Qwen3 8B
Alibaba · 2 thinking configurations
Intelligence6.0
Input / 1M$0.18
Output / 1M$0.70
Context32.8K
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 none · Click a point to switch configuration
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
6.0 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
45.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
1.9 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
24.9 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
28.6 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
11.1 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputNo
Speed43.4 tok/s
First token3.82 s
Maximum output8.2K
Catalog listing date2025-04-28