Qwen3 VL 235B A22B Instruct

Qwen3 VL 235B A22B Instruct

Qwen🇨🇳qwen/qwen3-vl-235b-a22b-instruct
Compare

Qwen3 VL 235B-A22B Instruct is Alibaba's large-scale multimodal MoE model, combining Qwen3's language capability with vision understanding for image, document, and video tasks. It suits demanding multimodal applications needing near-flagship quality.

Released
Sep 23, 2025
Input
TextImage
Output
Text
Support
ReasoningTool callingStructured outputs

Performance

Median latency and throughput measured across recent requests.

Throughput32 tok/s
Latency2.69s

Best at

The categories where this model ranks highest.

Image understanding

#85 · top 51%

Business, Management, & Finance

#113 · top 27%

Mathematical

#133 · top 33%

Life, Physical, & Social Science

#134 · top 32%

DomainScoreRank
Software & IT Services1454#146
Writing, Literature, & Language1386#160
Life, Physical, & Social Science1442#134
Entertainment, Sports, & Media1361#176
Business, Management, & Finance1440#113
Mathematical1430#133
Legal & Government1431#135
Medicine & Healthcare1431#155
Multimodal
Image understanding1214#85

Latest news about Qwen3 VL 235B A22B Instruct

Recent articles and community posts, linked to their original sources.