Qwen3 32B

Alibaba / Qwen Team · qwen/qwen3-32b

ProviderAlibaba / Qwen Team
Familyqwen
Typellm-reasoning
Statusactive
Released2025-04
Updated2025-04

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
Aider Polyglot Benchmarkunassessed40.0
AlpacaEvalunassessed38.2
Arena Elo — Codingunassessed1320.0
Arena Elo — Hard Promptsunassessed1367.6
Arena Elo — Mathunassessed1330.0
Arena Elo — Overall (Text)unassessed1310.0
Arena Elo — Style Controlunassessed1347.0
Artificial Analysis Intelligence Indexunassessed76.0
Artificial Analysis Output Speedunassessed70.0
BIG-Bench Hardunassessed62.8
GPQA Diamondunassessed62.5
HumanEvalunassessed85.2
IFEvalunassessed84.0
LiveCodeBenchunassessed54.6
MATH-500unassessed88.5
MMLU-Prounassessed74.8
MT-Benchunassessed8.5
MultiPL-E: C#unassessed78.2
MultiPL-E: Juliaunassessed59.2
MultiPL-E: Kotlin (unconfirmed)unassessed70.5
MultiPL-E: Luaunassessed53.5
MultiPL-E: Perlunassessed48.5
MultiPL-E: PHPunassessed75.8
MultiPL-E: Runassessed55.5
MultiPL-E: Rubyunassessed63.5
MultiPL-E: Scalaunassessed58.2
MultiPL-E: Swiftunassessed63.8
MuSRunassessed30.1
WildBenchunassessed65.5

Data

This card as JSON · Edit on GitHub