Qwen: Qwen3.5 397B A17B

qwen · Released Feb 16, 2026
DFO score #136 / 749
20.1 leaderboard score
Speed #264 / 355
58.7 tok/s
Input Price #485 / 749
$0.450 per 1M tokens
Output Price #548 / 749
$3.00 per 1M tokens
Context #208 / 749
262,144 tokens

Analysis Summary

Qwen3.5 397B A17B combines a strong coding result with tool use, function calling, vision, and video input. Its 262K-token context supports substantial code or document review, and its listed prices are relatively low. The measured profile is uneven: coding is a clear strength, while general reasoning and agentic performance are considerably weaker.

That makes it a potential cost-conscious specialist for coding assistance and multimodal tasks, rather than a reliable all-purpose agent. Teams should test its performance on their own repositories and require review for code changes or tool-driven actions. It may be useful when the work is well-scoped and cost matters, but the lower reasoning and agentic results argue against using it as the sole model for high-stakes client analysis or unattended automation.

Assessed September 23, 2026

Editorial notes

Qwen3.5 397B A17B has a strong coding result for its tier, plus vision, video input, tool use, and a 262K-token context; its overall reasoning and agentic results are weaker.

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

Qwen3.5 397B A17B has a strong coding result for its tier, plus vision, video input, tool use, and a 262K-token context; its overall reasoning and agentic results are weaker.

#136 of 749 overall Down 6 this week

Benchmarks

Intelligence Index 13.7 #136 of 454 · Artificial Analysis
Coding Index 30.8 #73 of 199 · Artificial Analysis
Agentic Index 5.3 #106 of 181 · Artificial Analysis
Creative Writing Not rated Arena rating
Instruction Following 1,434 #32 of 35 · Arena rating

Artificial Analysis data refreshed Nov 16, 2026. Arena ratings from the Nov 9, 2026 text leaderboard, with style control.

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

How Qwen: Qwen3.5 397B A17B compares

Qwen: Qwen3.5 397B A17B ranks #136 of 454 AI models we track for overall intelligence, #73 of 199 for coding, #106 of 181 for agentic tasks. Its 262K-token context window is larger than 72% of the models we list. At $0.45 per million input tokens it is cheaper than 35% of comparable models.

Position in the field
DFO score: ahead of 82% of models #136
Speed: faster than 26% of models #264
Price: cheaper than 35% of models #485
Context: larger than 72% of models #208
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Qwen: Qwen3.5 397B A17B $0.45 in $3.00 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

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 $0.45 $0.000450
Output $3.00 $0.003000

What would Qwen: Qwen3.5 397B A17B 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

$4.37/mo Qwen: Qwen3.5 397B A17B $0.0015 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: Qwen3.5 397B A17B for the hard ones. Most clients cut their estimate by 60-80%.

Talk to our team

About Qwen: Qwen3.5 397B A17B

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers..

Frequently asked questions about Qwen: Qwen3.5 397B A17B

How much does Qwen: Qwen3.5 397B A17B cost?

Qwen: Qwen3.5 397B A17B costs $0.45 per million input tokens and $3.00 per million output tokens.

What is the context window of Qwen: Qwen3.5 397B A17B?

Qwen: Qwen3.5 397B A17B has a context window of 262,144 tokens (262K).

Is Qwen: Qwen3.5 397B A17B good for coding?

On our coding benchmark index, Qwen: Qwen3.5 397B A17B ranks #73 of 199 models, placing it in the broader range of the field for code generation and debugging.

What can Qwen: Qwen3.5 397B A17B do?

Qwen: Qwen3.5 397B A17B supports image/vision input, tool use, and function calling.

Who created Qwen: Qwen3.5 397B A17B?

Qwen: Qwen3.5 397B A17B is developed by Qwen and was released on February 16, 2026.

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