Alibaba Launches Qwen4 Max, Scoring 43 on Intelligence Index at $3.27 per Task

Alibaba launched Qwen4 Max, which scores 43 on the Artificial Analysis Intelligence Index, 9 points above Qwen3.8 Max and 3 points behind Kimi K3.1 Pro. The model costs $3.27 per Intelligence Index task, about 3x less than Qwen3.8 Max and 11% less than Kimi K3.1 Pro, and uses 39% fewer output tokens per task. Qwen4 Max 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.
Event version 1.
Key insights
Intelligence Index score
Qwen4 Max scores 43 on the Artificial Analysis Intelligence Index using xhigh reasoning effort, 9 points ahead of Qwen3.8 Max (34) and 3 points behind Kimi K3.1 Pro (46).
Cost per task
Qwen4 Max costs $3.27 per Intelligence Index task, about 3x less than Qwen3.8 Max ($10.02) and about 11% less than Kimi K3.1 Pro ($3.68). Tencent Hy4 costs about $1.03 per task but scores 8 points lower.
Token efficiency
Qwen4 Max uses about 105k output tokens per Intelligence Index task, 39% fewer than Qwen3.8 Max at about 171k, compared with about 72k for Kimi K3.1 Pro and about 78k for Tencent Hy4.
Evaluation improvements
Qwen4 Max improves on every evaluation in the Index versus Qwen3.8 Max, including HLE-Diamond +21 points (24% to 45%), AA-Omniscience +18 points, AutomationBench-AA +17 points, CritPt v2 +13 points, Terminal-Bench-Science +11 points, Terminal-Bench 4.0 +9 points, GDP.pdf +3 points, FrontierCode 2.0 +3 points and AA-Briefcase +82 Elo.
Model details and pricing
Qwen4 Max has a 1M-token context window, accepts text and image input with text output, and is priced at $1.50/$4.50 per 1M input/output tokens on Alibaba's first-party APIs with a $0.075 cache hit price, lower than Qwen3.8 Max at $2.00/$6.00 with a $0.25 cache hit price.