Qwen: Qwen3 VL 235B A22B Thinking

qwen · Released Sep 23, 2025
DFO score #293 / 749
12.5 leaderboard score
Speed #267 / 355
57.7 tok/s
Input Price #467 / 749
$0.400 per 1M tokens
Output Price #579 / 749
$4.00 per 1M tokens
Context #389 / 749
131,072 tokens

Analysis Summary

Qwen3 VL 235B A22B Thinking is a Qwen multimodal model with image input, tool use, function calling, and a 131,072-token context window. The supplied data shows stronger results in math and general knowledge benchmarks than its overall intelligence index suggests, as well as a measured instruction-following result. Its reasoning profile is therefore uneven rather than uniformly strong.

The vision and tool support make it relevant to image-based analysis, document workflows, and structured content tasks. It may help teams interpret visual inputs alongside text, but it should not be treated as a leading general reasoner or autonomous agent. Check accuracy and adherence to client-specific instructions before using its output directly in published materials.

Pricing is comparatively low on input, though output costs more. It is worth testing where image understanding is central and a human can verify the result.

Assessed September 23, 2026

Editorial notes

Qwen3 VL 235B A22B Thinking combines image understanding, tool and function calling, and strong supplied math and knowledge results; its reasoning index remains limited overall.

The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?

DFO Verdict

Qwen3 VL 235B A22B Thinking combines image understanding, tool and function calling, and strong supplied math and knowledge results; its reasoning index remains limited overall.

#293 of 749 overall Down 88 this week

Benchmarks

Intelligence Index 8.5 #197 of 454 · Artificial Analysis
Coding Index Not published yet Artificial Analysis
Agentic Index Not published yet Artificial Analysis
Creative Writing Not rated Arena rating
Instruction Following Not rated Arena rating
GPQA Diamond 77.2%
HLE 10.1%
MMLU Pro 83.6%
AIME 2025 88.3%
SciCode 39.9%
LiveCodeBench 64.6%
TerminalBench Hard 11.4%
τ²-Bench 54.1%
IFBench 56.5%
LCR 58.7%

Artificial Analysis data refreshed Nov 16, 2026. Arena ratings from the Nov 9, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.

Artificial Analysis has not published coding or agentic results for Qwen: Qwen3 VL 235B A22B Thinking yet. Until it does, the model sits below tested models on the Coding and AI Agents lists.

Artificial Analysis no longer lists this model, so its indexes are converted from their older scale to stay comparable.

How Qwen: Qwen3 VL 235B A22B Thinking compares

Qwen: Qwen3 VL 235B A22B Thinking ranks #197 of 454 AI models we track for overall intelligence. Its 131K-token context window is larger than 48% of the models we list. At $0.40 per million input tokens it is cheaper than 38% of comparable models.

Position in the field
DFO score: ahead of 61% of models #291
Speed: faster than 25% of models #267
Price: cheaper than 38% of models #467
Context: larger than 48% of models #389
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Qwen: Qwen3 VL 235B A22B Thinking $0.40 in $4.00 out
Anthropic: Claude Fable 5.2 $8.00 in $40.00 out
Google: Gemini 4 Carbon $2.00 in $10.00 out
Google: Gemini 4 Argon $2.00 in $10.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens
Qwen: Qwen3 VL 235B A22B Thinking 131K

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.40 $0.000400
Output $4.00 $0.004000

What would Qwen: Qwen3 VL 235B A22B Thinking cost your business?

Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.

A website chatbot handling around 100 customer conversations a day, a few short messages each.

3,000
One request is one message, email, draft or automation call.
1,200 tokens

$5.33/mo Qwen: Qwen3 VL 235B A22B Thinking $0.0018 per request
$63.36/mo Anthropic: Claude Fable 5.2 $0.02 per request
$15.84/mo Google: Gemini 4 Carbon · best value $0.0053 per request

Full calculator with 749 models → Price Calculator

DFO AI AUTOMATION

These numbers get smaller with the right architecture.

We route routine calls to cheap models and save Qwen: Qwen3 VL 235B A22B Thinking for the hard ones. Most clients cut their estimate by 60-80%.

Talk to our team

About Qwen: Qwen3 VL 235B A22B Thinking

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math..

Frequently asked questions about Qwen: Qwen3 VL 235B A22B Thinking

How much does Qwen: Qwen3 VL 235B A22B Thinking cost?

Qwen: Qwen3 VL 235B A22B Thinking costs $0.40 per million input tokens and $4.00 per million output tokens.

What is the context window of Qwen: Qwen3 VL 235B A22B Thinking?

Qwen: Qwen3 VL 235B A22B Thinking has a context window of 131,072 tokens (131K).

What can Qwen: Qwen3 VL 235B A22B Thinking do?

Qwen: Qwen3 VL 235B A22B Thinking supports image/vision input, tool use, and function calling.

Who created Qwen: Qwen3 VL 235B A22B Thinking?

Qwen: Qwen3 VL 235B A22B Thinking is developed by Qwen and was released on September 23, 2025.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.