Qwen3 VL 30B A3B
Alibaba · 2 thinking configurations
Intelligence9.5
Input / 1M$0.20
Output / 1M$2.40
Context256K
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
Qwen vision-language model for visual reasoning, documents, and agent tasks
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
9.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
72.0 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
8.9 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
19.9 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
45.1 %MMMU-ProMultimodal understanding of academic problems that include images.
61.8 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
16.9 %Specifications from the catalog
Inputtext, image
Outputtext
Tool callingYes
Structured outputNot available
Speed113.7 tok/s
First token2.20 s
Maximum output32.8K
Catalog listing date2025-04