Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...
Tested on 11 benchmarks with 70.9% average. Top scores: LiveBench — Mathematics (83.7%), LiveBench — Coding (78.2%), LiveBench — Reasoning (75.8%).
Step 3.5 Flash scores 89.5 (101% as good) at $0.10/1M input · 69% cheaper
Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.
LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.
Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.
Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.
Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.
vs GPT-5 Chat
vs DeepSeek R1 Distill Qwen 14B
vs Step 3.5 Flash- Typemultimodal
- Context1.0M tokens (~500 books)
- ReleasedApr 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.003
Alibaba Qwen$0.33