This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Alibaba has launched a newer release, Qwen3 30B A3B 2507 (Reasoning). We suggest considering it instead.

Alibaba

•

Qwen3 32B

•

Open weights model

•

Released April 2025

Qwen3 32B (Reasoning) Intelligence, Performance & Price Analysis

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Try it out API Provider Benchmarks

Cost

In $0.24Out $0.54

N/A

Cost per Intelligence Index task

Verbosity

N/A

Output tokens from Intelligence Index

Qwen3 32B (Reasoning) is below average in intelligence and particularly expensive when comparing to other open weight models of similar size. The model supports text input, outputs text, and has a 33k tokens context window.

Qwen3 32B (Reasoning) scores 7 on the Artificial Analysis Intelligence Index, placing it below average among comparable models (median: 8).

Pricing for Qwen3 32B (Reasoning) is $0.24 per 1M input tokens (somewhat expensive, median: $0.12) and $0.54 per 1M output tokens (somewhat expensive, median: $0.25).

At 27 tokens per second, Qwen3 32B (Reasoning) is notably slow (73).

Reasoning	Yes This page shows the reasoning version of this model. A non-reasoning variant may also exist.
Input modality	Supports: text
Output modality	Supports: text
Context window	33k ~49 A4 pages of size 12 Arial font
Total parameters	32.8B
License	Apache 2.0
Model weights	Hugging Face

Metrics are compared against models of the same class:

Non-reasoning models → compared only with other non-reasoning models
Reasoning models → compared across both reasoning and non-reasoning
Open weights models → compared only with other open weights models of the same size class:

Tiny: ≤4B parameters
Small: 4B–40B parameters
Medium: 40B–150B parameters
Large: >150B parameters

Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:

<$0.15 per 1M tokens
$0.15–$1 per 1M tokens
>$1 per 1M tokens

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

No publicly available API

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

No publicly available API

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Capability Indexes

Measures the performance of models on specific capabilities and industries

Artificial Analysis Finance & Accounting Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

No publicly available API

Benchmarks

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

No publicly available API

AA-Briefcase v1.1Updated

Agentic knowledge work, (Elo-500)/2000

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

GDPval-AA v2.1Updated

Agentic real-world work tasks, (Elo-500)/2000

Humanity's Last Exam

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

Terminal-Bench 4.0

Agentic coding & terminal use

AA-LCR v1.1

Long context reasoning

SciCodeUnder review

Coding

CritPtUnder review

Physics reasoning

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

FrontierCode 1.1New

Agentic software engineering in open-source repositories

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

Harvey LAB-AA v1.1Updated

Legal agentic work, Hallucination-Gated All-Pass Rate

EnterpriseOps-Gym-AA

Agentic business operations

ITBench-AA

Kubernetes incident root-cause analysis

MLCR-AA

Medical long context reasoning

MMMU-Pro

Visual reasoning

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

AA-Briefcase v1.1Updated

AA-Briefcase Elo

AA-Briefcase v1.1 is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better

No publicly available API

AA-Briefcase Elo is a combined metric that aggregates analytical quality Elo, presentation Elo, and rubric pass rate, with rubric performance converted into Elo via synthetic head-to-head matches. Elo and 95% confidence interval bounds are clamped at 0.

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

No publicly available API

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Intelligence Index Comparisons

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Context Window

Context window: tokens limit · Higher is better

No publicly available API

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Time per Intelligence Index Task

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Latency

Measured by Time (seconds) to First Token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference (billions)

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Frequently Asked Questions

Common questions about Qwen3 32B (Reasoning)

Qwen3 32B (Reasoning) was released on April 28, 2025.

Qwen3 32B (Reasoning) was created by Alibaba.

Qwen3 32B (Reasoning) scores 7 on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 8).

Qwen3 32B (Reasoning) generates output at 27.4 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 72.7 t/s).

Qwen3 32B (Reasoning) has a time to first token (TTFT) of 1.61s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight models of similar size (median: 1.17s).

Qwen3 32B (Reasoning) costs $0.24 per 1M input tokens (somewhat higher than average, median: $0.12) and $0.54 per 1M output tokens (somewhat higher than average, median: $0.25), based on the median across providers serving the model.

Qwen3 32B (Reasoning) costs $0.24 per 1M input tokens and $0.54 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.27 per 1M tokens. Pricing may vary by provider. Compare provider pricing

Yes, Qwen3 32B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

Qwen3 32B (Reasoning) supports text input.

Qwen3 32B (Reasoning) supports text output.

No, Qwen3 32B (Reasoning) does not support image input. It can only process text.

No, Qwen3 32B (Reasoning) is not multimodal. It only supports text input.

Qwen3 32B (Reasoning) has a context window of 33k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Qwen3 32B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Qwen3 32B (Reasoning) has 32.8 billion parameters.

Qwen3 32B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use. View license

Qwen3 32B (Reasoning) achieves a score of 7 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Qwen3 32B (Reasoning) is available via API through 2 providers. Compare API providers

Qwen3 32B (Reasoning) is available through 2 API providers. Compare providers

Qwen3 32B (Reasoning) Intelligence, Performance & Price Analysis

Model summary

Verbosity

Comparison Summary

Technical specifications

142 models in this class

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index

Open Weights

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

AA-Briefcase v1.1Updated

AA-Briefcase Elo

AA-Briefcase Elo

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index

Openness Index

Artificial Analysis Openness Index: Score

Intelligence Index Comparisons

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Cost

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Cost to Run Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Cache Hit

Context Window

Context Window

Context Window for RAG

Context Window

Speed

Output Speed

Output Speed

Model Performance Representation

Time per Intelligence Index Task

Time per Intelligence Index Task

Latency

Latency: Time To First Answer Token

Time to First Answer Token

End-to-End Response Time

End-to-End Response Time

End-to-End Response Time

Model Performance Representation

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Total Parameters

Active Parameters at Inference Time

Frequently Asked Questions

When was Qwen3 32B (Reasoning) released?

Who created Qwen3 32B (Reasoning)?

How intelligent is Qwen3 32B (Reasoning)?

How fast is Qwen3 32B (Reasoning)?

What is the latency of Qwen3 32B (Reasoning)?

How much does Qwen3 32B (Reasoning) cost?

What is Qwen3 32B (Reasoning) API pricing?

Is Qwen3 32B (Reasoning) a reasoning model?

What input modalities does Qwen3 32B (Reasoning) support?

What output modalities does Qwen3 32B (Reasoning) support?

Can Qwen3 32B (Reasoning) process images?

Is Qwen3 32B (Reasoning) multimodal?

What is the context window of Qwen3 32B (Reasoning)?

Is Qwen3 32B (Reasoning) open source?

How many parameters does Qwen3 32B (Reasoning) have?

What is the license for Qwen3 32B (Reasoning)?

How does Qwen3 32B (Reasoning) perform on benchmarks?

Is Qwen3 32B (Reasoning) available via API?

Where can I use Qwen3 32B (Reasoning)?