Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d67, 15 pendingSources1,014

Qwen3.5 397B A17B

AlibabaReleased Feb 16, 2026Current

Score basis

Qwen3.5 397B A17B is strong in long context; capable in instruction following and multimodal tasks; and behind the leaders in coding, reasoning, and agentic tasks. Too few results yet to rate safety, math, multilingual tasks, or factuality.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Strong1 capability
  1. Long Context−9.0%2 of 3
Capable2 capabilities
  1. Instruction Following−14.0%2 of 3
  2. Multimodal−19.3%3 of 6
Limited3 capabilities
  1. Coding−28.8%8 of 10
  2. Reasoning−29.2%3 of 6
  3. Agentic−44.0%4 of 7
Not rated4 capabilities

Too few results yet to rate Safety, Math, Multilingual or Factuality.

Price

$0.60input$3.60outputper million tokens

From Alibaba's own price page · 7 providers tracked · All prices

Costs more than 64% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

163results on112benchmarks

  • 11 independently verified
  • 37 aggregator
  • 64 vendor-reported
  • 51 cross-referenced

From 16 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

8 papers reference Qwen3.5 397B A17B

Qwen3.5 397B A17B benchmark results

163 results on 112 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Long Context

StrongFull long context ranking

9.0% behind the leader2 of 3 ranked benchmarks measured

Show 3 more long context resultsHide 3 long context results

Instruction Following

CapableFull instruction following ranking

14.0% behind the leader2 of 3 ranked benchmarks measured

Show 4 more instruction following resultsHide 4 instruction following results

Multimodal

CapableFull multimodal ranking

19.3% behind the leader3 of 6 ranked benchmarks measured

Show 6 more multimodal resultsHide 6 multimodal results

Coding

LimitedFull coding ranking

28.8% behind the leader8 of 10 ranked benchmarks measured

Show 10 more coding resultsHide 10 coding results

Reasoning

LimitedFull reasoning ranking

29.2% behind the leader3 of 6 ranked benchmarks measured

Show 10 more reasoning resultsHide 10 reasoning results

Agentic

LimitedFull agentic ranking

44.0% behind the leader4 of 7 ranked benchmarks measured

Show 6 more agentic resultsHide 6 agentic results

Math

Not enough dataFull math ranking

0 of 5 ranked benchmarks measured

Show 9 more math resultsHide 9 math results

Factuality

Not enough dataFull factuality ranking

0 of 4 ranked benchmarks measured

Show 2 more factuality resultsHide 2 factuality results

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 79 more resultsHide 79 results

Qwen3.5 397B A17B: common questions

Who makes Qwen3.5 397B A17B?

Qwen3.5 397B A17B is made by Alibaba.

When was Qwen3.5 397B A17B released?

Qwen3.5 397B A17B was released on Feb 16, 2026, according to Artificial Analysis.

What is Qwen3.5 397B A17B good at?

Qwen3.5 397B A17B is strong in long context; capable in instruction following and multimodal tasks; and behind the leaders in coding, reasoning, and agentic tasks. Too few results yet to rate safety, math, multilingual tasks, or factuality.

How much does Qwen3.5 397B A17B cost?

Qwen3.5 397B A17B costs $0.60 per million input tokens and $3.60 per million output tokens, according to Alibaba's own price page. We track its price at 7 providers. At a mix of three input tokens to one output token, it costs more than 64% of the 330 priced models we track.

How many benchmarks has Qwen3.5 397B A17B been tested on?

We track 163 results for Qwen3.5 397B A17B on 112 benchmarks from 16 sources, 11 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Qwen3.5 397B A17B support?

OpenRouter lists tool calling, structured outputs, and reasoning for Qwen3.5 397B A17B.

About this record

Where Qwen3.5 397B A17B's numbers come from, and every name it appears under.

Tracked since
Apr 27, 2026
Newest source mention
Aug 23, 2026

Where the results come from

Verification: 163 scores · 11 independently verified · 37 aggregator-attributed · 51 vendor cross-reference · 64 vendor-reported. How these tiers are assigned

From 16 sources on 9 sites. Hugging Face supplies 69 of them; the 11 independently verified results come from 5 sites. Bars are coloured by trust tier.

  • huggingface.co69
  • artificialanalysis.ai38
  • api.llm-stats.com31
  • thinkingmachines.ai13
  • matharena.ai5
  • datasets-server.huggingface.co2
  • lmarena.ai2
  • mistral.ai2
  • epoch.ai1

Also known as

Qwen 3.5 397B 17Bqwen3-5-397b-a17bqwen3-5-397b-a17b-non-reasoningqwen3.5 397b a17b (non-reasoning)qwen3.5 397b a17b (reasoning)