Qwen3-Omni-30B-A3B (Thinking): benchmark results
Provider: Alibaba. Access: Open.
Unified ELO 1530 ± 1, rank #797 of 2033 rated models, from 58 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MOV-Bench | 55.49 | Accuracy (%; 519 audio-visual multi-hop multiple-choice ques | 100 |
| MOV-Bench - Intent Reasoning | 58.75 | Accuracy (%; 80 intent-reasoning questions; direct inference | 100 |
| MOV-Bench - Relational Reasoning | 60.63 | Accuracy (%; 127 relational-reasoning questions; direct infe | 100 |
| OmniClean | 34.93 | Accuracy (%; unweighted mean over nine audio-visual benchmar | 100 |
| OmniClean - Daily-Omni | 42.62 | Accuracy (%; the 237 of 1,197 Daily-Omni queries left after | 100 |
| OmniClean - IntentBench | 36.42 | Accuracy (%; the 660 of 2,689 IntentBench queries left after | 100 |
| OmniClean - UNO-Bench | 37.55 | Accuracy (%; the 228 of 1,000 UNO-Bench multiple-choice (UNO | 100 |
| OmniClean - Video-Holmes | 46.33 | Accuracy (%; the 885 of 1,837 Video-Holmes queries left afte | 100 |
| OmniClean - WorldSense | 27.7 | Accuracy (%; the 875 of 3,172 WorldSense queries left after | 100 |
| SEA-SpeechBench - Age Recognition (SEA Prompt) | 36.78 | Macro-F1 (%; speaker age group (teens, adults, seniors) from | 100 |
| SEA-SpeechBench - Age Recognition (English Prompt) | 38.1 | Macro-F1 (%; speaker age group (teens, adults, seniors) from | 92.9 |
| SEA-SpeechBench - Timestamped Content Query (0-30 s) | 1.28 | WER or CER (%; transcribe only the speech inside a queried t | 92.9 |
Interactive version: theaggregate.ai/model?slug=qwen3-omni-30b-a3b-thinking · How It Works · Data refreshed daily, snapshot 2026-09-27.