supermarket

Language

Qwen3-32B

By Alibaba Group, in the Qwen family.

Released
29 Apr 2025
Status
Legacy
Context
131.1K
Max output
8.2K
Input per 1M tokens
$0.16
Output per 1M tokens
$0.64
Open weights
Yes
License
apache-2.0
Parameters
32B
Knowledge cutoff
—
Reasoning
Yes
Modalities
text → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning10.2942 of 4
Coding & software engineering40.0Not ranked1 of 5
Human preference42.4Not ranked1 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Chess PuzzlesPuzzles solved5.0%Independent—28 Aug 2026Epoch AI
Chess PuzzlesPuzzles solved1.0%Independentnone28 Aug 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)67.5%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.1728Third party——https://conceptualreasoning.ai/lmca via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy65.7%Independent—28 Aug 2026Epoch AI
GPQA DiamondAccuracy54.1%Independentnone30 Aug 2026Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
OTIS Mock AIME 2024-2025Accuracy66.9%Independent—30 Aug 2026Epoch AI
OTIS Mock AIME 2024-2025Accuracy23.1%Independentnone30 Aug 2026Epoch AI

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Aider PolyglotPercent correct40.0%Third party——https://aider.chat/docs/leaderboards/ via Epoch AI

Long context

Long context results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Fiction.LiveBench% correct at 16K tokens (Epoch's column)74.2%Third party——Fiction.live leaderboard via Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1347Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes3926Independent—25 Sep 2026Arena

Other Qwen versions

Sources