// COMPARISON

Qwen3-32B

A head-to-head benchmark comparison of Qwen3-32B across 26 evaluations.

The models

Language Open (Restricted)
Params
32.8B
Context
β€”
Released
Apr 2025

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon .

Full Qwen3-32B specs β†’

Benchmark comparison

Benchmark Qwen3-32B
code
Codeforces Elo 1,977
LiveCodeBench v5 65.7%
LiveCodeBench v6 60.1%
general
AlignBench v1.1 8.72
ArenaHard 93.8%
C-Eval 87.3%
Creative Writing v3 81
IFEval 85%
LiveBench 74.9
MMLU-Pro 80%
MMLU-Redux 90.9%
MMMLU 80.6%
Multi-IF 73
WritingBench 7.9
knowledge
INCLUDE 73.7
math
AIME 2024 81.4%
AIME 2025 73.33%
HMMT February 2025 50.4%
MATH-500 97.2%
MT-AIME 2024 75
PolyMath-en 47.4
reasoning
AutoLogi 87.3
GPQA Diamond 69.7%
MLogiQA 76.3
ZebraLogic 88.8%
tool-use
BFCL v3 70.3%

Best result per row highlighted in cyan. Each benchmark links to its definition and sources; each model links to its full scorecard.

Frequently asked questions

Which of these models is best for coding? β–Ά

Qwen3-32B has the strongest result on Codeforces Elo among the models compared here. See the code-category rows in the table for the full picture.

How many benchmarks are compared? β–Ά

This comparison covers 26 benchmarks on which at least one of the selected models has a published score.

Where do the benchmark scores come from? β–Ά

Scores are aggregated from official model cards, technical reports and standard public evaluations, and link back to each benchmark's source. They are updated as new results are published.

Explore further

Build a different comparison

Models (0 selected)

Benchmarks (auto)

Select at least two models.