Qwen3-Max-Preview
Qwen3-Max-Preview shows substantial gains over the 2.5 series in overall capability, with significant enhancements in Chinese-English text understanding, complex instruction following, handling of subjective open-ended tasks, multilingual ability, and tool invocation; model knowledge hallucinations are reduced.
Parameter controls available:
1. Thinking Mode
- Enable thinking about the response before giving a final answer: toggle it `on`, otherwise it is `off` by default.
2. Code Interpreter
- Toggle it `on` to enable code interpreter. It is `off` by default.
- Lets the model write and execute Python code for calculations, data analysis, and visualizations
Powered by a server managed by @empiriolabsai. Learn more
Build with Qwen3-Max-Preview using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from EmpirioLabs AI
Qwen3.7-Max
Qwen3.5-4B-EL
Qwen3.5-9B-EL
Gemma-4-26B-A4B-EL
DeepSeek-V4-Pro-E
DeepSeek-V4-Flash-E
DeepSeek-V4-Pro-EL
DeepSeek-V4-Flash-EL
HappyHorse-1.0-EL
MiMo-V2.5