supermarket

Language

Qwen3-30B-A3B-Thinking-2507

By Alibaba Group, in the Qwen family.

Released
31 Jul 2025
Status
Legacy
Context
262.1K
Max output
32.8K
Input per 1M tokens
—
Output per 1M tokens
—
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 & reasoning13.1912 of 4

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 solved8.0%Independent—30 Aug 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)69.3%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.1953Third party——https://conceptualreasoning.ai/lmca via Epoch AI
MMLU-ProAccuracy80.9%Self-reported——EvalEval via Hugging Face Community Evals

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy70.1%Independent—30 Aug 2026Epoch AI
GPQA DiamondAccuracy72.2%Self-reported——EvalEval via Hugging Face Community Evals

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
OTIS Mock AIME 2024-2025Accuracy70.3%Independent—30 Aug 2026Epoch AI

Other Qwen versions

Sources