0

Qwen3 32B

Open weights

Alibaba's mid-tier dense Qwen3 model - 32B parameters with hybrid thinking modes, the largest of the dense Qwen3 lineup.

Open
Publisher
Alibaba
Family
Qwen
Params
32B
Context
131K
Input
Output
Providers
togetherfireworksollamaself-host
License
Apache-2.0
Released
28 Apr 2025
Canonical
qwenlm.github.io/blog/qwen3

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →
Context
131K
Input
$0.15
/1M tok
Output
$0.59
/1M tok
Blended
$0.26
#223/ 414/1M · 3:1
Speed
98
#107/ 414tok/s

Price & speed via Artificial Analysis · ranked across tracked models

Reported on 16 evals across 8 domains - best 86.9% on MATH-500 · #66 of 178

Reported eval scores

16
Simple Bench20
Simple Bench20
AIME 2024: Problems from the American Invitational Mathematics Examination30.3
MATH-50086.9
MMLU-Pro72.7
Arena-Hard53.3
Humanity's Last Exam (HLE)4.3
GPQA Diamond53.5
SciCode28
GPQA (Full Set)65.8
τ²-bench (Tau²-bench)29.8
Aider Polyglot Benchmark40
LiveCodeBench28.8
Terminal-Bench (Hard)3
IFBench31.5
AIME 2025: Problems from the American Invitational Mathematics Examination19.7