supermarket

Language

Qwen3-30B-A3B

By Alibaba Group, in the Qwen family.

Released
29 Apr 2025
Status
Legacy
Context
131.1K
Max output
8.2K
Input per 1M tokens
$0.20
Output per 1M tokens
$0.80
Open weights
Yes
License
apache-2.0
Parameters
30B, 3B active
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 & reasoning9.3982 of 4
Human preference39.6Not 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 solved4.0%Independent—30 Aug 2026Epoch AI
Chess PuzzlesPuzzles solved1.0%Independentnone30 Aug 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)60.3%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.1582Third party——https://conceptualreasoning.ai/lmca via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy61.7%Independent—30 Aug 2026Epoch AI
GPQA DiamondAccuracy50.4%Independentnone30 Aug 2026Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
OTIS Mock AIME 2024-2025Accuracy62.8%Independent—28 Aug 2026Epoch AI
OTIS Mock AIME 2024-2025Accuracy25.6%Independentnone30 Aug 2026Epoch AI

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
WeirdML (v2)Average accuracy29.8%Third party——WeirdML Leaderboard via Epoch AI

Long context

Long context results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Fiction.LiveBench% correct at 16K tokens (Epoch's column)40.6%Third party——Fiction.live leaderboard via Epoch AI

Writing

Writing results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
LLM Creative Story-Writing Benchmark V1 (Lech Mazur)Mean rubric score (percent of the 10-point scale)75.3%Third party——lechmazur/writing Github repository via Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1327Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes26041Independent—25 Sep 2026Arena

Other Qwen versions

Sources