qwen3-max-thinking
Qwen builds the Qwen3 Max Thinking model, a chat-based AI capable of extended thinking and structured output, with notable strengths in intelligence and general problem-solving as evidenced by its top 25% scores in the Intelligence Index, GPQA, and HLE benchmarks. Its context window of 256,000 tokens allows for complex and nuanced conversations.
Input
Output
Context
256K
Max Output
66K
Parameters
-
Technical Specifications
Model TypeChat
Context Window256,000 tokens
Max Output Tokens65,536 tokens
ParametersNot available
Release DateJan 25, 2026
Training CutoffNot available
Licenseproprietary
Open SourceNo
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
26.2%
HLE
66.0%
AA-LCR
86.1%
GPQA
83.6%
Tau2-Bench
70.7%
IFBench
43.1%
SciCode
31.7
Intelligence
24.2%
Terminal-Bench Hard
Resources & Links
proprietary, Proprietary - API access only
More Models by Qwen
qwen3-235b-a22b-thinking-2507262K context · 235B · Open weightsQwen 3 4B Thinking 2507262K context · 4B · Open weightsQwen 2.5 32B Instruct33K context · 32.8B · Open weightsQwen 2.5 14B Instruct AWQ33K context · 14.8B · Open weightsQwen 3 VL 8B Instruct262K context · 8.8B · Open weightsQwen 3.5 9B262K context · 9.7B · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 6, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.