Alibaba Group has released Qwen4-Max, a new 2.4-trillion-parameter sparse mixture-of-experts model. This model features native vision capabilities and a one-million-token context window. A key highlight is its reduced operational cost, with average task costs on the Work360 benchmark falling by 62% compared to its predecessor, Qwen3.8-Max. The architecture incorporates Qwen Sparse Attention and N-gram Embedding to enhance efficiency and long-context handling, making it suitable for complex, multi-step professional tasks across various domains. AI
IMPACT Sets a new standard for cost-efficient long-context processing, potentially accelerating adoption of AI agents in complex professional workflows.
RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]
- Alibaba Group
- Gated DeltaNet
- Gated Residual Networks with Dilated Convolutions for Monaural Speech Enhancement
- N-gram Embedding
- Qwen
- Qwen3.8-Max
- Qwen4
- qwen4-max
- Qwen Sparse Attention
- Work360
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →