Atlas

Models

← All models

Qwen3 Omni 30B A3B Instruct

Alibaba · 2025-09-22 · 35.3B parameters

Qwen3-Omni-30B-A3B-Instruct is Alibaba's non-thinking Qwen3-Omni checkpoint; it contains the MoE Thinker and Talker together with audio and vision encoders. It accepts text, image, audio, and video input and produces text and real-time streaming speech, with Qwen reporting support for 119 text languages, 19 speech-input languages, and 10 speech-output languages.

Benchmark scores

BenchmarkScore
AA-LCR0.0
AA-Omniscience Index-69.2
AIME 2025 (Artificial Analysis avg@10)52.3
Artificial Analysis Intelligence Index5.1
Artificial Analysis Omniscience Accuracy14.4
Artificial Analysis Omniscience Hallucination Rate97.7
Artificial Analysis Openness Index44.4
Audio MultiChallenge (Audio Output)24.3
Capability130.8
CritPt (avg@5)0.0
GPQA Diamond (Artificial Analysis avg@5)62.0
Humanity's Last Exam (Text-Only)5.1
IFBench (Artificial Analysis)31.2
LiveCodeBench (Artificial Analysis)42.2
MMLU Pro72.5
MMMU Pro55.5
SciCode (Artificial Analysis avg@3)18.6
Terminal-Bench Hard1.5
τ²-bench (Telecom)16.4
Loading Atlas data…