AIsaAIsaStudio 中文 Open AIsa Studio

Alibaba launches Qwen4 Max with 9-point gain over Qwen3.8 Max on Artificial Analysis Intelligence Index

Original title: Alibaba has launched Qwen4 Max, gaining 9 points over Qwen3.8 Max on the Artificial Analysis Intelli…

Alibaba has launched Qwen4 Max, scoring 43 on the Artificial Analysis Intelligence Index (xhigh reasoning effort), 9 points above Qwen3.8 Max and 3 points below Kimi K3.1 Pro at ~11% lower cost per task. It uses ~105k output tokens per task versus ~171k for Qwen3.8 Max, reaches 1686 Elo on AA-Briefcase, and trails Kimi K3.1 Pro on Terminal-Bench 4.0 (48% vs 67%). It offers a 1M token context window, text-and-image input, and pricing of $1.50/$4.50 per 1M input/output tokens on Alibaba's first-party APIs.

Why it matters

An independent benchmark team provides item-by-item comparisons of Qwen4 Max against Qwen3.8 Max and Kimi K3.1 Pro, along with pricing details for cost-effectiveness assessment.

Read the original ↗AI Daily, Nov 16

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Other coverage 5