Qwen3 Max (Preview)
Alibaba · 1 configuration
Intelligence12.6
Input / 1M$1.20
Output / 1M$6.00
Context262.1K
Tariff: Alibaba · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 0 without both values
Selected: thinking max · Click a point to switch configuration
Flagship Qwen model for complex reasoning, coding, and agentic workflows
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
12.6 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
76.4 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
10.1 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
32.7 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
48.0 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
24.2 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputNo
Speed55.9 tok/s
First token4.09 s
Maximum output32K
Catalog listing date2025-01-01