Alibaba has launched a newer model, Qwen3 4B 2507, we suggest considering this model instead.
For more information, see Comparison of Qwen3 4B 2507 to other models and API provider benchmarks for Qwen3 4B 2507.
Qwen3 4B (Reasoning) Intelligence, Performance & Price Analysis
Model summary
Intelligence
Artificial Analysis Intelligence Index
Speed
Output tokens per second
Input Price
USD per 1M tokens
Output Price
USD per 1M tokens
Verbosity
Output tokens from Intelligence Index
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
| 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 | 32k ~48 A4 pages of size 12 Arial font |
Qwen3 4B (Reasoning) is amongst the leading models in intelligence, but particularly expensive when comparing to other open weight models of similar size. It's also slower than average and very verbose. The model supports text input, outputs text, and has a 32k tokens context window.
Qwen3 4B (Reasoning) scores 14 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (averaging 9). When evaluating the Intelligence Index, it generated 20M tokens, which is very verbose in comparison to the average of 7.0M.
Pricing for Qwen3 4B (Reasoning) is $0.11 per 1M input tokens (expensive, average: $0.00) and $1.26 per 1M output tokens (expensive, average: $0.00). In total, it cost $26.92 to evaluate Qwen3 4B (Reasoning) on the Intelligence Index.
At 90 tokens per second, Qwen3 4B (Reasoning) is slower than average (90).
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
{"@context":"https://schema.org","@type":"Dataset","name":"Artificial Analysis Intelligence Index","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"Artificial Analysis Intelligence Index v4.0 incorporates 10 evaluations: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://creativecommons.org/licenses/by/4.0/","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":""}
Artificial Analysis Intelligence Index by Open Weights vs Proprietary
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).
{"@context":"https://schema.org","@type":"Dataset","name":"Artificial Analysis Intelligence Index by Open Weights vs Proprietary","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"Artificial Analysis Intelligence Index v4.0 incorporates 10 evaluations: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://creativecommons.org/licenses/by/4.0/","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":""}
Intelligence Evaluations
While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Intelligence Index Comparisons
Intelligence vs. Price
While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Intelligence Index Token Use & Cost
Output Tokens Used to Run Artificial Analysis Intelligence Index
The number of tokens required to run all evaluations in the Artificial Analysis Intelligence Index (excluding repeats).
Cost to Run Artificial Analysis Intelligence Index
The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input and output token pricing and the number of tokens used across evaluations (excluding repeats).
Context Window
Context Window
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).
{"@context":"https://schema.org","@type":"Dataset","name":"Context Window","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"Context Window: Tokens Limit; Higher is better","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://creativecommons.org/licenses/by/4.0/","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":""}
Pricing
Pricing: Input and Output Prices
Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Intelligence vs. Price (Log Scale)
While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Pricing Comparison of Qwen3 4B (Reasoning) API Providers
Speed
Measured by Output Speed (tokens per second)
Output Speed
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 (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
{"@context":"https://schema.org","@type":"Dataset","name":"Output Speed","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"Output Tokens per Second; Higher is better","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://creativecommons.org/licenses/by/4.0/","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":""}
Output Speed vs. Price
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).
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
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 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 (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
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.
Comparisons to Qwen3 4B
- Qwen3 4B
gpt-oss-20B (high)- gpt-oss-120B (high)
- GPT-5.2 (xhigh)
Llama 4 Maverick
Gemini 3 Flash- Gemini 3 Pro Preview (high)
Claude Opus 4.5- Claude 4.5 Sonnet
Mistral Large 3
DeepSeek V3.2
Falcon-H1R-7B
Grok 4.1 Fast- Grok 4
Nova 2.0 Pro Preview (medium)- Nova 2.0 Lite (medium)
MiniMax-M2.1
NVIDIA Nemotron 3 Nano
Kimi K2 Thinking
K-EXAONE
MiMo-V2-Flash
KAT-Coder-Pro V1
K2-V2 (high)
Mi:dm K 2.5 Pro
HyperCLOVA X SEED Think (32B)
GLM-4.7- Qwen3 235B A22B 2507
- GPT-5.1 (high)