Qwen3 Next 80B A3B
Alibaba · 2 thinking configurations
Intelligence11.2
Input / 1M$0.15
Output / 1M$1.20
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
Efficient Qwen thinking model for local reasoning, math, and coding agents
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
11.2 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
75.9 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
12.6 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
6.7 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
41.5 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
60.7 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
19.0 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputNot available
Speed172.0 tok/s
First token2.41 s
Maximum output32.8K
Catalog listing date2025-09