DataLearner logoDataLearnerAI
Latest AI Insights
Model Leaderboards
Benchmarks
Model Directory
Model Comparison
Resource Center
Tools
LanguageEnglish
DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

Products

  • Leaderboards
  • Model comparison
  • Datasets

Resources

  • Tutorials
  • Editorial
  • Tool directory

Company

  • About
  • Privacy policy
  • Data methodology
  • Contact

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

Privacy policyTerms of service
Page navigation
目录
Model catalogQwen3.5-122B-A10B
QW

Qwen3.5-122B-A10B

推理大模型

Qwen3.5-122B-A10B

Release date: 2026-02-25更新于: 2026-03-08 21:06:20720
Live demoGitHubHugging FaceCompare
Parameters
1220.0亿
Context length
262K
Chinese support
Supported
Reasoning ability

Qwen3.5-122B-A10B is an AI model published by 阿里巴巴, released on 2026-02-25, for 推理大模型, with 1220.0B parameters, and 262K tokens context length, under the Qwen License license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen3.5-122B-A10B

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking Level · Extended (Default)Standard Mode
Context length
262K tokens
Max output length
4096 tokens
Model type
推理大模型
Release date
2026-02-25
Model file size
No data
MoE architecture
Yes
Total params / Active params
1220.0B / 100B
Knowledge cutoff
No data
Qwen3.5-122B-A10B

Open source & experience

Code license
Qwen License
Weights license
Qwen License- 免费商用授权
GitHub repo
GitHub link unavailable
Hugging Face
https://huggingface.co/Qwen/Qwen3.5-122B-A10B
Live demo
No live demo
Qwen3.5-122B-A10B

Official resources

Paper
No paper available
DataLearnerAI blog
No blog post yet
Qwen3.5-122B-A10B

API details

API speed
No data
No public API pricing yet.
Qwen3.5-122B-A10B

Benchmark Results

Qwen3.5-122B-A10B currently shows benchmark results led by Pinch Bench (14 / 37, score 85.50), Claw Bench (14 / 27, score 86). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
All modesThinking

OpenClaw智能体能力综合测评

2 evaluations
Benchmark / mode
Score
Rank/total
Claw Bench
Thinking ModeTools
86
14 / 27
Pinch Bench
Thinking ModeTools
85.50
14 / 37
View benchmark analysisCompare with other models
Qwen3.5-122B-A10B

Publisher

阿里巴巴
阿里巴巴
View publisher details
Qwen3.5-122B-A10B

Model Overview

Qwen3.5-122B-A10B是阿里云于2026年2月25日推出的Qwen3.5系列开源模型之一[citation:2][citation:3]。该模型采用混合专家(MoE)架构,拥有1220亿的总参数量,推理时仅激活100亿参数,旨在以适中的计算成本拉近中小模型与顶尖闭源模型在复杂任务上的性能差距[citation:1][citation:8]。

作为一款综合能力突出的原生多模态模型,Qwen3.5-122B-A10B支持文本、图像和视频输入,能够解析长达2小时的视频内容[citation:5]。它在多模态理解、复杂智能体任务(如多步推理、工具调用、跨应用操作)以及多语言处理方面表现优异[citation:2][citation:8]。在专业领域知识、多语言任务等多项评测中,该模型均取得了领先分数[citation:2]。

开发者可通过Hugging Face、GitHub或魔搭社区获取模型权重,进行研究与微调[citation:8]。其强大的多模态理解和推理能力,使其适用于视频内容分析、高级视觉问答和复杂的自动化流程控制等场景。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信,获得最新 AI 技术推送

DataLearner 官方微信二维码