Alibaba
Qwen3 Omni 30B A3B Instruct
Quality Score7.1
Value Score6.8
Reliability15.4
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text, image, video, speech
- Output modalities
- text, speech
- Context window
- 65,536 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.250
- Output
- $0.970
- Cached Input
- not available
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 4.8
- Coding
- not available
- Agentic
- not available
- Omniscience
- -69.3
- Correct
- 14.3%
- Blended price
- $0.322
Answer outcomes
Correct 14.3%Incorrect 83.6%Abstained 2.1%
Artificial Analysis benchmarks
- SciCode
- 19%
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 62%
- CritPt
- 0%
- AA-Omniscience
- 15%
- AA-LCR
- 0%
Similar models
- Qwen3.5 2B (Non-reasoning)AlibabaQuality Score 4.2Value Score not available
- Qwen3.5 0.8B (Non-reasoning)AlibabaQuality Score 2.4Value Score not available
- Qwen3 Next 80B A3B InstructAlibabaQuality Score 13.0Value Score 14.6
- Qwen3.5 4B (Non-reasoning)AlibabaQuality Score 12.1Value Score 17.1
- Qwen3.5 Omni FlashAlibabaQuality Score 13.9Value Score 18.8
- Qwen3.5 9B (Non-reasoning)AlibabaQuality Score 15.3Value Score 19.6