Language modelActive

Qwen 3 14B

Alibaba

Released: April 27, 2025
Data date: September 8, 2026

Speed: 59 tokens/s
Output throughput
Price: $0.12 · $0.24
Input · Output / 1M tokens
Input: Text
Output: Text

Qwen 3 14B brings the dense Qwen3 setup down to 14.8 billion parameters while retaining switchable Thinking. It can produce additional reasoning steps or answer directly.

Its 40 layers use grouped-query attention with 40 Q heads and 8 KV heads. Qwen lists 32,768 native context tokens and up to 131,072 tokens with YaRN.

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	API, LocalSource
Parameters	14.8BSource
Context window	32,768 tokensSource
Weights repository	Qwen/Qwen3-14BSource
License	Apache-2.0Source
Architecture	Qwen3 causal language model; dense or sparse MoESource
Input	TextSource
Output	TextSource
Reasoning mode	base checkpoint; report evaluates pre-training onlySource
Tool calling	NoSource
Structured output	NoSource
Native context window	32,768 tokensSource
Maximum context window	131,072 tokensSource
Parameters	14.8 BSource
Languages	119 languages and dialectsSource
Repository created	2025-04-27 (Repository creation date is a precise publication proxy, but may differ from the public announcement date or an individual checkpoint's first availability.)Source
Training tokens	36 trillionSource

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

MMLU (Show measurement, test conditions, and source)

Source value: 81.05
Score: 81.05
Metric: percent
Unit: %
Category: knowledge
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

MMLU-Redux (Show measurement, test conditions, and source)

Source value: 79.88
Score: 79.88
Metric: percent
Unit: %
Category: knowledge
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

MMLU-Pro (Show measurement, test conditions, and source)

Source value: 61.03
Score: 61.03
Metric: percent
Unit: %
Category: knowledge
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

SuperGPQA (Show measurement, test conditions, and source)

Source value: 34.27
Score: 34.27
Metric: percent
Unit: %
Category: knowledge
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

BBH (Show measurement, test conditions, and source)

Source value: 81.07
Score: 81.07
Metric: percent
Unit: %
Category: knowledge
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

GPQA (Show measurement, test conditions, and source)

Source value: 39.9
Score: 39.9
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

GSM8K (Show measurement, test conditions, and source)

Source value: 92.49
Score: 92.49
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

MATH (Show measurement, test conditions, and source)

Source value: 62.02
Score: 62.02
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

EvalPlus (Show measurement, test conditions, and source)

Source value: 72.23
Score: 72.23
Metric: percent
Unit: %
Category: coding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

MultiPL-E (Show measurement, test conditions, and source)

Source value: 61.69
Score: 61.69
Metric: percent
Unit: %
Category: coding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

MBPP (Show measurement, test conditions, and source)

Source value: 73.4
Score: 73.4
Metric: percent
Unit: %
Category: coding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

CRUX-O (Show measurement, test conditions, and source)

Source value: 68.6
Score: 68.6
Metric: percent
Unit: %
Category: coding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3 Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official Qwen3 base-model evaluation; benchmark protocol in report table notes

Source Qwen3 Technical Report

Page 1 of 2

Sources and data date

Type	Evidence and data date
Speed	Alibaba, Non-reasoning. Output speed after the first streaming chunk, not total response time. Classified as deprecated by Artificial Analysis. Artificial Analysis maintains only the default 10K-input workload there. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · Qwen3-14B model card · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · Qwen3-14B model card · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	active-parameters-billions Original wording Dense checkpoint; no separate activated-parameter count is applicable/published.
Additional source	Qwen3 Technical Report (retrieved September 8, 2026) · Qwen3 Technical Report · Editorial description reviewed October 2, 2026
Additional source	Model metadata (retrieved September 8, 2026)
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0

Qwen 3 14B

Specifications and access

Measurements without matching peer values

Our tests

Pelican on a bicycle

Popularity

Published prices

Sources and data date