Qwen3 Omni 30B A3B (Reasoning)

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Qwen3 Omni 30B A3B Reasoning by Alibaba: Text model; TTFT 0.943s, 94.9 tok/s.

Input Modality

Output Modality

Inference Speed

94.905 tokens/s

Latest Release Date

9/22/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Qwen3 Omni 30B A3B (Reasoning)

Release date

9/22/2025

Performance

94.905 tokens/s

model_creator.name

Alibaba

AA Evaluation Scores

AA Intelligence Index

15.6

AA Coding Index

12.7

AA Math Index

MMLU Pro

0.792

GPQA

0.726

HLE

0.073

LiveCodeBench

0.679

SciCode

0.306

Math-500

AIME

AIME 2025

0.74

IFBench

0.434

LCR

TerminalBench Hard

0.038

TAU2

0.213

Output Speed (tokens/s)

94.905 tok/s

TTFT (s)

0.943s

First Answer Token (s)

22.017s

Alibaba

◎

Qwen3 Omni 30B A3B (Reasoning)

$0.25/M$0.97/M

Qwen3 Omni 30B A3B Reasoning by Alibaba: Text model; TTFT 0.943s, 94.9 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0