Alibaba's Qwen3.7-Max achieves 56.6 on AI Index, improving reasoning and coding

Alibaba's Qwen team has released Qwen3.7-Max, achieving a score of 56.6 on the Artificial Analysis Intelligence Index. This represents a 4.8-point improvement over its previous preview version. The new model demonstrates enhanced capabilities in scientific reasoning, agentic tasks, coding, and reduced hallucination. AI

Summary written by gemini-2.5-flash-lite from 1 sources. How we write summaries →

IMPACT Sets new SOTA on the Artificial Analysis Intelligence Index, signaling advancements in reasoning and agentic capabilities.

RANK_REASON Frontier-lab model release with benchmark score. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on X — Qwen (Alibaba) →

• Alibaba
• Artificial Analysis Intelligence Index
• Qwen
• Qwen3.6-Max-Preview
• Qwen3.7-Max

• model release
• paper