← All benchmarks
Qwen3 Omni 30B A3B Instruct
Alibaba · Released 2025-09-22 · Independent benchmark scores from Artificial Analysis
Intelligence Index
6.0
Output speed
107.9
tokens/sec
Blended price
$0.43
per 1M tokens
Time to first token
0.88s
Model metadata
| Model ID | 0b226b82-1462-4860-bf1a-f8aed7024791 |
|---|---|
| Slug | qwen3-omni-30b-a3b-instruct |
| Release date | 2025-09-22 |
| Provider | Alibaba |
| Provider slug | alibaba |
| Output speed | 107.9 tok/s |
| Time to first token | 0.88s |
| Time to first answer | 0.88s |
| Blended price ($/1M) | $0.43 |
| Input price ($/1M) | $0.25 |
| Output price ($/1M) | $0.97 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | 52.3% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 6.00 |
| artificial analysis math index | 52.30 |
| gpqa | 62.0% |
| hle | 4.6% |
| ifbench | 31.2% |
| lcr | 0.0% |
| livecodebench | 42.2% |
| math 500 | — |
| mmlu pro | 72.5% |
| scicode | — |
| tau banking | — |
| tau2 | 16.4% |
| terminalbench hard | 1.5% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct
Benchmark data from Artificial Analysis.