Qwen3.7 Max
Alibaba · 1 configuration
Intelligence29.5
Input / 1M$2.50
Output / 1M$7.50
Context1M
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
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
29.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
92.3 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
40.5 %SciCodeCode generation for scientific research problems.
49.5 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
74.5 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
94.7 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
80.5 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
31.1 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
Speed202.6 tok/s
First token2.28 s
Maximum output131.1K
Catalog listing date2026-05-21