Qwen3 VL 235B A22B Thinking
Qwen vision-language thinking model for visual reasoning, documents, and agent tasks
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
RELEASE DATESep 23, 2025
WEIGHTSOpen weights
CONTEXT WINDOW131.1K
MAX OUTPUT32.8K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.