Updated daily at 05:00 UTC
- Released
- 27 Mar 2025
- Status
- Legacy
- Context
- 32.8K
- Max output
- 2K
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- apache-2.0
- Parameters
- 7B
- Knowledge cutoff
- —
- Reasoning
- No
- Modalities
- text, image, audio, video → text, audio
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
Not enough independent results yet
Only independent and third-party results rank a model; self-reported and unattributed numbers never do.
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
No benchmark results yet
Other Qwen-Omni versions
- Qwen3.8-Omni-Flash17 Sep 2026
- Qwen3.5-Omni-Flash15 Mar 2026
- Qwen3.5-Omni-Plus15 Mar 2026
- Qwen3-Omni-30B-A3B-Instruct22 Sep 2025
- Qwen3-Omni-30B-A3B-Thinking22 Sep 2025
- Qwen3-Omni-Flash15 Sep 2025
- Qwen2.5-Omni-3B30 Apr 2025
- Qwen-Omni-Turbo19 Jan 2025