Qwen3 VL 235B
alibaba/qwen3-vl-235b-a22b-thinking- Alibaba
- Family · Qwen3 VL
- Tools · Vision
Not on OSMEXO yet
Spec & list price
Context250K
Usage
Requests / day9.7K
Tool calls / req0.07
Per request · 30 days
Avg input5.7K0.4× median
Avg output684about median
Reasoning share84%1.5× median
Tool-call failures3.4%1.8× median
Consumption
Peak 270.1M 8 OctLow 18.6M 27 Sep
News & trends
1 mentions this week ▼ 67%Qwen3 VL family · videos, posts, articles · 30 days
Trending · 14 days · Qwen3 VL family
- FLUX.3 Image Klein (5.6B + Qwen3-VL-4B-Instruct) across 15 complex prompts: Macro, Typography, Fluid physics, and 0.5x Selfies, Workflows Include5 upvotes
- FLUX.3 Image Klein (5.6B + Qwen3-VL-4B-Instruct) across 15 complex prompts: Macro, Typography, Fluid physics, and 0.5x Selfies, Workflows Include5 upvotes
News · latest from Alibaba
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Qwen3.8-Flash Now Available in the EU on Alibaba Cloudtwitter.com · 31 Oct
- Alibaba's Qwen3.8-Flash-Next model tried to upload a file to Beijing in a testnotebookcheck.net · 27 Oct
- Running Qwen3.8-Flash-Next NVFP4 at 184 tok/s on a single RTX 6000 Promeshapplied.com · 26 Oct
Benchmarks
Benchmark data: Artificial AnalysisFamily progress
Intelligence Index
- Family releases11.9
When to use
Best for
- Reasoning over images and documents
- Chart, diagram and screenshot analysis
- Vision-based agents with tool calls
- Long multimodal document review
Think twice for
- Image generation
- Cheap high-volume vision tagging
- Latency-sensitive chat
- Strict schema-bound structured output
Research papers
- In-Context Learning Can Help Vision-Language Models Overcome Training Priors9 Oct
- Team MSU GenText-Forensics Challenge 2026 Technical Report29 Sep
- R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables3 Jul
- Ill-Posed by Design: Probing Evidence Use in VLMs23 Jun
- PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks11 Jun
- Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning11 Jun
- Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion30 May
- Can You Trust What You See? Human and AI Detection of Synthetic Legal Evidence29 May
Same family
Qwen3 VL- 9.9
- 13.4
- 9.5
- 8.4
- 11.9
- 7.0
- 8.2
- 5.7
Want Qwen3 VL 235B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.