Qwen 3 32b

Qwen 3 32b is a 32b model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.

Vision by description
Native PDF input

Model weights

Pricing

Auto routing · per 1M tokens

Input: $0.080
Output: $0.24

Compare provider prices

Specifications

Context window: 41K
Max output: 32.8K
Parameters: 32B
Avg output (7d): 324 tokens; Longer than 28% of models

Benchmarks

Artificial Analysis

LMArena

Vectara

Sourced from Artificial Analysis.

Intelligence Index

7.3

Better than 24% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

0.0%

Better than 6% of models compared

Reasoning

HLE

Humanity's Last Exam

4.1%

Better than 14% of models compared

IFBench

Instruction-following benchmark

31.5%

Better than 17% of models compared

Coding

LiveCodeBench

Contamination-free coding benchmark

28.8%

Better than 32% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

19.7%

Better than 22% of models compared

AIME

American Invitational Mathematics Examination

30.3%

Better than 58% of models compared

Math-500

Diverse mathematical problem solving benchmark

86.9%

Better than 56% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

72.7%

Better than 42% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

53.5%

Better than 27% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation