Qwen3 Coder 480B
Alibaba · 1 configuration
Intelligence11.9
Input / 1M$1.50
Output / 1M$7.50
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 · 0 without both values
Selected: thinking default · Click a point to switch configuration
Qwen coding model for software agents, repository edits, and code reasoning
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
11.9 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
61.8 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
4.5 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
43.6 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
40.5 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
15.7 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
Speed53.7 tok/s
First token3.14 s
Maximum output65.5K
Catalog listing date2026-03-17