Qwen3.8 27B
Alibaba · 4 thinking configurations
Intelligence27.6
Input / 1M$0.50
Output / 1M$3.00
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 cost4 measured configurations · 0 without both values
Selected: thinking medium · Click a point to switch configuration
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
27.6 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.
14.1 %SciCodeCode generation for scientific research problems.
39.0 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
65.2 %MMMU-ProMultimodal understanding of academic problems that include images.
74.2 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
18.4 %Specifications from the catalog
Inputtext, image, video
Outputtext
Tool callingYes
Structured outputYes
Speed48.9 tok/s
First token3.88 s
Maximum output131.1K
Catalog listing date2026-08-14