Qwen3.5 9B
Alibaba · 2 thinking configurations
Intelligence13.3
Input / 1M$0.17
Output / 1M$0.25
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 · 1 without both values
Selected: thinking none · Click a point to switch configuration
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
13.3 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
78.6 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
9.4 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
21.3 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
85.1 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
37.8 %MMMU-ProMultimodal understanding of academic problems that include images.
66.8 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
14.0 %Specifications from the catalog
Inputtext, image, video
Outputtext
Tool callingYes
Structured outputYes
SpeedNot available
First tokenNot available
Maximum output32.8K
Catalog listing date2026-03-10