The PolyglotsStrict ZDR Verified

Alibaba

Name: ARMES
Availability: InStock
Author: ARMES

Multilingual mastery and agentic coding.

Run Alibaba in ARMES

Laboratory Overview

Alibaba's Qwen lab produces the premier multilingual and open-weight models in the world. With models like Qwen 3.8 and Qwen 3.6 Max, Alibaba leads across polyglot reasoning, coding, and mathematical benchmarks.

Core Research Focus:Multilingual masteryagentic codingopen-innovationmulti-modal reasoningcross-language code generation.

Privacy & Zero Data Retention

Strict Zero Data Retention (ZDR): Requests are processed ephemerally in RAM. No user data, prompts, or completions are stored, indexed, or used for model training.

No user telemetry sent to Alibaba

Alibaba Foundation Models (1)

Available under ARMES unified subscription without separate API keys or billing agreements.

Tier:

Mixture of Experts (MoE)

MoEEco

Qwen 3.8-2.4t-a95b

Terminal-Bench 2.1: 86.6% (vendor) / 81.3% (AA independent), SWE-bench Pro: 67.7%, DeepSWE 1.1: 56.6%, PaperBench: 93.0% (#1), GPQA Diamond: 92.6%, FrontierSWE: 73.5%, OSWorld-Verified: 86.1%, OmniDocBench 1.5: 92.1%, IFBench: 82.8%, HLE: 43.6%, JobBench: 53.4% | Alibaba's most capable model and the first Qwen-Max released as open weights (GA Aug 3, 2026; open weights Aug 12, 2026).

1M ctx

$2.00 / $6.00 /MTok

Intelligence Dossier Try in Chat

Explore Other AI Labs on ARMES

Compare models across the 21+ leading laboratories unified in your workspace.

xAI

Back to all AI Labs & Models