Qwen3.6-Max-Preview
Released
Qwen3.6-Max-Preview is an AI model released by Qwen on Tuesday, Apr 14 2026, 12 days after Qwen3.6-Plus. It has a 256k token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover NL2Repo-Bench, and Terminal-Bench 2.0.
Get Qwen releases and AI news.
Every other Monday
Benchmarks
Coding
Terminal & CLI
Compare Qwen3.6-Max-Preview with
Suggested comparisons
Qwen3.6-Max-PreviewvsQwen4-MaxQwen3.6-Max-PreviewvsGPT-6.2 AstraQwen3.6-Max-PreviewvsClaude Fable 5.2Qwen3.6-Max-PreviewvsGemini 4 NeonQwen3.6-Max-PreviewvsMuse EmberQwen3.6-Max-PreviewvsGrok 4.7Qwen3.6-Max-PreviewvsDeepSeek-V4.1-Flash-1017Qwen3.6-Max-PreviewvsMistral Large 4Qwen3.6-Max-PreviewvsKimi K3.1 ProQwen3.6-Max-PreviewvsGLM-5.3-FlashQwen3.6-Max-PreviewvsNemotron 3.5 Bolt E4B 4GBAbout
Alibaba Cloud listed Qwen3.6-Max-Preview on April 14, 2026 as a hosted text-only preview. Qwen's April 18 write-up presented it as an upgrade over Qwen3.6-Plus for coding agents, instruction following and less common factual questions.
The preview scored 65.4 on Terminal-Bench 2.0 and 42.9 on NL2Repo in the launch chart. It was a separate preview checkpoint before the Qwen3.7 generation.
Frequently asked questions
Qwen3.6-Max-Preview was released by Qwen on Tuesday, Apr 14 2026.