (s)

1.125s

First Answer Token (s)

13.087s

Alibaba

◎

Qwen3 Next 80B A3B (Reasoning)

$0.50/M$6.00/M

Qwen3 Next 80B A3B Reasoning by Alibaba: Text model; TTFT 1.125s, 167.2 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0