Qwen3.5 35B A3B
Alibaba · 2 thinking configurations
Intelligence19.3
Input / 1M$0.25
Output / 1M$2.00
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 cost2 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
19.3 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
84.5 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
21.0 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
89.2 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
72.5 %MMMU-ProMultimodal understanding of academic problems that include images.
72.7 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
20.1 %Specifications from the catalog
Inputtext, image, video
Outputtext
Tool callingYes
Structured outputYes
Speed145.2 tok/s
First token2.12 s
Maximum output65.5K
Catalog listing date2026-02-25