supermarket

Language

Qwen3-4B-Instruct-2507

By Alibaba Group, in the Qwen family.

Released
6 Aug 2025
Status
Legacy
Context
262.1K
Max output
—
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
Yes
License
apache-2.0
Parameters
4B
Knowledge cutoff
—
Reasoning
No
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 & reasoning0.0Not ranked1 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 solved4.0%Independent—28 Aug 2026Epoch AI
MMLU-ProAccuracy69.6%Self-reported——Model Card via Hugging Face Community Evals

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy45.8%Independent—28 Aug 2026Epoch AI
GPQA DiamondAccuracy62.0%Self-reported——Model Card via Hugging Face Community Evals

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
OTIS Mock AIME 2024-2025Accuracy52.2%Independent—28 Aug 2026Epoch AI

Other Qwen versions

Sources