Qwen3 Vision‑Language model built on a 235B MoE backbone (≈22B active per token). Strong at OCR, charts/tables, multi‑image reasoning, and complex document understanding. The Thinking variant enables long‑form, chain‑of‑thought style reasoning.
Added Aug 26, 2025
Model weightsContext Window
N/A
Max Output
32.8K
Avg output tokens (7d)
2.2K tokens
Input Price (Auto)
$0.50/1M
Output Price (Auto)
$6.00/1M
Cache Read (Auto)
$0.25/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
13.4
Agentic work
T²-Bench Telecom (legacy)
Legacy fallback · Conversational AI agents in dual-control scenarios
54.1%
Better than 55% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
63.7%
Better than 58% of models compared
Reasoning
HLE
Humanity's Last Exam
11.9%
Better than 59% of models compared
IFBench
Instruction-following benchmark
56.5%
Better than 67% of models compared
Coding
Terminal-Bench Hard (legacy)
Legacy fallback · Agentic coding and terminal use
11.4%
Better than 47% of models compared
LiveCodeBench
Contamination-free coding benchmark
64.6%
Better than 71% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
88.3%
Better than 87% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
83.6%
Better than 85% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
77.2%
Better than 61% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
63.7%
Better than 58% of models compared
Last updated Sep 11, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Qwen3 VL 235B A22B Thinking with similar models from the same provider or model family.
Qwen3 VL 235B A22B Instruct Original
qwen3-vl-235b-a22b-instruct-originalNote: direct via Alibaba, a Chinese entity - privacy and logging guarantees may be limited. Qwen3 Vision‑Language model (235B MoE, ≈22B active) tuned for instruction following and grounded visual QA. Excels at image understanding, dense OCR, charts and diagrams, and multi‑image context. Use this variant when you want concise, direct answers grounded in the visuals.
Qwen 3 235b A22B 2507 Thinking
qwen/qwen3-235b-a22b-thinking-2507The thinking version of Qwen 3 235b A22B 2507, with enhanced reasoning capabilities and step-by-step problem solving.
Qwen 3 235b A22B 2507
qwen/qwen3-235b-a22b-instruct-2507Qwen 3 235b A22B Instruct 2507 the updated version of Qwen3 235B A22B, with significant improvements in performance. This model is non-thinking.
Qwen 3 235b A22B
qwen/qwen3-235b-a22bQwen 3 235b is a 235b model with 22B active parameters. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.
Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instructQwen3 Vision‑Language model (235B MoE, ≈22B active) tuned for instruction following and grounded visual QA. Excels at image understanding, dense OCR, charts/diagrams, and multi‑image context.
Qwen 3.8 27B Queen
qwen/qwen3.8-27b-queenQwen 3.8 27B Queen is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 262,144-token context window.