Alibaba

Qwen3.5 397B A17B

Name: Alibaba Qwen3.5 397B A17B
Author: Alibaba

Compare

Model ID:qwen/qwen3.5-397b-a17b

2026-02-16

Compare

Qwen3.5 397B-A17B is Alibaba's flagship open-weight language model, featuring 397 billion total parameters with 512 Mixture-of-Experts activating just 17 billion per token. Released in February 2026, it supports 201 languages and a 256K-token context window, with multi-token prediction for accelerated inference. The model delivers state-of-the-art performance across language understanding, logical reasoning, code generation, and GUI interactions, while being 60% cheaper to run than its predecessor and 8× more capable at handling large concurrent workloads.

API|VisionReasoning|Open ModelApache 2.0

Knowledge Cutoff

2026-02-01

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory

262KIN66KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words

$0.39IN$2.34OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

Calculate Cost

Source:Official Docs OpenRouter

AI Performance Evaluation

Arena Overall Score

1447

±5

As of 2026-05-01

Overall Rank

No.47

21,382 Votes

Arena by Ability

Hard Prompts

1464±6No.46

Expert Knowledge

1469±14No.45

Instruction Following

1428±8No.53

Conversation Memory

1450±10No.48

Creative

1412±10No.49

Coding

1488±8No.52

Math

1447±15No.38

Arena by Occupation

Creative Writing

1426±9No.45

Social Sciences

1464±10No.44

Media

1405±10No.55

Business

1444±9No.49

Healthcare

1468±15No.46

Legal

1439±15No.66

Software

1482±7No.46

Mathematics

1458±17No.36

Source:Arena Intelligence

Overall

AA Intelligence Index

40%↑1%

Reasoning & Math

GPQA Diamond

86%↑4%

HLE

19%↑1%

Coding

AA Coding Index

37%↑1%

TAU2

84%↑3%

TerminalBench

36%↑2%

SciCode

41%↓1%

Language & Instructions

IFBench

52%↓11%

AA-LCR

58%↓4%

Output Speed

Standard Mode

53tok/s↓24

First Output 1.64s

Reasoning Mode

62tok/s↓24

First Output 52.44s

Source:Artificial Analysis

Alibaba